Team
Tom Beucler (Principal Investigator)
Saranya Ganesh S (Postdoctoral Scholar)
Jingyan Yu (Postdoctoral Fellow, also collaborating with Prof. Rozenblat and P.D. Tonini)
Frederick Iat-Hin Tam (PhD Student)
Milton Gomez (PhD Student)
Francesco Zanetta (Visiting PhD Student from ETH/MeteoSwiss)
Deborah Bassotto (Visiting PhD Student from University of Valencia)
Fabien Augsburger (Masters Student)
Sabrina Damiani (IDYST Admin Officer)Alumni
Marine Berthier (Previously ECCE Masters Intern, now Masters student at KTH)
Jo Lécuyer (Previously Masters Intern, now Masters Student at OACOS)
Aser Atawya (Previously Bachelor Fellow)
Marie McGraw (Previously Visiting Research Scientist at UNIL)
Meryam Cherqaoui Fassi (Previously Bachelor Student at UNIL, now Masters Student at ETH)
Publications
Preprints
• (Submitted) Feldmann, M. T. Beucler, M. Gomez & O. Martius: Lightning-Fast Thunderstorm Warnings: Predicting Severe Convective Environments with Global Neural Weather Models.
• (Submitted) Christopoulos, C., I. Lopez-Gomez, T. Beucler, Y. Cohen, C. Kawczynski, O. Dunbar & T. Schneider: Online Learning of Entrainment Closures in a Hybrid Machine Learning Parameterization.
• (Submitted) Behrens, G., T. Beucler, F. Iglesias-Suarez, S. Yu, P. Gentine, M. Pritchard, M. Schwabe & V. Eyring: Improving Atmospheric Processes in Earth System Models with Deep Learning Ensembles and Stochastic Parameterizations.
• (Submitted) Tam, F. I, T. Beucler & J. Ruppert: Identifying Three-Dimensional Radiative Patterns Associated with Early Tropical Cyclone Intensification.
• (Submitted) Cache, T., M. Gomez, T. Beucler, J. Blagojevic, J. Leitao & N. Peleg: Enhancing generalizability of data-driven urban flood models by incorporating contextual information.
• (Submitted) Aarnink, J., T. Beucler, M. Vuaridel & V. Ruiz-Villanueva: Automatic detection of instream large wood in videos using deep learning.
• (Submitted) Yu, S., Z. Hu, A. Subramaniam, W. Hannah, L. Peng, J. Lin, M. Bhouri, R. Gupta, B. Lütjens, J. Will, G. Behrens, J. Busecke, N. Loose, C. Stern, T. Beucler et al.: ClimSim-Online: A Large Multi-scale Dataset and Framework for Hybrid ML-physics Climate Emulation.
• (Submitted) Gomez, M., & T. Beucler: Lessons Learned: Reproducibility, Replicability, and When to Stop.
• (Submitted) Lin, J., S. Yu, L. Peng, T. Beucler, E. Wong-Toi, Z. Hu, P. Gentine, M. Geleta & M. Pritchard: Sampling Hybrid Climate Simulation at Scale to Reliably Improve Machine Learning Parameterization.
2024
• (Whitepaper) Beucler, T., E. Koch, S. Kotlarski, D. Leutwyler, A. Michel & J. Koh: Next-Generation Earth System Models: Towards Reliable Hybrid Models for Weather and Climate Applications. SATW Whitepaper on “AI for Climate Change Mitigation”, 5.2.
• Rampal, N., S. Hobeichi, P. B. Gibson, J. Baño-Medina, G. Abramowitz, T. Beucler, J. González-Abad, W. Chapman, P. Harder & José Manuel Gutiérrez: Enhancing Regional Climate Downscaling Through Advances in Machine Learning. Artificial Intelligence for the Earth Systems, 3(2), 230066.
• Grundner, A., T. Beucler, P. Gentine & V. Eyring: Data-Driven Equation Discovery of a Cloud Cover Parameterization. Journal of Advances in Modeling Earth Systems, 16, e2023MS003763 [pdf].
• Iglesias-Suarez, F., P. Gentine, B. Solino-Fernandez, T. Beucler, M. Pritchard, J. Runge & V. Eyring: Causally-informed deep learning to improve climate models and projections. Journal of Geophysical Research: Atmospheres, 129, e2023JD039202 [pdf].
• Mooers, G., T. Beucler, M. Pritchard & S. Mandt: Understanding Precipitation Changes through Unsupervised Machine Learning. Environmental Data Science, 3, e3 [pdf].
