Bayesian inference for regularly spaced, latticed stationary random fields is computationally demanding. Whittle-type likelihoods in the frequency domain based on the fast Fourier Transform (FFT) have several appealing features: i) low computational complexity of only O(nlogn), where n is the number of spatial locations, ii) robustness to assumptions of the data generating process, iii) easy handling of missing data and irregularly spaced domains, and iv) flexibility in modelling the covariance function via the spectral density directly in the spectral domain. It is well known, however, that the Whittle likelihood suffers from bias and low efficiency for spatial data. The debiased Whittle likelihood is a recently proposed alternative with better frequentist properties. We propose a methodology for Bayesian inference for stationary random fields using the debiased spatial Whittle likelihood, with an adjustment from the composite likelihood literature to reduce the remaining bias in the posterior. The adjustment is shown to give a well-calibrated Bayesian posterior as measured by coverage properties of credible sets, without sacrificing the quasi-linear computation time.

Speaker: Dr Tom Goodwin (he/him)

I am a postdoctoral research fellow at UNSW under Professor Robert Kohn. I work mainly in Bayesian inference for complex time series models. My PhD was completed at the University of Technology, Sydney in spectral domain methods for Bayesian inference. My interests include Bayesian inference, time series analysis, large spatial data, and machine learning.

Over the last 10 years, Willem has worked closely with Dr Walter Baethgen from Columbia University (NY) and the Instituto Nacional de Investigación Agropecuaria (INIA) in Uruguay, to develop new tools to support sustainable water management in agriculture and forestry. Uruguay, being a small country wedged between Brazil and Argentina with an economy strongly driven by agriculture, has jumped on the opportunity to be a leading sustainable economy example. As a result, Uruguay is seen by the region as an “observatory”. This is further strengthened by a history of running long-term experiments, such as the 60-year soil carbon and agricultural rotations experiment at La Estanzuela.

The work from Willem with INIA focuses therefore on three elements:
1. Providing decision support using models to improve sustainable outcomes
2. Strengthening the long-term experiments through data analytics and modelling
3. Capacity building in water management in INIA and Uruguay

In this presentation, the highlights of the last project will be discussed in context of the overall efforts in developing Uruguay as an observatory for sustainable management.

Speaker: DARE Director, Prof Willem Vervoort (he/him)

Willem has a PhD in field hydrology from the University of Georgia in the US and Agricultural Engineering undergraduate degree from Wageningen University. He is the leading hydrologist at The University of Sydney and an expert in quantitative Hydrology and Catchment Management and simulation modelling. His main research focus is on sustainable water management to balance climate and human impacts. He has a specific interest in agricultural management and impacts.

Willem combines remote sensing, field data and simulation modelling to develop quantitative tools scaling from the field to the continent. Current projects include Bayesian model optimisation, multi-objective model optimisation, understanding model uncertainty in relation to observed water quality and quantity, and the use of satellite data to improve model structures and predictions. Recent work developed soil moisture predictions for Australia and water accounting tools from the field to the landscape.

Willem has extensive experience working with industry in projects with the Cotton industry, Grains industry, Icon water, and more recently with a European/Australian consortium of SME in the water value chain.

Co-designing landscape restoration projects with First Nations communities means more than consultation, it requires showing up on Country, understanding historical context, and building genuine relationships. This talk shares lessons from a Cultural Restoration Strategy co-developed with Traditional Owners in the Upper Hawkesbury, where restoration planning focused on flood-impacted cultural sites. By centring cultural priorities and working collaboratively from the ground up, we can create more meaningful, lasting outcomes for both people and Country.

Speaker: Dr Eliza Middleton (she/her)

Dr Eliza Middleton is a senior ecologist with almost 20 years of experience in biodiversity assessment, insect ecology, and making science accessible to a wide audience. She has a PhD in Entomology and is passionate about turning complex ecological data into clear, practical strategies that support both conservation and development goals.

Before joining Water Technology, Eliza worked at the University of Sydney, where she led projects focused on koala habitat protection, environmental accounting, and helped the university become the first in Australia to adopt nature-related financial disclosures. Her work has taken her across Australia, delivering flora and fauna surveys, impact assessments, and restoration planning, often in close partnership with Indigenous communities. Eliza is also an experienced science communicator, regularly contributing to radio and television, and is driven by a strong belief that good environmental decisions come from collaboration, clear communication, and respect for Country.

Accurate crop yield prediction and forecast is critical for precision agriculture, especially at field scale. In this seminar, approaches for improving crop yield prediction/forecast will be presented.

First, we will explore the potential of red-edge (RE) based vegetation indices, especially the Triple Red-Edge Index (TREI), for improving crop yield prediction. Using the three RE bands provided by Sentinel-2, the TREI outperformed traditional vegetation indices by integrating all three RE bands. The discussion will focus on why this index was developed and how it helped to improve the prediction of canola and wheat yield at the field scale across large regions in Australia.

Secondly, the performance of three deep learning models for wheat yield forecasting will be compared using structured and unstructured data. The advantages of spatial and temporal data representation will also be discussed.

Speaker: Dr Dhahi Al-Shammari (he/him)

Dhahi is a postdoctoral researcher in the School of Life & Environmental Sciences, the University of Sydney. Dhahi’s research interests are in modelling (e.g. crop yield and crop type models) in space and time. Specifically, he is interested in developing machine learning algorithms in agriculture for crop yield prediction, crop type mapping, and soil carbon prediction. Dhahi has completed his master’s degree in science in agriculture at the University of New England (Armidale, NSW, Australia), and a PhD at the University of Sydney.

A Shared Environmental Analytics Facility (SEAF): Translating science knowledge and data analytics into timely information for streamlined decisions

SEAF is a mechanism for interpreting environmental data that has been developed in consultation with end users and stakeholders. It enables a trusted data and information supply chain that generates information products, like maps, reports and forecasting tools for use in research and decision making.

SEAF is a collective effort between research, government and industry. The efforts are led by DARE partner, The Western Australian Biodiversity Science Institute (WABSI) and the Western Australian Marine Science Institution (WAMSI), with multiple partners providing funding, scientific and technical expertise for the development and delivery of SEAF.

• It simplifies how we access, interpret, use and manage environmental information, providing trusted, single-point access to disparate information sources, through secure data sharing.
• It draws data for use in predictive models and custom-built analytics – turning it into practical, useable information and forecasting tools.
• SEAF helps unlock value from shared data and analytics to enable users to make more informed decisions for cumulative environmental impact assessments, at a region-specific scale.
• SEAF provides the ability to understand and interpret dynamic information.
• It creates a shared, robust, repeatable and sustainable environmental information value chain.

This talk will provide an overview of SEAF, outline the science behind the integrated ecosystem model, and explain the technology platform.

Speaker: Chris Gentle (DARE Advisory Board Member)

Chris Gentle is currently the Program Director, Information Management at the Western Australia Biodiversity Science Institute. Chris has over twenty years’ experience consulting at a strategic level within the information management industry for natural resources and government sectors. He has specialised knowledge in developing and implementing location-intelligence strategies and leading ICT strategy and implementation planning for resource infrastructure capital projects. Chris has a focus on customer outcomes with his multi-disciplinary expertise gained through years of working in the data management and systems as well as the engineering services industry.

Chris holds a Bachelor of Science from The University of Western Australia, a Graduate Diploma in Technology Management and an M.B.A. from La Trobe University.

Speaker: Prof Matt Hipsey

Professor Matt Hipsey is the co-director of the Centre for Water and Spatial Science at UWA. He leads the Aquatic Ecodynamics research group at UWA’s School of Agriculture and Environment. His multidisciplinary team specialises in water quality and aquatic ecosystem model development, with applications to wetlands, lakes, rivers, and estuaries. With over 60 journal articles and 20 conference papers on modelling aquatic ecosystems, Matt is a major developer of widely used modelling software packages. His work focuses on understanding the impacts of climate change and land-use change on environmental processes and habitats, providing valuable insights for managing aquatic ecosystems.

Speaker: Brendan Busch 

Brendan Busch is a Senior Research Engineer for the Aquatic EcoDynamics (AED) Research group at the University of Western Australia (UWA). Mr Busch’s primary focus is on data engineering and visualisation of complex numerical models. In his current capacity, Mr Busch is tasked with designing and creating data and model analytics solutions for environmental assessment. His specialisation lies in MATLAB, but he also utilises a variety of languages and platforms within the realm of analytics and Geographic Information Systems (GIS). Mr Busch also works with the Western Australia Marine Science Institute (WAMSI) as the technical lead in the development of the Shared Environmental Analytical Facility (SEAF) – a cloud-based platform that facilitates the sharing and curation of environmental data for industry stakeholders and regulators being designed in conjunction with Microsoft, PwC and other industry leading players.

Soil moisture plays a critical role in hydrological processes, agricultural productivity, and climate dynamics. However, capturing its spatial and temporal variability remains a major challenge due to limitations in current monitoring systems. This presentation explores recent advancements in soil moisture monitoring, with a focus on integrating in-situ observations, remote sensing technologies, and data-driven modelling approaches. We highlight a method for localising machine learning models to enhance the resolution, accuracy, and scalability of existing soil moisture data. In addition, we discuss the potential of self-supervised learning models to forecast future soil moisture levels. These advancements aim to support better soil and water management under changing environmental conditions.

