My broad interests are atmospheric physics, deep learning, climate informatics and environmental fluid dynamics. I combine statistics, theory, numerical simulations and observational analyses to improve our understanding of meteorology and climate, and guide the development of operational models of storms and clouds. I am currently an assistant project scientist in atmospheric science affiliated with the University of California, Irvine and Columbia University. I work with Michael Pritchard and Pierre Gentine on combining deep learning and atmospheric physics to develop the first operational neural-network representation of storms and clouds in models used to predict the future climate. During my PhD, I worked at the Lorenz Center at MIT with Timothy Cronin and Kerry Emanuel to better understand storms, radiation, and how they interact with atmospheric water in the Tropics.
(2020) Under review, Brenowitz, N., T. Beucler, M. Pritchard & C. Bretherton: Interpreting and Stabilizing Machine-Learning Parametrizations of Convection. arXiV, 2003.06549.
(2020) Under review, Beucler, T., D. Leutwyler & J. Windmiller: Quantifying Convective Aggregation Using the Tropical Moist Margin’s Length. arXiv, 2002.11301.
(2020) Under review, Beucler, T. et al.: Enforcing Analytic Constraints in Neural-Networks Emulating Physical Systems. arXiv, 1909.00912.
(2020) 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.
(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.
(2019) Beucler, T.: Interaction between Water Vapor, Radiation and Convection in the Tropics, Ph.D. Thesis in Atmospheric Science.
(2018) Beucler, T. & T. Cronin: A Budget for the Size of Convective Self-Aggregation. Quarterly Journal of the Royal Meteorological Society, 145, 947-966.
(2018) 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.
(2016) Beucler, T. & T. Cronin: Moisture-Radiative Cooling Instability. Journal of Advances in Modeling Earth Systems, 8, 1620–1640.
(2016) 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.
(2014) Beucler, T. & K. Emanuel: Self-aggregation phenomenon in cyclogenesis, Masters Thesis in Fluid Mechanics.
Selected Conference Presentations
(2020) Climate-Invariant Nets: Physical Rescalings Help NNs Generalize to Out-of-sample Climates. SIAM Mathematics of Planet Earth 2020
(2020) Towards Physically-Consistent, Data-Driven Models of Convection. IEEE International Geoscience and Remote Sensing Symposium 2020
(2020) Towards Physically-Consistent, Data-Driven and Interpretable Models of Convection. NOAA STAR Artificial Intelligence Seminar
(2020) Building a Hierarchy of Hybrid, Neural Network Models of Convection. 100th American Meteorological Society Annual Meeting
(2020) Comparing Convective Self-Aggregation in Models to Obs. MSE Variability. 100th American Meteorological Society Annual Meeting
(2019) Achieving Conservation of Energy in Neural Network Emulators for Climate Modeling. 2019 International Conference on Machine Learning
(2018) A Spectral Budget for the Size of Convective Self-Aggregation. 33rd Conference on Hurricanes and Tropical Meteorology
(2017) A Moist Static Energy Perspective on Atmospheric Rivers. 17th Conference on Mesoscale Processes
(2017) The Vertical Structure of Radiative-Convective Instability. 21st Conference on Atmospheric and Oceanic Fluid Dynamics
(2016) Instabilities of Radiative Convective Equilibrium with an Interactive Surface. 32nd Conference on Hurricanes and Tropical Meteorology
US CLIVAR Data Science Webinar Series. Co-organizer and Moderator (June 2020-April 2021)
Deep Learning to Represent Sub-Grid Processes in Climate Models. E3SM Blog Post (August 2020)
When the Wind Blows: Predicting how Hurricanes Change with Climate. CaféSci Boston (June 2018)
Higher Grounds. MIT Climate Changed Ideas Competition (January 2018)