• Beucler, T., P. Gentine, J. Yuval, A. Gupta, L. Peng, J. Lin, S. Yu, S. Rasp, F. Ahmed, P. O’Gorman, D. Neelin, N. Lutsko & M. Pritchard: Climate-Invariant Machine Learning. Science Advances, 10, eadj7250 [pdf].
2023
• Beucler, T., I. Ebert-Uphoff, S. Rasp, M. Pritchard & P. Gentine: Machine Learning for Clouds and Climate. Clouds and Their Climatic Impact: Radiation, Circulation, and Precipitation, edited by: Sullivan, SC and Hoose, C., Wiley–American Geophysical Union: 327-346. [pdf]
• (Workshop) Lin, J., M. A. Bhouri, T. Beucler, S. Yu & M. Pritchard: Stress-testing the coupled behavior of hybrid physics-machine learning climate simulations on an unseen, warmer climate. 2023 Conference on Neural Information Processing Systems.
• Mooers, G., M. Pritchard, T. Beucler, P. Srivastava, H. Mangipudi, L. Peng, P. Gentine & M. Pritchard: Comparing Storm Resolving Models and Climates via Unsupervised Machine Learning. Scientific Reports. [pdf]
• Zanetta, F., D. Nerini, T. Beucler & M. Liniger: Physics-constrained deep learning postprocessing of temperature and humidity. Artificial Intelligence for the Earth Systems, 2, e220089. [pdf]
• (NeurIPS 2023 Conference) Yu, S., W. Hannah, L. Peng, M. Bhouri, R. Gupta, J. Lin, B. Lütjens, J. Will, G. Behrens, J. Busecke, N. Loose, C. Stern, T. Beucler et al.: ClimSim: A large multi-scale dataset for hybrid physics-machine learning climate emulation. Advances in Neural Information Processing Systems. “Oustanding Datasets and Benchmarks” award. [pdf]
• Ganesh S., S., T. Beucler, F. I. Tam, M. Gomez, J. Runge & A. Gerhardus: Selecting Robust Features for Machine-Learning Applications using Multidata Causal Discovery. Environmental Data Science, 2: e27. [pdf]
2022
• Grundner, A., T. Beucler, P. Gentine, F. Iglesias-Suarez, M. Giorgetta & V. Eyring: Deep Learning Based Cloud Cover Parameterization for ICON. Journal of Advances in Modeling Earth Systems, e2021MS002959. [pdf]
• Wu, Z., T. Beucler, E. Székely, W. Ball & D. Domeisen: Modeling Stratospheric Polar Vortex Variation and Identifying Vortex Extremes Using Explainable Machine Learning. Environmental Data Science 1: e17. [pdf]
• Behrens, G., T. Beucler, P. Gentine, F. Iglesias-Suarez, M. Pritchard & V. Eyring: Non‐Linear Dimensionality Reduction with a Variational Encoder Decoder to Understand Convective Processes in Climate Models. Journal of Advances in Modeling Earth Systems, e2022MS003130. [pdf]
2021
• (Workshop) Mangipudi, H., G. Mooers, M. Pritchard, T. Beucler & S. Mandt: Analyzing High-Resolution Clouds and Convection using Multi-Channel VAEs. 2021 Conference on Neural Information Processing Systems.
• Gentine, P., V. Eyring & T. Beucler: Deep Learning for the Parametrization of Subgrid Processes in Climate Models. Deep Learning for the Earth Sciences: A Comprehensive Approach to Remote Sensing, Climate Science, and Geosciences, 307-314.
• Mooers, G., M. Pritchard, T. Beucler, J. Ott, G. Yacalis, P. Baldi & P. Gentine: Assessing the Potential of Deep Learning for Emulating Cloud Superparameterization in Climate Models with Real-Geography Boundary Conditions. Journal of Advances in Modeling Earth Systems, 13, e2020MS002385. [pdf]
• Beucler, T., M. Pritchard, S. Rasp, J. Ott, P. Baldi & P. Gentine: Enforcing Analytic Constraints in Neural-Networks Emulating Physical Systems. Physical Review Letters, 126.9: 098302. Editors’ Suggestion. [pdf]
2020
• Brenowitz, N., T. Beucler, M. Pritchard & C. Bretherton: Interpreting and Stabilizing Machine-Learning Parametrizations of Convection. Journal of the Atmospheric Sciences, 77, 4357-4375.