Speaker: Marliana Widyastuti (she/her)

Marliana Tri Widyastuti is a PhD student at the University of Sydney specialising in digital soil mapping, with a focus on the spatial modelling of soil properties. Her research integrates geospatial data, machine learning, and environmental variables to improve the accuracy and usability of soil information for land management and agricultural planning.

A research-driven approach has informed Alcoa’s continuous improvement of rehabilitation in WA’s Northern Jarrah Forest for more than 40 years. Research has focused on site preparation, topsoil return, fertiliser, seed biology and horticultural practices to return plants. The return of fauna to rehabilitation has been studied, most recently using cameras and GPS collars. Significant factors contributing to the success of this research program include an inhouse research team, long-term commitment to research trials, and ongoing collaboration with Australian research institutions. Alcoa’s research program not only sheds light on ways to continuously improve rehabilitation and biodiversity return in the Northern Jarrah Forest, but also offers valuable insights into restoration globally.

Speaker: Dr Lucy Commander

Lucy has over 20 years of experience in environmental research, mine rehabilitation and science communication. Working in the government, NGO and university sectors, she has undertaken research at mine sites across Western Australia with a particular focus on seed-based restoration, edited several national practitioner guidelines and enjoys organising workshops and symposia to share knowledge. Lucy has worked at Alcoa for over two years, leading the Forest Research Centre and managing research projects to enable continuous improvement to environmental practices.

In this talk, I will demonstrate the application of various data-driven techniques for modelling hydrological droughts. The talk will be structured into three segments. The first segment will focus on non-stationary modelling of drought characteristics in relation to large-scale modes of climate variability such as the ENSO, IOD, and SAM. This will involve fitting probability distributions to drought characteristics, where the parameters of these distributions vary as functions of climate driver indices. These models will be used to infer how drought characteristics change under different phases of these climate modes. The second segment will showcase the use of Hidden Markov Models to investigate regime shifts in streamflow during drought periods. In the third segment, I will present the use of Random Forest algorithms to identify predictors of streamflow losses during flash droughts. The talk will conclude with a summary of the applications, strengths, and limitations of these data-driven techniques, as well as potential future directions for leveraging such methods to enhance our understanding of droughts.

Speaker: Dr Pallavi Goswami

Dr Pallavi Goswami is a Postdoctoral Research Fellow in the School of Earth, Atmosphere and Environment at Monash University, Australia. Her research focuses on understanding droughts (meteorological/hydrological/agricultural), their onset timeframes (flash vs slow), processes, characteristics, drivers, and their compounding/cascading with other hazards such as floods (drought-to-flood transitions), etc. Her present research is part of the Climate Systems Hub of the National Environmental Science Program (NESP), funded by the Australian Government. Dr Goswami did a joint PhD with Monash University (Australia) and IIT Bombay (India) in hydrology and water resources. Her interests include extreme events, non-stationarity of weather hazards, and hydro-climatic changes & variability. She is also interested in understanding future projections of extreme events, including implications for adaptations.

First-order optimization methods, particularly stochastic gradient descent, are the primary workhorse in machine learning (ML) for their historically low per-iteration costs. Recent theoretical advancements, including rapid convergence in overparameterized scenarios, implicit regularization, and the emergence of network architectures like skip connections, have solidified their dominance in ML. Nonetheless, sensitivity to hyperparameter tuning, susceptibility to saddle point entrapment, slow convergence in rugged landscapes with smaller networks, and inefficiency in constrained and distributed optimization settings remain significant challenges for these methods.

Second-order methods, on the other hand, can attain superior convergence rates, overcome non-convexity and ill-conditioning, effectively handle constraints, and exploit parallelism and distributed architectures in novel ways. However, their non-trivial sub-problems as well as high per-iteration costs continue to limit their wide-spread usage. In light of this, I will provide an overview of ongoing research into efficient, robust, and scalable second-order optimization algorithms for ML. To that end, I will focus Newton-MR variants, a novel class of Newton-type methods, that offer many desirable theoretical and practical properties and have the potential to surpass first-order methods in the next generation of optimization methods for large-scale machine learning.

Speaker: A/Prof Fred Roosta-Khorasani

Fred Roosta is an associate professor in the School of Mathematics and Physics at the University of Queensland (UQ). In addition, he is a chief investigator and a theme leader with the ARC Training Centre for Information Resilience (CIRES). Prior to joining UQ, he was a post-doctoral fellow in the Department of Statistics at the University of California, Berkeley. He obtained his PhD from the University of British Columbia in 2015.

Fred’s research interests and prior works span several areas of applied mathematics and computer science, including machine learning, numerical optimization, scientific computing, computational statistics as well as distributed and high performance computing. He is generally interested in studying various theoretical and algorithmic aspects of solving modern data analysis problems. In 2018, he was awarded the Discovery Early Career Researcher Award (DECRA) by the Australian Research Council for his research on second-order optimization for machine learning.

This presentation will comment on the importance of data management plans in supporting the management of data created by a research project. It will describe how the FAIR and CARE principles can be applied and used within a data management plan. Discussion on why FAIR and CARE should be considered for the management of data will be presented.

A data management plan is a document that allows you to record intended and expected details related to the data that will arise from your research project. A data management plan is a living document for a research project, which outlines data creation, data policies, access and ownership rules, management practices, management facilities and equipment, and who will be responsible for what. Nowadays they are seen as a mandatory component when embarking on a research project.

FAIR is a principles approach to data management. It promotes elements to help ensure good data management. Researchers spend considerable time, money and effort collecting and interrogating data. Making your data findable, accessible, interoperable and reusable (FAIR) maximises the impact of that investment, including gaining more citations for your data sets.

The CARE principles describe how data should be treated to ensure that Indigenous governance over the data and its use are respected. The CARE principles reflect the crucial role of data in advancing Indigenous innovation and self-determination. They ensure that data movements like the open data movement respect the people and purpose behind the data. FAIR and CARE are two components of data management that should be considered and mentioned when creating a data management plan.

Speaker: Dr Robin Burgess

Robin Burgess is the Manager of the Engagements Team at the ARDC (Australian Research Data Commons). He has a strong background and real interest in all aspects of research data management, particularly planning, publishing, governance and of course the application of the FAIR and CARE principles.

Robin has a PhD in Biosciences where he focused on data management techniques and a love of arts related data having worked at the Glasgow School of Art for 6 years. Robin moved to Sydney 8 years ago taking up roles as a Repository and Digitisation Manager at Sydney University, followed by a Senior Research Data Librarian at UNSW. Robin’s passion and interest in data and its management continues to grow in his role at the ARDC.

Regional geophysical datasets underpin our ability to build 2D and 3D geological models across much of the world, where surface expressions of geology are limited. In this talk we will explore the range of methods from purely interpretive to Machine Learning that are currently used to build geological models. We will primarily focus on airborne magnetic data sets, however the logic applies to a whole range of geophysical methods.

Speaker: Professor Mark Jessell, DARE Senior Academic Domain Advisor

Mark Jessell is a Professor and Western Australian Fellow at the Centre for Exploration Targeting at The University of Western Australia. Mark studied up to MSc level in the UK, then moved to the USA to do a PhD, went to Melbourne to do a Postdoc and take up a teaching and research position at Monash University before moving to Toulouse, France taking up a position with the Institute de Recherche pour le Developpement, before joining the University of Western Australia in 2013.

Mark’s scientific interests revolve around microstructure studies (the Elle platform), integration of geology and geophysics in 3D (the Loop/MinEx CRC project), and the tectonics and metallogenesis of the West African and Guyanese Cratons (WAXI & SAXI).

Mark has extensive experience collaborating with the minerals sector though AMIRA International industry consortium funding for the WAXI and SAXI projects and the MinEx CRC; a partnership between industry and the Australian Government. Mark is also involved in a MRIWA industry/state government collaboration on the Paterson Orogen which is supported by funding from the ARC, MRIWA and industry.

Recent advances in sensing have augmented ore discovery, mining and sorting procedures that promise to improve the effectiveness and sustainability of mining operations. While these activities operate at different spatial and temporal scales, combining posterior models can further benefit the sustainability of exploration and mining operations. Discovering the combination of data and modelling techniques that operate across scales to achieve reliable predictions takes time and effort.

Traditionally, we use geophysics at the regional (100s km) to camp (10s km) scales. Geophysical datasets, like gravity and magnetics can be interpreted to identify geological structures that help us discover mineral deposits. The utility of geophysics at these scales means they are almost ubiquitous features for machine learning models that predict locations of mineralisation at different scales. We use petrophysics to make sense of our interpretations as properties like density and magnetic susceptibility form a critical knowledge link between geophysics and geology. For example, density data helps with gravity data and is an important rock property for many activities in the minerals value chain. This presentation presents the challenges, potential solutions and benefits for data integration in the minerals value chain.

Speaker: Dr Mark Lindsay, DARE Domain Lead – Minerals

Mark Lindsay completed his BSc (Honours) at Monash University in 2008 and graduated from his PhD at Monash University and Université Paul Sabatier (Toulouse III) in October 2013.

He is currently a Science Leader at the CSIRO and leads “Minerals 4D” and digitalisation of the mining value chain. Mark is also an Adjunct Senior Research Fellow in the School of Earth Sciences, Centre for Exploration Targeting, at the University of Western Australia. His research interests include complex Earth systems, knowledge management and representation, uncertainty and ambiguity in 3D geological and mineral exploration modelling, and the process and psychology of data interpretation. These themes are an important field of research that have the potential to have a large impact on current practices of deterministic modelling and risk assessment.

