Workshop Program for Connecting Machine Learning to Earth System Science 2026
The ACCESS Community Workshop Connecting Machine Learning to Earth System Science runs across three days from Wednesday 19 to Friday 21 August. It contains a mixture of plenary sessions that occur in a single location, parallel sessions, training and informal discussion sessions.
The program is subject to amendments—please revisit this webpage for the most up-to-date version of the program.
On this page:
Day 1: Wednesday 19 August
| Time | Session | Session Chair | Presenter | Title (and link to abstract) |
|---|---|---|---|---|
| 9:00 – 9:45 | Arrival Registration and tea/coffee | |||
| 9:45 – 10:00 | Housekeeping and Welcome to Country | |||
| 10:00 – 10:30 | Session 1: Plenary (1 speaker) | Sanaa Hobeichi | Terry O'Kane | Novel neural operator and transformer architectures for climate prediction |
| 10:30 – 11:00 | Morning Tea | |||
| 11:00 – 11:30 | Session 2: Evaluation methods (2 speakers) | Yiyi Guo | Hung Luu | Can we test machine learning models without ground truth? |
| Yuan Zhuang* | Evaluating Geo-Foundation Model Embeddings for Wildfire Risk Assessment | |||
| 11:30–12:00 | Lightning Talks (15 speakers x 2 mins including change over) | Will Hobbs | Data-driven polar research: M/L activities at the Australian Antarctic Program Partnership | |
| Chandana Nagenahally Manjunath* | Dynamic Network Analysis of ENSO-driven Global Commodity Price Volatility: Implications for Food and Energy Security | |||
| Wei Ji Leong | CuPy-Xarray: towards direct to GPU decoding of raster file formats | |||
| Christian Stassen | Machine learning for regional climate downscaling in the Australian Climate Service | |||
| Abhnil Amtesh Prasad | WRF-LES training data generation framework for AI surrogates of parameterized convection | |||
| Pearse Buchanan | Optimization of Australia's ocean biogeochemical model with a machine learning surrogate. | |||
| Lynn Zhou | Rapid Forecast‑Based Attribution via a Climate Emulator | |||
| Haoran Li, Shixue Li | Coarse-to-Fine: Multi-source Fusion for Bias-Corrected Precipitation Downscaling | |||
| Jakob Gradl* | A hybrid variational physics informed/physics encoded neural network for strictly mass-conserving joint inversion of mass and momentum balance in ice flow modelling | |||
| 12:00 - 13:30 | Poster viewing (Dedicated first 30 minutes, with last hour overlapping with lunch) | |||
| 12:30 - 13:30 | Lunch | |||
| 13:30 – 15:00 | Training: Autoencoders Part 1 - Introduction | Tennessee Leeuwenburg | ||
| 15:00 - 15:30 | Afternoon Tea | Lachlan Astfalck | FlowGP: Physically Coherent ML for Probabilistic Field Reconstruction | |
| 15:30 - 16:15 | Session 3: Physics-Informed / Hybrid Machine Learning Part I (3 speakers) | Micael Oliveira | David Lee | Data driven thermodynamically consistent moist phase exchanges for atmospheric convection |
| David Fuchs | Plugging Pytorch to an atmospheric model the TorchClim way | |||
| 16:15 - 17:00 | Breakout session: Putting GenAI to Work in Earth System Science Part 1 | Yue, Micael, Edward, Taimoor & Sanaa | ||
| 17:00 - 18:00 | Free time | |||
| 18:00 - onwards | Dinner. Food served from 18:30 (Venue TBC) | |||
Day 2: Thursday 20 August
| Time | Session | Session Chair | Presenter | Title (with link to Abstract) |
|---|---|---|---|---|
| 8:30 – 8:50 | Arrival | |||
| 8:50 – 9:00 | Housekeeping and Acknowledgement of Country | |||
| 9:00 – 10:30 | Session 4: Forecasting, nowcasting & data assimilation (6 speakers) | Steve Sherwood | Yiyi Guo* | Distributional Bias Correction for Madden-Julian Oscillation Forecast |
| Carl Doedens* | Solar nowcasting with latent diffusion and XGBoost: assessing feature importance and evaluation in different environments | |||
| Chen Li | Assessment of Global Data-Driven Models for Weather and Sub‑Seasonal Prediction over Australia | |||
| Mengmeng Han | Infusing deep-learning model with domain knowledge for better surface wind nowcasting | |||
| Ajitha Cyriac | Validating satellite-derived data for sea surface temperature downscaling using machine learning | |||
| Peter Oke | A data-driven approach for mesoscale ocean forecasting | |||
| 10:30 – 11:00 | Morning Tea | |||
| 11:00 – 11:45 | Session 5: Atmosphere applications (3 speakers) | Heidi Nettelbeck | Eun-Pa Lim | Ozone – an untapped source of subseasonal to seasonal forecast predictability |
| Hongyan Zhu | Model simulations of TC-Alfred (2025): Machine learning versus physical models | |||
| Harun Rashid | Assessing Australian rainfall teleconnections using linear and machine learning models | |||
| 11:45 – 12:05 | Lightning Talks (10 speakers x 2 mins including change over) | Spencer Patrick Clark* | Pattern scaling in an overshoot world | |
| Kevin Horner / Daimon Byl / Benjamin Cottrell * | Practical Gray-Box Universal Differential Equation Methods for Chaotic Climate-Relevant Dynamics | |||
| Tishampati Dhar | A review of Geospatial Foundation models, Embeddings and Practical Applications | |||
| Li Wang | AI-Assisted Porting and Performance Optimization of LFRic Kernels | |||
| Ryan Holmes | Coastal downscaling of Australian seasonal sea level and sea surface temperature forecasts using neural networks | |||
| Jasmine Peterson* | Machine Learning and Australia’s shape | |||
| Krish Singh* | Using Machine learning to calibrate complex process-based models for carbon stock projection in NSW forests | |||
| Zhihao Deng* | Climatological Anomalies Projection using Neural Ordinary Differential Equations | |||
| William Edge | Gaussian Process Regression for multi-scale oceanographic observations | |||
| 12:05 - 13:30 | Poster viewing (Dedicated first 25 minutes, with last hour overlapping with lunch) | |||
| 12:30 - 13:30 | Lunch Potential for community led breakout sessions run in parallel during lunch |
|||
| 13:30 – 15:00 | Training: Autoencoders Part 2 | Tennessee Leeuwenburg | ||
| 15:00 - 15:30 | Afternoon Tea | |||
| 15:30 - 16:15 | Session 6: Ocean applications (3 speakers) | Taimoor Sohail | Rick de Kreij* | Statistical inversion of surface tracers to infer fine-scale near-surface ocean currents |
| Stephanie Contardo | A machine-learning and process-based hybrid workflow for shoreline position prediction | |||
| Chaojiao Sun | Deep learning projections of coral bleaching risk: will the 2024–25 Ningaloo marine heatwave become the new normal? | |||
| In Parallel: Atmosphere Working Group Meeting | ||||
| 16:15 - 17:00 | Breakout session: Putting GenAI to Work in Earth System Science Part 2 | Yue, Micael, Edward, Taimoor & Sanaa | ||
Day 3: Friday 21 August