Earth foundation models for environmental hazard mapping

• Zhuang, Y., Hobeichi, S. et al. (2026). Evaluating AlphaEarth Foundations Embeddings for Wildfire Susceptibility Mapping. (arXive Preprint)

Machine learning for regional climate modelling

This body of work applies machine learning to improve the spatial representation of climate variables, benchmark ML approaches against dynamical downscaling, and reduce the computational cost of regional climate simulations.

Selected publications:

• Curran, D., Hobeichi, S. et al. (2026). Generate the Forest before the Trees- A Hierarchical Diffusion model for Climate Downscaling. Transactions on Machine Learning Research. (accepted)
• Hobeichi, S. et al. (2026). Applying a standardised benchmarking framework to evaluate AI methods for precipitation downscaling over Australia. Artificial Intelligence for the Earth Systems.
• Rampal, N., Hobeichi, S. et al. (2025). A Reliable Generative Adversarial Network Approach for Climate Downscaling and Weather Generation. Journal of Advances in Modeling Earth Systems.
• Rampal, N., Hobeichi, S. et al. (2024). Enhancing Regional Climate Downscaling through Advances in Machine Learning. Artificial Intelligence for the Earth Systems.
• Nishant, N., Hobeichi, S. et al. (2023). Comparison of a novel machine learning approach with dynamical downscaling for Australian precipitation. Environmental Research Letters.
• Hobeichi, S. et al. (2023). Using Machine Learning to Cut the Cost of Dynamical Downscaling. Earth's Future.

Machine learning in drought research

Machine learning is used here to improve drought characterisation, prediction, and interpretation.

Selected publications:

• Hobeichi, S. et al. (2022). Toward a Robust, Impact-Based, Predictive Drought Metric. Water Resources Research.
• Devanand, A., Hobeichi, S. et al. (2024). Australia's Tinderbox Drought: An extreme natural event likely worsened by human-caused climate change. Science Advances.
• Grant, M. O., Hobeichi, S. et al. (2025). Historical trends of seasonal droughts in Australia. Hydrology and Earth System Sciences.
• Holgate, C. M., Hobeichi, S. et al. (2025). Physical mechanisms of meteorological drought development, intensification and termination: an Australian review. Communications Earth & Environment.

Machine learning in renewable energy research

• Richardson, D., Hobeichi, S. et al. (2026). Limited influence of climate modes of variability on residual load in Australia's electricity grid. Environmental Research: Energy.
• Richardson, D., Hobeichi, S. et al. (2026). Wind power growth drives winter risk and supply-dominated variability in Australia's energy system. Environmental Research: Climate.
• Richardson, D., Hobeichi, S. et al. (2025). Predicting Australian energy demand variability using weather data and machine learning. Environmental Research Letters.

Machine learning in paleoclimate research

• Falster, G., Hobeichi, S. et al. (2026). High resolution monthly precipitation isotope estimaes across Australia from machine learning. EGUsphere.

Large-scale climate variability and predictability of precipitation and hydroclimate extremes

• Hobeichi, S. et al. (2026). Climate-Mode Precursors and the Predictability of Amazon Hot and Dry Extremes. Earth's Future. (accepted)
• Hobeichi, S. et al. (2024). How well do climate modes explain precipitation variability? npj Climate and Atmospheric Science.

Historical changes in hydrological and energy budgets

This body of work investigates historical changes in the terrestrial hydrological cycle and land–atmosphere energy exchanges, using observational synthesis products, energy and water budget closure, and model evaluation frameworks.

Selected publications:

• Hobeichi, S. et al. (2022). Reconciling historical changes in the hydrological cycle over land. npj Climate and Atmospheric Science.
• Hobeichi, S. et al. (2021). Robust historical evapotranspiration trends across climate regimes. Hydrology and Earth System Sciences.
• Hobeichi, S. et al. (2020). Evaluating precipitation datasets using surface water and energy budget closure. Journal of Hydrometeorology.
• Hobeichi, S. et al. (2020). Conserving land-atmosphere synthesis suite (CLASS). Journal of Climate.
• Hobeichi, S. et al. (2019). Linear Optimal Runoff Aggregate (LORA). Hydrology and Earth System Sciences.
• Hobeichi, S. et al. (2018). Derived Optimal Linear Combination Evapotranspiration (DOLCE). Hydrology and Earth System Sciences.

Scientific datasets (DOLCE, LORA, and CLASS)

• Hobeichi, S. et al. (2021). Derived Optimal Linear Combination Evapotranspiration - DOLCE v3.0. NCI National Research Data Collection.
• Hobeichi, S. et al. (2019). Conserving Land-Atmosphere Synthesis Suite (CLASS) v1.1. NCI National Research Data Collection.
• Hobeichi, S. et al. (2018). Linear Optimal Runoff Aggregate (LORA) v1.0. NCI National Research Data Collection.
• Hobeichi, S. et al. (2017). Derived Optimal Linear Combination Evapotranspiration v1.0. NCI National Research Data Collection.