Mark is working toward a stochastic approach to modelling that attempts to understand the importance of different data types in answering geoscientific questions, and how knowledge and associated uncertainties propagate through the mining value chain.

El Niño-Southern Oscillation (ENSO), the phenomenon that gives rise to El Niño and La Niña events, has long been a subject of study by applied mathematicians. This phenomenon is a quasi-periodic oscillation between El Niño (warm) and La Niña (cool) events which occur every 2-7 years via air-sea coupled processes in the ocean and atmosphere of the equatorial Pacific. These events, by perturbing patterns of atmospheric circulation, produce changes to local weather on every continent, making this a phenomenon with global consequences.

The physical processes that give rise to ENSO have characteristics of chaotic systems, while also displaying a range of spatial and temporal patterns. In this talk, I will discuss three very different mathematical framings of the tropical Pacific system: first, as a dynamical system with regime-like behaviours; second, as a discrete system with three different states; and third, using Bayesian quantile regression to characterize spatial changes to the system over time. Each of these lenses has resulted in new insights into how to predict ENSO and understand how it is changing over time.

Speaker: Dr Nandini Ramesh

Dr Nandini Ramesh is a Senior Research Scientist in Natural Hazards and Climate Risk at Data61, CSIRO. She received her PhD in Ocean and Climate Physics from Columbia University as a NASA Earth and Space Science Fellow. She then worked as a Postdoctoral Scholar at the University of California, Berkeley, following which she was a Research Fellow and Chief Investigator at the ARC Centre for Data Analytics for Resources and the Environment at the University of Sydney.

Her research focuses on the physics of tropical climate on seasonal to decadal timescales, with a particular interest in the impacts of large-scale phenomena such as El Niño and La Niña events and monsoons on rainfall. She uses a range of techniques spanning dynamical systems theory, machine learning, computational fluid dynamical modelling and geospatial data analysis to answer questions about fundamental physical processes and the predictability of these phenomena.

This seminar explores the transformative potential of Large Language Models (LLMs) in revolutionising the development of advanced materials. By comparing LLMs with conventional machine learning techniques, we highlight their unique capabilities in multi-task learning, processing and generating predictions in universal formats, and leveraging vast amounts of text data to address complex questions in material development.

We propose integrating LLMs into the early stages of materials science research, enabling a paradigm shift in material recommendation and analysis. Real-world examples demonstrate how LLMs have accelerated discovery while acknowledging limitations and risks. This seminar aims to inspire researchers to embrace the potential of LLMs in materials science and foster collaboration between AI and materials science communities to unlock new frontiers in advanced materials development.

Speaker: Tong Xie

Tong Xie is a PhD candidate at the School of Photovoltaic and Renewable Energy Engineering (SPREE), UNSW Sydney, acclaimed as one of Australia’s National Computational Infrastructure’s Top 10 HPC AI-Talents. As the CEO of GreenDynamics and the Group Lead of UNSW AI4Science, he is pioneering the use of Generative AI to accelerate the discovery and development of sustainable materials. His expertise extends to Natural Language Processing and Material Science. He also founded the DARWIN natural science language model, demonstrating his innovative approach to advancing AI in material sciences.

Since the early days of analysing digital images, researchers have tried to automatically extract meaning from the images by both enhancing them for better interpretation by the human eye and brain and by automatically extracting features from the images themselves. One of the drawbacks of using feature extraction methods that search for specific shapes (e.g. lineaments) in natural scenes such as geophysical data is that geological datasets are complex and do not follow simple rules. Additionally, different features across multimodal datasets (e.g. gravity and magnetics) may correspond to the same underlying geology.

What if we adopt an alternative approach by segmenting and organising the naturally occurring features within these multimodal gridded datasets into a collection of maps, thus allowing a subject matter expert to “navigate” in search of insights and meaning?

In this study, we propose a hybrid method that attempts to cluster features within small image patches and provide these clusters in a manner that allows the earth scientist to interpret these clustered images using their prior knowledge of the region. Specifically, we explore the use of Haralick texture descriptors to encode the information within the patches from gravity and magnetic images, and t-SNE for the nonlinear (2D) projection to build a t-SNE atlas for organising multimodal geophysical information in a sensible way, allowing a subject matter expert to “navigate” large datasets in search of insights and meaning. Also, the Haralick texture representation of the image patches from magnetic and gravity data provides a straightforward way to combine the different types of geophysical data (ie, feature fusion of multimodal data).

Our approach is demonstrated on a large region in Western Australia, spanning hundreds of thousands of square kilometres. We also explore its application in three further scenarios: (1) interpreting massive synthetic datasets for machine learning applications, (2) analysing hundreds of thousands of 3D models sampled to explore the space of geophysical models derived from emerging techniques such as trans-dimensional inversions, and (3) understanding the relationship between the structure and composition of small rock samples using x-ray fluorescence.

Speaker: Dr Leonardo Portes, DARE Post Doctoral Research Fellow

Leonardo holds a Bachelor and a Master of Physics from the Universidade Federal de Minas Gerais (UFMG/Brazil) where he also completed a multidisciplinary PhD in Sport Sciences, focusing on the nonlinear time-series analysis of human motor behavior.

He joined The University of Western Australia (UWA) in 2018 as a Research Fellow in the Department of Mathematics and Statistics. His work is characterised by its interdisciplinary breadth, incorporating elements of statistical physics, complex systems science, and data analytics to address real-world challenges across various sectors, including resources, sports, and medical data analysis. He has contributed to data science projects and training for companies such as Rio Tinto, Anglo American, and Woodside, which led to his recognition with the prestigious Australian Global Talent Visa in Data Science/DigTech in 2021.

Currently, Leonardo is a Senior Research Fellow at DARE within the Department of Mathematics and Statistics at UWA. He is also affiliated with UWA’s Centre for Exploration Targeting. His research interests lie in the integration of network science, dynamical systems, nonlinear time series analysis, data visualization, and machine learning to develop robust analytical tools that enhance decision-making processes. He is currently developing innovative data visualisation tools aimed at organising multimodal geophysical information in a sensible way, allowing subject matter experts to “navigate” large datasets in search of insights and meaning. Additionally, he provides mentorship in data science and Python programming to PhD candidates.

This talk will describe insights gained from a decade of autonomous marine systems development at the University of Sydney’s Australian Centre for Field Robotics. Over the course of this time, we have developed and deployed numerous underwater vehicles and imaging platforms in support of applications in engineering science, marine ecology, archaeology and geoscience. We have operated an Australia-wide benthic observing program designed to deliver precisely navigated, repeat imagery of the seafloor. This initiative makes extensive use of Autonomous Underwater Vehicles (AUVs) to collect high-resolution stereo imagery, multibeam sonar and water column measurements on an annual or semi-annual basis at sites around Australia, spanning the full latitudinal range of the continent from tropical reefs in the north to temperate regions in the south.

The program has been very successful over the past decade, collecting millions of images of the seafloor around Australia and making these available to the scientific community through online data portals developed by the facility and affiliated groups. These observations are providing important insights into the dynamics of key ecological sites and their responses to changes in oceanographic conditions through time. We have also contributed to expeditions to document coral bleaching, cyclone recovery, submerged neolithic settlement sites, ancient shipwrecks, methane seeps and deepwater hydrothermal vents. The talk will also consider some of our more recent work focused on developing automated tools for working with this imagery and illustrate how this is being used to inform further exploration work using these platforms.

Speaker: Professor Stefan Williams

Professor Stefan Williams is the Director of the Digital Sciences Initiative at the University of Sydney. He is also the Professor of Marine Robotics at the University’s Australian Centre for Field Robotics (ACFR) where he leads research in the field of marine robotics.

Physics-based models, such as hydrodynamic models, are crucial for accurate flood prediction. However, setting up and running high-resolution flood models is often computationally expensive and time-consuming. This limitation hinders the use of hydrodynamic models in real-time forecasting and probabilistic analyses, where numerous model simulations are required. Conversely, pure machine learning models, employed as surrogate models, offer both computational efficiency and prediction accuracy. Despite these advantages, they often lack explainability regarding the underlying mechanisms of their predictions.

In this study, we introduce a novel physics-informed machine learning model, termed Hy-NET, designed for rapid high-resolution flood mapping. According to the Theory-Guided Data Science (TGDS) taxonomy, Hy-NET is classified as a hybrid TGDS model. Hy-NET is a U-NET-based deep learning model that leverages low-resolution hydrodynamic model predictions as initial estimates, subsequently upskilling them to align with high-resolution model outcomes. A low-resolution model operates significantly faster than a high-resolution model for the same study area, due to fewer computational cells and the ability to use larger computational time-steps. Despite these differences, the results of low-resolution models are largely correlated with those of high-resolution models.

The Hy-NET model utilises low-resolution images of 512×512 pixels, along with corresponding digital elevation models, as its inputs. In the context of artificial intelligence (AI), Hy-NET falls under the umbrella of generative AI, as it generates new images that resemble the given training dataset. The proposed approach has been tested on three Australian watersheds: Wollombi, Burnett River, and Chowilla. The HEC-RAS model is employed to generate both low-resolution and high-resolution flood maps for model training and testing. While being much more computationally efficient than high-resolution models, the Hy-NET model demonstrates significant upskilling capability, achieving results that closely match high-resolution flood model outputs in terms of water depths and flood inundation extents.

