Explainable AI for climate science

My current research focuses on using AI not only for prediction, but also as a tool for scientific discovery and physical assessment. I develop XAI approaches to evaluate the physical realism of neural networks in weather and climate sciences, and to improve our understanding of the physical mechanisms that drive climate and weather variability. 

I am particularly interested in how neural networks learn climate processes, how their predictions can be interpreted in physical terms, and how AI can help understand previously unknown relationships within the climate system. More recently, my fork has been focused on understanding neural network predictions of heavy rainfall, linking large scale atmospheric dynamics to local precipitation events.

• Explainable AI shows that a neural network learns extratropical cyclones as predictors of heavy precipitation (preprint): Link to preprint
• Can AI models be trusted to predict heavy rainfall? (interview by UiB AI): Link to interview

SST pattern influence on the Earth's energy budget

While a major part of my current work focuses on explainable AI for climate and weather science, my broader scientific interests consist of climate dynamics in general. In particular, I am interested in how patterns and gradients of sea surface temperature (SST) influence atmospheric circulation and the global energy budget of the planet. My previous work has been focused on understanding how regional SST gradients shape global climate responses through their interaction with the Earth's energy budget, including their influence on the transient climate response.

• The role of SST pattern effects in transient global warming (Journal of Climate): Link to paper
• ENSO influences on internal variability of the Earth's energy budget (Geophysical Research Letter): Link to paper

Understanding changes in future European heavy rainfall 

I also contribute to a project focusing on understanding what will drive changes in european heavy rainfall using large scale dynamical variables. Find our interactive app focusing on CMIP model biases and projections here: 

Interactive map for european rainfall biases

I teach and develop courses and workshops regarging technical tools for geoscientific data.

2026 - BCCR Training Programme in Machine Learning

2025 - GFI evening course: machine learning for geosciences

2020-2024 - Python for geosciences

Submitted publications

1. Robin Guillaume-Castel, Camille Li and Stefan P. Sobolowski. "Explainable AI shows that a neural network learns extratropical cyclones as predictors of heavy precipitation." 
2. Danielle L. Spring, Michael D. Fox, J. A. Mattias Green, Robin Guillaume-Castel, Ronan C. Roche, Laura E. Richardson, Gaga Mele, Eesaa Harris, John R. Turner, and Gareth J. Williams. "Scale-dependent upwelling dynamics on coral reefs: what satellites don’t see"

Peer reviewed publications

1. 2026 - Joshua Oldham-Dorrington, Camille Li, Stefan P. Sobolowski and Robin Guillaume-Castel. "Understanding biases and changes in European heavy precipitation using dynamical flow precursors." Weather and Climate Dynamics
2. 2025 - Robin Guillaume-Castel and Benoit Meyssignac, "Quantifying the influence of the sea surface temperature pattern effect on transient global warming." Journal of Climate.
3. 2025 - Robin Guillaume-Castel, Paulo Ceppi, Joshua Dorrington, Benoit Meyssignac "ENSO diversity explains interannual variability of the pattern effect." Geophysical Research Letters.
4. 2025 - Danielle Spring, Michael Fox, JA Mattias Green, Robin Guillaume-Castel, Zoe Jacobs, Ronan Roche, John Turner, Gareth Williams, "Climate change impacts to upwelling and shallow reef nutrient sources across an oceanic archipelago." Limnology and Oceanography.
5. 2023 - Benoit Meyssignac, Jonathan Chenal, Norman Loeb, Robin Guillaume-Castel, Aurélien Ribes, "Time-variations of the climate feedback parameter λ are associated with the Pacific Decadal Oscillation." Communications Earth & Environment.
6. 2023 - Benoit Meyssignac, Robin Guillaume-Castel, Rémy Roca, "Revisiting the global energy budget dynamics with a multivariate Earth energy balance model to account for the warming pattern effect." Journal of Climate.
7. 2023 - Michael Fox, Robin Guillaume-Castel, Clinton Edwards, Jess Glanz, Jamison Gove, JA Green, Ellis Juhlin, Jennifer Smith, Gareth Williams, "Ocean currents magnify upwelling and deliver nutritional subsidies to reef-building corals during El Niño heatwaves." Science Advances.
8. 2022 - Jonathan Chenal, Benoit Meyssignac, Aurélien Ribes, Robin Guillaume-Castel, "Observational constraint on the climate sensitivity to atmospheric CO₂ concentrations changes derived from the 1971--2017 global energy budget." Journal of Climate.
9. 2021 - Robin Guillaume-Castel, Gareth Williams, Justin Rogers, Jamison Gove, JA Mattias Green, "Quantifying upwelling in tropical shallow waters: A novel method using a temperature stratification index." Limnology and Oceanography: Methods.
10. 2020 - Sian Henley, Marie Porter, Laura Hobbs, Judith Braun, Robin Guillaume-Castel, Emily Venables, Estelle Dumont, Finlo Cottier, "Nitrate supply and uptake in the Atlantic Arctic sea ice zone: seasonal cycle, mechanisms and drivers." Philosophical Transactions of the Royal Society A.

Theses

• 2023 - PhD thesis: "Influence of the sea surface temperature pattern effect on the global top of the atmosphere energy budget and on global warming"
• 2020 - MSc thesis: "El Niño-Induced Upwelling Variability in the Central Tropical Pacific Ocean"
• 2019 - MSc thesis: "Seasonal variability of Atlantic water inflow in the continental shelf North of Svalbard using mooring data"