• (Workshop) Beucler, T., M. Pritchard, P. Gentine & S. Rasp: Towards Physically-Consistent, Data-Driven Models of Convection. IEEE International Geoscience and Remote Sensing Symposium 2020. [pdf]
• (Workshop) Mooers, G., J. Tuyls, S. Mandt, M. Pritchard & T. Beucler: Generative Modeling of Atmospheric Convection. Proceedings of the 10th International Conference on Climate Informatics, 98-105. [pdf]
• Beucler, T., D. Leutwyler & J. Windmiller: Quantifying Convective Aggregation Using the Tropical Moist Margin’s Length. Journal of Advances in Modeling Earth Systems, 12, e2020MS002092. [pdf]
• Abbott, T., T. Cronin & T. Beucler: Convective dynamics and the response of precipitation extremes to warming in radiative-convective equilibrium. Journal of the Atmospheric Sciences, 77, 1637-1660. [pdf]
2016-2019
• Beucler, T., T. Abbott, T. Cronin & M. Pritchard: Comparing Convective Self‐Aggregation in Idealized Models to Observed Moist Static Energy Variability Near the Equator. Geophysical Research Letters, 46, 17-18. [pdf]
• (Workshop) Beucler, T., S. Rasp, M. Pritchard & P. Gentine: Achieving Conservation of Energy in Neural Network Emulators for Climate Modeling. 2019 International Conference on Machine Learning.
• (Thesis) Beucler, T.: Interaction between Water Vapor, Radiation and Convection in the Tropics. Ph.D. Thesis in Atmospheric Science.
• Beucler, T. & T. Cronin: A Budget for the Size of Convective Self-Aggregation. Quarterly Journal of the Royal Meteorological Society, 145, 947-966.
• Beucler, T., T. Cronin & K. Emanuel: A Linear Response Framework for Radiative-Convective Instability. Journal of Advances in Modeling Earth Systems, 10(8), 1924-1951.
• Beucler, T. & T. Cronin: Moisture-Radiative Cooling Instability. Journal of Advances in Modeling Earth Systems, 8, 1620–1640.
• Beucler, T.: A Correlated Stochastic Model for the Large-scale Advection, Condensation and Diffusion of Water Vapour. Quarterly Journal of the Royal Meteorological Society, 142, 1721–1731.
• (Thesis) Beucler, T.: Self-aggregation phenomenon in cyclogenesis, Masters Thesis in Fluid Mechanics.
Presentation Recordings
2024
• Beucler, T.: Tropical precipitation in a changing climate. Joint CLIMACT-ECCE seminar.
• Beucler, T.: Atmospheric physics-guided machine learning for climate modeling and weather forecasting. US CLIVAR PPAI Webinar.
• Beucler, T.: Causal Feature Selection for Tropical Cyclone Intensity Forecasting. 104th AMS Annual Meeting.
2023
• Beucler, T. & M. McGraw: AI for tropical meteorology: Challenges and opportunities. ITU“AI for Good” seminar series.
• Beucler, T.: Generating Climate Model Hierarchies from Data using ML. Core Science Keynote, 103rd AMS Annual Meeting.
2022
• Beucler, T.: Atmospheric Physics-Guided Machine Learning for Climate Modeling and Weather Forecasting. ESiWACE2 2nd Virtual Workshop on Emerging Technologies for Weather and Climate Modelling
• Beucler, T.: Climate-Invariant Machine Learning. AGCI Workshop on “Exploring the Frontiers in Earth System Modeling with Machine Learning and Big Data”
• Beucler, T.: Atmospheric Physics-Guided Machine Learning. IXXI Conference on ML and sampling methods for climate and physics (short version here from AMLD)
• Beucler, T.: Physics-Guided and Causally-Informed Machine Learning for Climate Modelling. ECMWF Machine Learning Workshop
2020
• Beucler, T.: Climate-Invariant Nets: Physical Rescalings Help NNs Generalize to Out-of-sample Climates. SIAM Mathematics of Planet Earth 2020
• Beucler, T.: Towards Physically-Consistent, Data-Driven and Interpretable Models of Convection. NOAA STAR Artificial Intelligence Seminar
• Beucler, T.: Building a Hierarchy of Hybrid, Neural Network Models of Convection. 100th American Meteorological Society Annual Meeting
• Beucler, T.: Comparing Convective Self-Aggregation in Models to Obs. MSE Variability. 100th American Meteorological Society Annual Meeting
2016-2019
• Beucler, T.: A Spectral Budget for the Size of Convective Self-Aggregation. 33rd Conference on Hurricanes and Tropical Meteorology
• Beucler, T.: A Moist Static Energy Perspective on Atmospheric Rivers. 17th Conference on Mesoscale Processes
• Beucler, T.: The Vertical Structure of Radiative-Convective Instability. 21st Conference on Atmospheric and Oceanic Fluid Dynamics
• Beucler, T.: Instabilities of Radiative Convective Equilibrium with an Interactive Surface. 32nd Conference on Hurricanes and Tropical Meteorology