Speaker: Dr Viraj Vidura Herath

Viraj Herath is a Senior Researcher at Macquarie University within the Faculty of Science and Engineering, a role he has held since December 2023. A civil engineer with a specialization in water resources, Viraj’s research focuses on physics-informed machine learning, flood modelling, and rainfall-runoff modelling.

In 2015, Viraj completed his BSc in Engineering at the University of Peradeniya, Sri Lanka, where he was awarded the Ceylon Development Engineering Prize for Best Performance in Civil Engineering. He then worked as a temporary lecturer in the Faculty of Engineering at the same university for one year.

In 2017, Viraj was awarded the President’s Graduate Fellowship from the National University of Singapore to pursue his PhD studies. He earned his PhD in 2021 with a thesis titled “Hydrologically Informed Machine Learning for Rainfall Runoff Modelling.” Prior to his current position in Australia, Viraj served as a Senior Hydraulic and Hydrological Modeller at the Hydroinformatics Institute in Singapore for three years.

Speaker: Professor Lucy Marshall, DARE Deputy Director

Lucy Marshall is Executive Dean of Faculty of Science and Engineering at Macquarie University in Sydney.

Lucy received her Bachelor of Civil Engineering in 2001, Master of Engineering Science in 2002 and her PhD in Civil and Environmental Engineering in 2006, all from the University of New South Wales (UNSW) in Sydney. From 2006-2013 she was Associate Professor of Watershed Analysis at Montana State University, working at the interface of engineering and environmental science in quantifying uncertainty in hydrologic and environmental systems.

Following this she was Director of the Water Research Centre in the School of Civil and Environmental Engineering and Associate Dean of Engineering (Equity and Diversity) at UNSW.

Lucy’s technical expertise is in hydrologic modelling, model optimisation, and quantification of uncertainty in water resources analysis. Lucy is an expert in Monte Carlo methods, Bayesian inference, and associated methodologies aimed at improved uncertainty analysis of water resources modelling and the assessment of uncertainty in water resources.

How is Geophysics Correlated with Geochemistry?
Toward a Quantifiable Understanding of the Link Between Geophysics and Geochemical Isotopes
Geophysics and geochemistry are fundamental tools for studying geodynamic processes. Each records the spatial and temporal scales of Earth’s properties. Geophysics provides large-scale coverage with a snapshot of modern-day Earth properties, while geochemical data offer valuable time-integrated information but are limited by their spatial coverage. Recent years have seen an increase in the spatial coverage of geochemical isotope mapping (e.g., U-Pb, Sm-Nd), presenting an opportunity to link these two types of datasets. The spatial distribution of isotope maps has been correlated with geophysics; however, these correlations are made only qualitatively and lack a quantified statistical relationship. Here, I use a tree-based machine learning approach to quantify the link between geophysics and geochemistry. The feature importance provides a quantifiable matrix to link them. The resolved correlation suggests a high spatial variability of these correlations, indicating that simple correlations between isotope map boundaries and geophysics may not be universally applicable. Instead, it provides both a challenge and an opportunity to understand the complex Earth system.

Speaker: Dr Lu Li
Lu Li is a geophysicist and postdoctoral research associate at the University of Western Australia. He is currently working on using geophysics to understand the basin evolution in the North Australia Craton. He obtained his PhD from UWA, studying the lithosphere properties of Antarctica and their impact on cryosphere and solid-earth interactions. He is interested in using geophysics to understand natural resources, tectonics, and ice dynamics.

Plate Tectonic Limits on the Assembly of Cratonic Australia
Continuous Proterozoic plate reconstructions consistent with plate geodynamics were designed to reconcile data, conceptual models, and human imagination as applied to the assembly of the Australian craton. The reconstructions were created using GPlates and considered available magmatic and metamorphic UPb zircon data. Two tectonic scenarios for the Paleo- to Mesoproterozoic assembly of the cratonic lithosphere of Australia were tested for their geodynamic and geochronological viability. The scenarios are founded on tectonic events that are relatively well-established and well-supported by data, but also with several periods and areas that are disputed mostly due to scarcity of data. For these scenarios, we test geodynamic criteria to explore a) which possibilities are better supported by our geodynamic criteria, and b) the implications of those models for the larger-scale plate tectonic setting. The time frame in this model set includes assembling two supercontinents, Nuna (1900–1800 Ma) and Rodinia (1300–900 Ma), and the transition between them. Model 1 presents a progressive assembly of the Australian continent between 2000 Ma and 1300 Ma, showing events in the West Australian Craton (WAC), the convergence of the WAC and the North Australian Craton (NAC), and then accretion at the margin of the South Australian Craton and NAC until collision in the Albany-Fraser Orogen (AFO). Model 2 suggests WAC was separate from the rest of the Australian Craton until 1300 Ma and all combined in one orogenic cycle. It proposes Andean-type subduction along the E and NE margins of the WAC for 40–60 million years as the means of final assembly. Both models are geodynamically plausible, yet each lacks sufficient data support to conclusively resolve the differences and deepen our understanding of the Proterozoic assembly of Australia.

Speaker: Dr Weronika Gorczyk
Weronika Gorczyk is a senior research fellow at the Centre for Exploration Targeting at the University of Western Australia. Her research interest includes geodynamics of mantle/crust interactions in all tectonic environments, basin evolution and data analytic. Over last 5 years she has been leading basin oriented projects.

Airborne geophysics can provide useful information that can assist in large scale geological mapping. However, this data can be hard to interpret, especially when there is limited ground truth due to varying cover thickness. Here, we demonstrate how computer vision based feature extraction combined with unsupervised community detection models can be used to identify areas with similar geological textures to aid in interpretation and mapping.

In this study, a pre-trained convolutional neural network (CNN) model was used to extract textural information from the airborne geophysics. A uniform manifold approximation and projection (UMAP) was fitted to the data to reduce the dimensionality and graph the relationships.

Community detection algorithms can use the graph produced by the UMAP to detect groups with similar properties. We tested the Louvain (using both Potts and Dugue modularities), Leiden and Walktrap algorithms using gravity and total magnetic intensity (TMI) data from an area of the Gawler Craton in South Australia. The results were compared to the mapped Archean to Early Mesoproterozoic geology to assess model performance.

Speaker: Dr Katie Silversides

Katie Silversides is a data scientist and geologist at Datarock. She works in the applied science team, solving mining and exploration problems using a combination of domain expertise and advanced machine-learning techniques.

Katie completed her PhD in Geology at the University of Sydney. She then worked at the Rio Tinto Centre for Mine Automation, working on applying machine learning to solve different problems relating to orebody geology. This was followed by a position in DARE working on geology and hydrology projects, focusing on missing data, uncertainty and model selection.

Vegetation is crucial for the health of environment – it stabilises soil, supports beneficial pollinators and other animals, purifies water, stores carbon, and provides food and habitat for biodiversity. The Australian continent supports a vast array of ecosystem types, yet we lack sufficient data to be able to understand how these ecosystems work at both large temporal and spatial scales. Whilst Australia is at the forefront of climate change, there is an urgent need for such information to inform environmental management and climate actions.

This talk will first provide a bit of context on how we use various approaches to track vegetation growth from space using satellite remote sensing data, ground measurements, and citizen science data. Then move on to discuss why Australia lacks vegetation phenology information, and how we improved that. Finally, a case study regarding grassland species distribution to demonstrate how we could use such nation-wide vegetation phenology information for agriculture, biodiversity, and climate change research and management.

Speaker: Dr Qiaoyun Xie

Dr Qiaoyun Xie, or Dr X, is a geospatial scientist and a Lecturer at the School of Engineering, The University of Western Australia. Dr. X and her lab ‘take the pulse of nature’ by using geographical information systems and remote sensing technologies to monitor vegetation dynamics and its interactions with climate.

Using satellite data, or what she describes as her ‘eyes in the sky’, along with field measurements, she tracks ecosystem dynamics, especially plant growth. Her research on ecosystem monitoring focuses on vegetation parameter retrieval; vegetation dynamics; vegetation phenology and shifting seasonality with climate variability; land surface responses and their interactions with climate; and land use activities and major disturbance events.

Currently, her research involves using remote sensing and field measurements to understand the phenology patterns and carbon dynamics of vegetation across Australian landscapes, including vegetation resilience and resistance to droughts. Her research reported ground-breaking evidence of climate change impacts on Australian grassland composition, which is key to informing fire, agriculture, and pollen management to improve human life quality and mitigate health threats.

Reliability Inference with Extended Sequential Order Statistics by Tim Pesch

In this presentation I will address the complexity of non-identical components in multi-component, load sharing systems. For most technical systems the assumption of heterogeneous components is reasonable since components are either of different type or vary in their functions within the system. While most reliability related work resorts to the assumption of homogeneous components, I aim to address the often more realistic assumption of heterogeneous components extending the model of so called ‘Extended Sequential Order Statistics’ by two novel inferential methods.

Firstly, the derivation of Maximum Likelihood Estimates (MLE’s) of the underpinning model parameters, and secondly, the introduction of a likelihood ratio test which can decide on whether components can be assumed identical. Both methods are powerful tools in reliability contexts. The former increases our understanding of component behaviour, especially upon failure of other components. This knowledge empowers system operators to make better decisions regarding maintenance schedules and failure time prediction. The latter supports operators in their quest of identifying component equivalence.

Speaker: Tim Pesch

Tim is a mathematician with experience in reliability probability estimation. He completed his studies in mathematics with a focus on frequentist statistics at RWTH Aachen University in Germany. His Master thesis featured the combination of two well established models in reliability theory, the Stress-Strength model and the Competing Risk model, in the presence of censored data. His research yielded maximum likelihood-estimators for model parameters as well as the reliability probability under an exponential assumption, amongst other inferential results.

Conveyor Belt Wear Forecasting through a Bayesian Hierarchical Modeling Framework using Functional Data Analysis and Gamma Processes by Ryan Leadbetter

Reliability engineers make critical decisions about when and how to maintain conveyor belts, decisions that can significantly impact the production of the mine. The engineers use thickness measurements across the belt’s width to justify these decisions. However, the current approaches to forecast the wear of the conveyor belts are naive and throw away valuable information about the special wear characteristics of the conveyor. We have developed a new method for forecasting belt wear that retains the wear profile’s spatial structure and considers the wear rate’s heterogeneity – caused by operation and ore body composition variations.

Speaker: Ryan Leadbetter

Ryan is a mechanical engineer who is now undertaking a PhD in applied statistics through the Centre for Transforming Maintenance Through Data Science. Ryan’s PhD focuses on the predictive maintenance of overland iron ore conveyors. More specifically, he focuses on using condition monitoring and maintenance data to inform decisions on how and when to maintain mining machinery.

There has been a lot of recent interest in various computational methods that allow one to extract models of the deterministic evolution operator of a dynamical system from time series data. These methods have become increasingly successful as they are able to leverage increasing computational resource available today. I will start by contrasting these efforts against some earlier attempts to do this (including some of my own) and then move on to describe our recent work with reservoir computers.

Viewed in this setting, reservoir computers are a pattern generator which appear particularly appropriate to the task of reconstructing dynamics as their memory mimics the role of Takens’ theorem in delay reconstruction. I will briefly explore some of these ideas and finish by describing our attempts to quantify the performance of reservoirs and apply them to modelling tasks in industrial settings.

Speaker: Professor Michael Small 

Michael Small is the CSIRO-UWA Chair of Complex Systems and a former Future Fellow. He is the Deputy Editor-In-Chief of the Journal Chaos, and Main Editor of Physica A. He is a Chief Investigator of the ARC Industrial Transformation Training Centre for Transforming Maintenance Through Data Science, the Industrial Transform Research Hub for Transforming energy Infrastructure through Digital Engineering, and the Medical Research Future Fund project for Transforming Indigenous Mental Health and Wellbeing.

When he is not transforming things, his research relates to complex systems, network science, dynamical systems and chaos, and focusses on data-driven approaches to understanding dynamical systems.

Suppose you get a set of (independent) data points in some discrete but huge domain {1,2,…,k}, and want to determine if this data is uniformly distributed. This is a basic and fundamental problem in statistics, and has applications in computer science, not all made up: from testing the mixing time of a random walk, to detecting malicious changes in a data stream, to selecting a good algorithm depending on the input distribution.

The goal, of course, is to perform this task efficiently, both time- (time complexity) and data-wise (sample complexity). In this talk, I will survey and discuss seven algorithms for uniformity testing, and explain some of their advantages and disadvantages.

Speaker: Dr Clément Canonne

Dr Clément Canonne is a Lecturer in the School of Computer Science at the University of Sydney, where he does research in theoretical computer science. His main research interests lie in property testing, learning theory, and, more generally, randomised algorithms and the theory of machine learning.

Prior to joining the University of Sydney, Clément was a Goldstine postdoctoral fellow at IBM Research Almaden, and a Motwani fellow at Stanford University. He obtained his Ph.D. from Columbia University in 2017.

Global climate change has altered precipitation patterns and disrupted the characteristics of drought and rainfall events. This, combined with nutrient and grazing practices in grasslands, will likely expose vegetation to conditions beyond their adaptive capacity, altering biodiversity and productivity, and changing ecosystem function. Knowledge on how grasslands respond to these pressures, and their potential to recover, is needed to maintain essential ecosystem services in the future.

In this talk, I will introduce my PhD research and present some of the findings from my project to date. I will describe how we used a new drought tracking technique to characterise the spatiotemporal dynamics for past drought and rainfall events in Australia. I will also present some preliminary results from our field experiment, including how grassland productivity and diversity respond to extreme precipitation, nutrient addition, and cattle grazing.

Speaker: Elise Verhoeven

Elise is a PhD candidate with the School of Life and Environmental Sciences at The University of Sydney. Elise is interested in how plant communities respond to disturbances, and which plants could be important for maintaining ecosystem function under global change conditions. Her PhD research is looking at the interactive effect of extreme precipitation (drought and rain), nutrient addition, and cattle grazing on the structure, productivity, and ecosystem function in grasslands in north-west NSW.

In this talk, I describe an approach to modelling social networks that has its origins in models for interactive spatial processes, including in plant ecology. The approach construes global network structure as the outcome of dynamic, potentially realisation-dependent processes occurring within local neighbourhoods of a network. I describe a hierarchy of models implied by the approach and note that they can be estimated from partial network data structures obtained through certain types of network sampling schemes. I illustrate how these models enhance our capacity to model observed human networks and present an example of their application to the transmission of an infectious disease.

Speaker: Professor Philippa “Pip” Pattison AO (Chair of DARE Advisory Board)

A quantitative psychologist by background, Professor Pattison began her academic career at the University of Melbourne. She served in a number of academic leadership roles at the University of Melbourne, including president of its Academic Board from 2007-2008 and Deputy Vice-Chancellor (Academic) from 2011-2014 before taking up the role in 2014 of Deputy Vice-Chancellor Education at the University of Sydney. During her term, Pip led the University’s strategy for learning and teaching, with a major focus on transformation of the undergraduate curriculum, the student experience and new approaches to postgraduate education and microcredentials. Pip retired from the role at the end of 2021.

The primary focus of Professor Pattison’s research is the development and application of mathematical and statistical models for social networks and network processes. Applications have included the transmission of infectious diseases, the evolution of the biotechnology industry in Australia, and community recovery following bushfire.

Professor Pattison was elected a Fellow of the Academy of the Social Sciences in Australia in 1995 and of the Royal Society of NSW in 2017.

Professor Pattison was named on the Queen’s Birthday 2015 Honours List as an Officer of the Order of Australia for distinguished service to higher education, particularly through contributions to the study of social network modelling, analysis and theory, and to university leadership and administration.

Coastal science and engineering is a relatively young field and historically has lacked sufficient data to be able to understand how this complex earth system works at both large temporal and spatial scales. Yet, with a large portion of the world’s population living within 50km of the coastline, we are being asked to provide advice and understanding on how coastlines will change into the future.

This talk will first provide a bit of context on just how data sparse our field is, and how we are now engaging and rapidly trying to catch up to our hydrological colleagues. We will discuss how we are applying basic machine learning techniques to improve our ability to predict coastal change at a variety of timescales of interest to the public, from individual storms, to where the coast might be by 2100.

The talk will be aimed at a broadscale (non-expert) audience, discussing the challenges associated with trying to model the coastline, and the techniques we have so far applied, and we’d love thoughts and ideas from the audience as well.

Speaker: Associate Professor Kristen Splinter

Kristen is an ARC Future Fellow and Deputy Director of the Water Research Laboratory at UNSW Sydney. Her work encompasses a wide range of coastal topics examining sandy beach evolution from storms to multiple decades. She has developed a number of behavioural type numerical models to predict sandbar and shoreline evolution and the focus of her Fellowship will be to develop regional scale models for long-term shoreline prediction, along the embayed coastlines of NSW. She’s been dipping her toes into machine learning since about 2015 but her students are the real experts.

Speaker: Patrick ‘Kit’ Calcraft

Kit is a DARE affiliated PhD candidate in his first year working on machine learning methods for shoreline prediction, including bridging the gap between physics and ML. He is co-supervised by Associate Professor Kristen Splinter, Dr Josh Simmons (DARE) and Professor Lucy Marshall. He will present an overview of what he’s been up to in year 1 of his PhD.

Ensemble Kalman type methods have seen an explosion in use in data assimilation applications and more recently for a range of learning tasks. Despite their desirable stability properties, they are not consistent with Bayes theorem for non-linear, non-Gaussian systems.

Recently, a range of controlled particle filters have been proposed which aim to emulate the structure of Ensemble Kalman type methods whilst simultaneously providing consistent samples in the asymptotic limit. More specifically, such filters involve constructing a control law to steer particles such that the corresponding probability distribution satisfies a variational Bayes formula.

I will provide an overview of this new class of filters and how they can be used for nonlinear ensemble data assimilation and Bayesian inverse problems. A framework which allows to derive these filters will be explored, which will also highlight the main differences among them.

Speaker: Dr Sahani Pathiraja (DARE Chief Investigator)

Sahani Pathiraja is a Lecturer (tenure track assistant professor) in Data Science at the University of New South Wales (UNSW) in Sydney. Sahani received her double Bachelor of Science (mathematics) and Engineering (environmental) in 2011 with Hons (1st Class) and the University Medal, and her PhD in Civil and Environmental Engineering in 2018, all from the University of New South Wales (UNSW Sydney). Her dissertation topic was on improved data assimilation methods for hydrologic applications.

From 2017-2022 she was a postdoctoral researcher in the Institute of Mathematics at the University of Potsdam, Germany as part of the Collaborative Research Centre on Data Assimilation. She worked primarily on the theoretical analysis of modern sequential Monte Carlo methods as well as on new applications of data assimilation in biomedical modelling.

Sahani’s technical expertise spans both the mathematical theory and applications of data science methods, especially in hydrology. Her research is motivated by 1) how applications can inspire new theory and 2) how theory be developed in a more practically relevant way. Specifically, her research primarily focuses on Bayesian inference, Monte Carlo methods, stochastic analysis of data assimilation methods and uncertainty quantification.

The Bureau of Meteorology provides a range of water information products and forecast services to the Australian community. While the Bureau has been providing a flood forecast and warning service for several decades, new water forecasting services have been developed and brought into production over the last 15 years. These forecast services can be categorised as either nation-wide (grid-based) or targeting specific locations (point-based) and cover different temporal scales. This seminar will begin by providing an overview of these forecasting services, with an emphasis on forecasts at the seasonal timescale.

Water forecasting services encompass the Australian Water Outlook (AWO) and seasonal streamflow forecast (SSF) service. The AWO provides historical analysis, seasonal forecasts and decadal projections of key variables of the surface water balance: root-zone soil-moisture, runoff and actual evapotranspiration. AWO is underpinned by the Australian Water Resource Model (AWRA-L), run at a daily time-step and at a 5km resolution. The seasonal streamflow forecast (SSF) service provides point-based seasonal forecasts of river discharge at 341 point-locations across Australia, coincident with selected river gauging stations and major water storages.

The Bureau has embarked on a 10-year research plan focused on Earth System Modelling. A unified modelling system supporting all forecast products and services will drive efficiency gains, improve product consistency and remove the maintenance burden of disparate systems now in operation. The final part of this seminar will cover a scientific evaluation to unite both the AWO and SSF service. This unification has been achieved by applying statistical post-processing to AWO seasonal forecasts to generate seasonal streamflow forecasts.

Speaker: Dr Christopher Pickett-Heaps

Dr Christopher Pickett-Heaps is a hydrologist at the Bureau of Meteorology and is a member of the Hydrological Applications team in the Science and Innovation Group of the Bureau. Christopher has been with the Bureau since 2013. His primary role is a hydrological modeller, working to extend the capability of current water forecasting models and systems. Currently Christopher is the scientific lead of a project to integrate seasonal streamflow forecasting with seasonal landscape forecasting. Prior to this, Christopher worked on the Australian Water Outlook. Christopher has also contributed to the development of operational systems underpinning different water forecasting services.

Christopher was awarded a PhD from the University of Melbourne in earth-system modelling after studying in both Australia and France. Christopher then continued working in France before moving to Boston for two years as a post-doctoral fellow at Harvard University. Christopher returned to Australia in 2010 to take a 3-year position at The CSIRO before joining the Bureau. Christopher is based in Canberra.

Estimating future climate change and its uncertainties relies on the analysis of a range of global climate models (GCMs) and the assessment of their spread. To meet the spatial scales required to study the local impacts of climate change, GCMs are downscaled dynamically using regional climate models or empirically using statistical methods and machine learning techniques. Due to the high computational cost involved in dynamical downscaling (DD), only a few GCMs are considered in this approach, resulting in a limited range of predictions that might not be sufficient to accurately assess the uncertainty in the predicted changes. Statistical methods and machine learning, on the other hand, perform downscaling at a much lower cost, but can perform poorly when extrapolated to future climates.

We introduce a hybrid downscaling framework that leverages the merits of dynamical downscaling and machine learning while overcoming the limitations of a single approach. In the new framework, a machine learning model is developed for each coarse grid cell to predict the subgrid distribution of the variable of interest as a function of the local climate and subgrid land surface characteristics. The fine-scale data needed for training ML is sourced from dynamically downscaling 10 representative years from the entire distribution of the coarse data.

As a proof of concept, we apply the new framework to downscale daily Evapotranspiration from the Australian BARRA-R reanalysis dataset over Sydney from 12.5km down to 1.5km. We employ three machine learning algorithms and demonstrate their performance. We also explore spatial transitivity, i.e. the capability of the trained ML models to downscale regions outside the spatial domain they were trained in, and we demonstrate when it is effective.

In the proposed framework, multiple GCMs can be downscaled for the same cost as downscaling a single GCM. Ultimately, this should improve our ability to analyse future changes in local climate, and provide more robust information for impacts adaptation planning.

Speaker: Dr Sanaa Hobeichi

Sanaa Hobeichi is a post-doctoral researcher at the University of New South Wales (UNSW) Climate Change Research Centre and the ARC Centre of Excellence for Climate Extremes (CLEX). Her research spans climate science and machine learning, focusing on developing machine learning methods for downscaling climate data and improving drought predictions. She is also interested in explainable machine learning and physics-informed machine learning.

Sanaa is passionate about advancing climate science education for secondary school students. By leading the Climate Classrooms workshops for teachers, she facilitates the development of teaching resources that effectively incorporate climate science research into the Australian Curriculum.

Sanaa obtained her PhD in Climate Science from UNSW, and she holds a BSc in Computer Science and Applied Mathematics from the Lebanese University, and a MSc in Environmental Remote Sensing from Qatar University.

Numerical models of groundwater flow play a critical role for water management scenarios under climate extremes. Large‑scale models play a key role in determining long range flow pathways from continental interiors to the oceans, yet struggle to simulate the local flow patterns offered by small‑scale models. We have developed a highly scalable numerical framework to model continental groundwater flow which capture the intricate flow pathways between deep aquifers and the near surface. The coupled thermal‑hydraulic basin structure is inferred from hydraulic head measurements, recharge estimates from geochemical proxies, and borehole temperature data using a Bayesian framework. We use it to model the deep groundwater flow beneath the Sydney–Gunnedah–Bowen Basin, part of Australia’s largest aquifer system. Coastal aquifers have flow rates of up to 0.3 m/ day, and a corresponding groundwater residence time of just 2,000 years.

In contrast, our model predicts slow flow rates of 0.005 m/day for inland aquifers, resulting in a groundwater residence time of ∼ 400,000 years. Perturbing the model to account for a drop in borehole water levels since 2000, we find that lengthened inland flow pathways depart significantly from pre‑2000 streamlines as groundwater is drawn further from recharge zones in a drying climate. Our results illustrate that progressively increasing water extraction from inland aquifers may permanently alter long‑range flow pathways. Our open‑source modelling approach can be extended to any basin and may help inform policies on the sustainable management of groundwater.

Speaker: Dr Ben Mather

Dr. Ben Mather is a research fellow in the EarthByte Group within the School of Geosciences at The University of Sydney. He is an expert in fusing multi-disciplinary datasets with Earth evolution models to understand the occurrence of enigmatic volcanoes. Related research interests include the cycling of volatiles within the Earth, probabilistic thermal models of the lithosphere to unravel past tectonic and climatic events, and the response of groundwater flow pathways to tectonic forces.

A firm supporter of open-source software, Dr. Mather develops computational methods and tools that adhere to Findable, Accessible, Interoperable and Reusable (FAIR) standards and which are hosted in public repositories. He is a vocal advocate for the integral role of geoscience in responding to challenges we face in transitioning to the carbon-neutral economy. Dr. Mather has been interviewed in national and international print media, TV, and radio on a wide variety of subjects including earthquakes, volcanoes, groundwater, and critical minerals.

GitHub: github.com/brmather
Twitter: @BenRMather

The mining industry is currently going through a significant phase of digital transformation to try and meet the rising global demand for minerals. As part of this digitalisation and modernisation, mining companies are collecting larger volumes of more complex data than ever before. Technologies that can assist in turning data into information and insights are key to prevent geoscientists from drowning in their new sea of data.

In this talk, we will explore how recent advances in computer vision – specifically in the field of deep learning – have provided algorithms and workflows that have the ability to efficiently augment and automate the many observational tasks in geoscience such as drill core logging. Several case studies will be presented to demonstrate how these models are trained and deployed to solve challenging geoscience problems.

Speaker: Brenton Crawford

Brenton Crawford is a geologist, data scientist, entrepreneur and mining technology enthusiast. He studied geology and geophysics at Monash University and began his career in consulting working for PGN Geoscience in a number of geological and geophysical roles in both exploration and mining. Brenton has also worked as a geophysicist and data scientist for MMG Exploration working in nickel, copper and zinc exploration and project generation in Australia, Africa and South America.

In 2015, Brenton co-founded Solve Geosolutions – Australia’s first exploration and mining focused data science consultancy which has since been acquired. In 2018, Brenton co-founded Datarock – a computer vision technology company geared at building productionised image and video analysis solutions for exploration and mining where he has served as both its Head of Business Development and Chief Operating Officer. Brenton currently serves as Datarock‘s Chief Geoscientist and Technologist.

Speaker: Professor Sally Cripps

Sally Cripps is an internationally recognized scholar and leader in Bayesian Machine Learning (ML) and Artificial Intelligence (AI). In addition to her role as Director of Technology at the Human Technology Institute she is a Professor of Mathematics and Statistics at the University of Technology Sydney. Sally has held a number of leadership positions in ML and AI. She was cofounder and co-director of the University of Sydney’s Centre for Translation Data Science (CTDS), she was founder and Director of the Australian Research Council’s Industrial Transformation Training Centre (ARC ITTC) Data Analytics for Resources and Environments (DARE). Most recently Sally was Research Director of Analytics and Decision Science and Science Director of the Next Gen AI Training Programme in CSIRO’s Data61. She was also chair of the International Bayesian Society for Bayesian Analysis (ISBA) section on Education and Research in practice. She has served as a board member for Climate Services for Agriculture in the Department of Water and the Environment and as a member of the Data Analytics Centre of NSW Health and Human Services Expert Working Group and the NSW Smart Cities Research & Academic Working Group.

Sally’s research focuses on the development of new foundational methods in AI to address global challenges. Her work has been published in the world’s most prestigious statistical and machine learning journals such as, The Journal of the Royal Statistical Society, and the Journal of the American Statistical Association; Theory and methods, (JASA), Biometrika and Journal of Computational and Graphical Statistics (JCGS), Conference on Neural Information Processing Systems (NeurIPS) and Conference on Artificial Intelligence and Statistics (AIStats). She has applied these methods to a diverse range of fields including social disadvantage, mental health, climate, minerals and the environment. In recognition of the quality of her research Sally was awarded an ARC Future Fellowship and a visiting scholar fellowship to the Alan Turing Institute in the UK. Sally has attracted over $25M in industry, government and philanthropic funding.

Recent advances in artificial intelligence, including the development of highly sophisticated large language models (LLM), have proven beneficial in many real-world applications. However, evidence of inherent bias encoded in these LLMs has raised concerns about equity. In response, there has been an increase in research dealing with bias, including studies focusing on quantifying bias and developing debiasing techniques. Benchmark bias datasets have also been developed for binary gender classification and ethical/racial considerations, focusing predominantly on American demographics. However, there is minimal research in understanding and quantifying bias related to under-represented societies.

Motivated by the lack of annotated datasets for quantifying bias in under-represented societies, we endeavoured to create benchmark datasets for the New Zealand (NZ) population. We faced many challenges in this process, despite the availability of three annotators. This research outlines the manual annotation process, provides an overview of the challenges we encountered and lessons learnt, and presents recommendations for future research.

Speaker: Professor Gill Dobbie

Professor Gillian Dobbie is widely recognised for her research in database systems and artificial intelligence. She holds a PhD in Computer Science from the University of Melbourne, where she specialised in database theory and design. Her research interests encompass a wide range of topics, including conceptual modeling, knowledge representation, query optimisation, data privacy, data stream mining, continual learning, and adversarial learning. She has published over 160 papers in top-tier conferences and journals, such as SIGCSE, IJCAI, ICDM, SIGIR, CIKM, ICDE, SIGMOD, TODS, ACM Computing Surveys. She was awarded the DASFAA 10+ Year Best Paper Award for her research contribution with Prof Ling Tok Wang and Prof Mengchi Liu. Professor Dobbie is a Fellow of the Royal Society of New Zealand and Chair of the Marsden Fund Council.

Throughout her career Professor Dobbie has been a catalyst for collaboration and interdisciplinary work, leading the development of projects such as Precision Driven Health, which received the MinterEllisonRuddWatts Research & Business Partnership Award. She continued to build bridges between academia and industry through her leadership of the Auckland ICT Graduate School.

Beyond her academic pursuits, Professor Dobbie is actively engaged in promoting diversity and inclusivity in STEM fields. She is passionate about encouraging underrepresented groups to pursue careers in computer science, fostering an environment where everyone can thrive.

Dr Tom Remenyi will present his view on the research sector, and some of the key barriers to transforming research outputs into impact. Tom will then present the Eratos platform, a tool designed to assist with data management and analytics, with a particular focus on assisting research teams commercialise research. Tom will show some demonstrations of how the platform is currently being used, some successful projects so far, and point out some of the areas researchers are finding value.

Speaker: Dr Tom Remenyi

Dr Tomas Remenyi is a climate services professional expert at translating complex climate science into useful, accessible products, tools or advice. Tom focuses on meaningful engagement with stakeholders so as to rapidly determine the nexus of where their needs intersect with what known science can actually deliver. Tom has a decade of experience delivering useful climate services with more than 50 projects across a range of sectors including natural hazards, emergency services, tourism, energy, and agriculture.

Tom has a dynamic mix of science and commerce training that allows him to view both the research and commercial sectors from a perspective that differs from others. As a ‘systems thinker’ Tom is always trying to figure out what the blockers are to positive change within society across multiple sectors. Tom is currently supervising 2 PhD students and regularly supports executive leadership teams to better understand how climate change will impact their operations and strategy. After 20 years working as an academic, Tom has now transitioned into the commercial realm to help be a bridge over the research-commerce divide.

Biodiversity offset credits in New South Wales are transacted within a regulatory environment defined by detailed trading rules and many different types of biodiversity credits that can lead to thin markets and high transaction costs. In this talk, I will present a recent paper I co-authored with Charles Plott (Caltech), Gary Stoneham (CMD), Ingrid Burfurd (CMD), and Mladen Kovac (NSW DPE), which is not only academically valuable but also practically indispensable. It provides the necessary guidance and structure to ensure that the proposed market tool is not just an abstract concept but a practical and effective solution to the challenges faced in biodiversity offset credit trading in NSW.

The paper presents the key elements of this market, including a search algorithm that identifies potential trading partners based on regulatory constraints and an online exchange tool that streamlines the process of price discovery and allocation of offset contracts.

The search algorithm for biodiversity offset rules relies on key comparisons, improving efficiency compared to linear searching. It systematically eliminates records until the target record is found. This algorithm is applied to BOS data structures in a predefined order to update the public register, initiating a new search cycle.

Speaker: Dr Rogelio Canizales-Perez

Dr Canizales-Perez is an Economist, with a PhD in Environmental Science and several years of experience as a Public Servant managing all environmental, economic, finance, and policy affairs that support the development of Natural Capital Markets in NSW, Australia (specialised in Natural Capital policy programs such as the Biodiversity Offsets Scheme). His professional journey has been characterised by a serious dedication to innovative (and disruptive) solutions and a profound sense of responsibility to contribute significantly to the organisation’s growth while fostering a positive and lasting impact on society.

He worked for more than nine years in the Mexican Government delivering products on nationwide strategic and regulatory water planning functions. Dr Canizales-Perez is a clear and effective communicator and highly skilled at econometrics, natural capital accounting, and environmental markets design with demonstrated experience as a Team Leader in developing innovative and fit-for-purpose market information tools.

The first part of Floris’s talk will look at drought research in the Pacific Island Countries (PICs). Drought is becoming an increasing concern for food security and production in the PICs. For example, the 1997–98 drought cost Fijian farmers $US 63 million in lost revenue from mostly sugar cane farming and threatened food security in the region. A recent study on droughts impacts in PICs identified 5 research challenges of which one is to develop drought early warning systems. The results of initial research into developing a drought forecasting system based on LSTMs will be presented.

The second part of the talk will look at using novel data sources to predict algal blooms. In 2000, it was estimated that algal blooms cost Australia more than $AUD 95 million per year by impacting our water ways and water supplies, fisheries, agriculture, and recreational water use. Continuing research being conducted by UNSW suggests that this is likely to be much higher but is yet to be assigned a dollar value. Furthermore, blue green algal blooms (BGABs) pose a significant health risk to humans and stock. WaterNSW is responsible for the challenging task of monitoring and reporting BGABs. Unfortunately, it is nigh on impossible to monitor the entire water network in NSW as its resources are limited. Therefore, we are looking into ways in which we can use readily available data such as climate records, satellite data, and novel data sets such as dust data, to predict where and when blooms might occur. These predictions can be used to aid in managing blooms through, e.g., directing when and where to erect warning signs, deploying mobile aeration stations, shunting water in and out of weirs to disrupt blooms and identify hotspots where longer term management strategies may be needed or monitor whether management plans have been effective in reducing BGABs.

Finally, a summary of current and future projects will be given as a key goal of this talk is to identify potential future collaborations with members of DARE.

Speaker: Floris Van Ogtrop

As technology pervades our lives in an increasingly rich ecosystem of digital devices, they can capture huge amounts of long-term personal data. A core theme of my research has been to create systems and interfaces that enable people to harness and control that data and its use. This talk will share key insights a series of case studies from that work and plans to build upon these. The first case studies explored how to harness data from wearables, such as smart watches, for personal informatics interfaces that help us gain insights about ourselves over the long term, for analysis of a large dataset (over 140,000 people) and for Virtual Reality games for exercise. The second set of case studies are from formal education settings where personal data interfaces, called Open Learner Models (OLMs), can harness learning data. I will share key insights that have emerged for a research agenda: OLMs for life-wide learning; the nature of the different interfaces needed for fast, versus slow and considered, thinking; communicating uncertainty; scaffolding people to really learn about themselves from their data; and how these link to urgent challenges of education in an age of AI, fake news and truth decay.

Speaker: Judy Kay

Bayesian inference has been increasingly used in statistics and related areas as a principled and convenient tool for reasoning with uncertainty. Bayesian computation is often a challenging task and modern applications of Bayesian inference, such as Bayesian deep learning, have called for more scalable Bayesian computation techniques. In this talk, I will give a quick introduction to Variational Bayes for scalable Bayesian inference. I then provide a general discussion on its pros and cons, recent advances and applications, and some potential research directions.

Speaker: Minh-Ngoc Tran

The advancement of sensing technologies, embedded systems, wireless communication technologies, nanomaterials and miniaturisation makes it possible to develop IoT enabled smart sensing systems. IoT enabled wearable and non-wearable sensors generate useful data to monitor physiological parameters as well as human activities continuously to detect any abnormal and/or unforeseen situations which need immediate attention. Therefore, necessary help can be provided in times of dire need. IoT enabled sensors provides real time environmental data which will provide full awareness of weather/climate and can be used to take any strategic/corrective actions to address issues. This seminar will discuss fabrication and developmental works on IoT enabled sensors based on MEMS as well as flexible materials for home, health, and environmental monitoring.

Speaker: Subhas Mukhopadhyay

Quantum inertial sensors, quantum sensors that measure vector gravity, the gravity gradient tensor, acceleration, rotation and time offer unprecedented accuracy and very low in-run and bias offset drift. These properties are critical for many applications including the mapping of underground water resources, mineral exploration, underground structure detection and mapping, inertial navigation in GPS denied scenarios, satellite navigation, and planetary exploration. When fused with a high bandwidth, high dynamic range classical sensor, we get the best of both worlds.

In the Quantum Sensors Group at ANU, we develop fit for purpose sensors based on detailed quantum models, and are just now developing our first sensors in field deployable SWaP. We exploit a host of techniques from Bose-Einstein condensed sources, to large momentum transfer atomic beam splitting, to quantum squeezing and, in collaboration with Sydney company Q-CTRL, optimised composite pulses to provide immunity to environmental noise. This talk will be an introduction to these very promising sensors and a discussion of a variety of applications. I will discuss the strengths and weaknesses of these sensors and identify the most promising applications.

Speaker: John Close

Northern Australian savannas hold exceptional biodiversity values within largely intact vegetation complexes, yet many of the 180+ mammal species, and some other taxa, found in the region when Europeans colonised Australia are Endangered. Recently, 10 mammal species were added to the 20 or so already listed in the Australian endangered category, one up-listed to Critically Endangered, one to Extinct, 2 un-listed, 2 down-listed to Vulnerable and so on. Current predictions suggest that 9 species of mammal in northern Australia are in imminent danger of extinction within 20 years. We examined the robustness of the assumptions of status and trends in light of the low levels of monitoring of species and ecosystems across northern Australia, including monitoring the effects of management actions. The causes of the declines include a warming climate, pest species, changed fire regimes, grazing by introduced herbivores, and diseases.

Speaker: Noel Preece

Quantum computing has emerged as the next computing technology paradigm, which promises to transform many critical fields, such as pharmaceutical and fertilizer design, supply chain and traffic optimisation, or optimisation for machine learning tasks. This is an exciting development for statisticians and data scientists because it will give rise to a new evolutionary branch of statistical and data analytics methodologies. This seminar will introduce quantum computing, explain its power and challenges, and provide a few examples of applications of quantum computing to problems of interest to statisticians.

Speaker: Anna Lopatnikova

PFAS (per- and poly-fluoroalkyl substances) are a class of putative toxic chemicals used in firefighting foams and some industrial processes. Escape of these chemicals into waterways has implications for ecological and human health. Their long environmental half-lives, detection difficulty and remediation complexities make them especially problematic. This DARE seminar will introduce relevant findings from the rapidly evolving field of PFAS research, as performed across Alaska.

Speaker: Kristin Nielsen

This seminar will begin with an overview of research at the Gardens, and some of the plant resources that enable it, with a special focus on data. Next, three case studies will be presented. These highlight topics where there is opportunity to develop approaches to unlock data in RBG collections, or improve inference from rich genetic datasets. The case studies focus on understanding plant biodiversity (e.g., links between traits and environment), or directly informing conservation and restoration actions (e.g., managing genetic risks to endangered plants).

Speaker: Jason Bragg

We have entered a new era of the Anthropocene and are facing a biodiversity crisis, with extinction rates of species at least twice that of the background rate. Coupled with biodiversity loss is also rapid environmental change and increases in disturbance events, such as extreme weather events and wildfires. Ecologists are now concerned that entire ecosystems are at risk of collapse. To address this urgent challenge, we need to understand how disturbance events affect individual species, communities and how these changes permutate through ecosystems. The first part of the seminar will include an example of the population dynamics of a threatened species in a highly variable environment, an example of how wildfire operates in arid Australian and lastly how arid ecosystems may be modified from climate change. The second part of the seminar will introduce new research programs started since 2019 that expand these concepts into agricultural and forest ecosystems.

Speaker: Aaron Greenville

Dirichlet processes and their extensions have reached great popularity in Bayesian nonparametric statistics. They have also been introduced for spatial and spatio-temporal data, as a tool to analyse and predict surfaces.

A popular approach to the Dirichlet process in a spatial setting relies on a stick-breaking representation, where the dependence over space is described in the definition of the stick-breaking probabilities. Extensions to include temporal dependence usually introduce a temporal dependence among the atoms of the Dirichlet process, however this approach does not let us properly test and incorporate a possible interaction between space and time.

In this talk, a Dirichlet process is proposed where the stick-breaking probabilities are defined to incorporate both spatial and temporal dependence. An advantage of the method is that it offers a natural way to test for separability of the two components. The performance of this approach will be tested on simulations and a real-data example from meteorology.

Speaker: Clara Grazian

Digital spectroscopy is transforming the way we characterise soils. Spectroscopy from numerous electromagnetic ranges produce various types of digital spectra, which can provide soil information. This presentation will look into mathematical and statistical techniques to extract information from the spectra to predict soil information. We will discuss techniques from machine learning (large p, small n) to deep learning models (large p, large n) and the challenges and opportunities in analysing spectra data from the lab to the field.

Speaker: Budiman Minasny

Gaussian Processes (GPs) provide a probabilistic method of modelling functions that can be applied to both classification and regression problems. The first part of this talk will present a range of geological problems that GPs have been applied to. The second part of the talk will present use of Bayesian model selection to evaluate Lower Namoi aquifer water balance models. This method tests the likelihood that different hypothesised components (inflows and outflows) are contributing to the water balance and the impact of other components on these likelihoods.

Speaker: Katie Silversides

Our capability to reconstruct past landscapes, and the processes that shape them, underpins our comprehension of paleo-Earth, from its tectonic, atmospheric, and oceanic past dynamics to the evolution of life.

First, I will present a global-scale landscape evolution model assimilating paleo-elevation and paleo-climate reconstructions over the past 100 Myr. The simulations track the evolution of geomorphic and sedimentary features, including paleo-physiography maps, sediment fluxes, and stratigraphic architectures. From these simulations, we could reappraise the role surface processes plays in controlling sediment delivery to the oceans, evaluate sedimentation rates and the distinct phases of sediment transfer from terrestrial to marine basins. This advance in global landscape evolution modelling opens new avenues to quantify the role that the constantly evolving physiography of the Earth has played in modulating the transport of sediments from mountain tops down to the ocean basins, ultimately regulating the carbon cycle and Earth’s climate fluctuations through deep time.

The idea that landscapes play a role in biological evolution has a long history that can be traced back to the 19th century with Darwin and Wallace when faunal and floral boundaries were noted to correspond to physiographic discontinuities and gradients. More recently, species adaptation in response to the motion of continents has been extensively studied. Yet, only a few studies have looked at how the evolution of migration pathways is modulated by Earth’s morphological changes on geological time scale. In this second part of the seminar, I will focus on the Quaternary evolution of Sundaland, the partially inundated shelf separating Java, Sumatra and Borneo from the Malay Peninsula. Building upon recent work on climatic and tectonic history of the region, I ran a series of landscape evolution simulations to (1) investigate the role that physiographic and climatic changes might have played in regional biological diversification and (2) quantify how landscape dynamics could influence species migration. Specifically, I evaluate the regional geomorphological evolution by characterising main paleo-rivers’ routing history, associated watershed evolution and multiple morphometrics describing the landscape complexity (slopes, elevational range, erosion/deposition rates). From these simulations, I will present two applications. First, focusing on the past 1 Myr, I will show that physiographic changes have modified the regional connectivity network and remodelled the pathways of species dispersal supporting the theory that rapidly evolving physiography has fostered Quaternary biodiversification across Southeast Asia. Then, from predicted Sundaland physiography, I reconstruct Homo Erectus dispersal routes, coupling ecological movement simulations to landscape evolution model and find that the hospitable terra firma conditions of Sundaland facilitated the prior dispersal of hominins to the edge of Java. I then estimate a characteristic dispersal time of Homo Erectus across Sundaland. Our comprehensive reconstruction method to unravel the peopling timeline of Southeast Asia provides a novel framework to evaluate the evolution of early humans.

Speaker: Tristan Salles

Natural language processing and graph representation learning are trending AI topics. They’ve received increasing attention due to their effectiveness in a wide range of application domains (e.g., healthcare, speech recognition) and downstream machine learning tasks (e.g., clustering, prediction). In this talk, Monica presents some state-of-the-art natural language processing and graph representation learning algorithms and discusses how natural language processing was adapted and integrated into network representation learning and analysis. In particular, Monica talks about existing graph representation learning research on different types of networks and research progress on the large-scale dynamic heterogeneous networks. This talk also showcases some applications of the two topics.

Speaker: Monica Bian

Small, constructed waterbodies are designed to attenuate floods and enhance water quality. Despite a range of guidelines that inform the design of these waterbodies, many still experience harmful algal blooms (HABs). It is vital to improve our understanding of how small waterbodies respond to HABs, considering the increasing number of small waterbodies being built globally and increasing HAB risk with climate change. This seminar will introduce Shuang’s research using a data-driven approach in her PhD studies and current work. These studies include design recommendations for small, constructed waterbodies to limit HABs, and remote sensing detection methods for HABs and water quality in waterbodies on local and global scales.

Speaker: Shuang Liu