SEMINAR 2026
Improving Tropical Climate Projections: From Numerical Models to Machine Learning
| Speaker | Dr Shuchang Liu, Massachusetts Institute of Technology, USA |
| Date/Time | Monday, 2 Feb, 3pm |
| Location | S11-02-07 Conference Room |
| Host | Prof Yi Ming, Institute Professor of Climate Science and Society, Schiller Institute for Integrated Science and Society; |
Abstract
Reliable projections of climate extremes are vital for adaptation and resilience in the tropics, yet current models struggle to capture the meso-scale atmosphere processes driving these events. This talk presents an integrated approach that bridges high-resolution numerical modeling and machine learning to improve the fidelity and efficiency of tropical climate projections. I will first show how systematic calibration and bias-corrected downscaling enhance the realism of tropical simulations, and introduce CERA (Climate-Invariant Encoding through Representation Alignment), a physics-guided machine learning framework that generalizes across warming scenarios. Together, these advances pave the way for physics-consistent machine learning climate models that enable more credible and actionable projections of extreme weather in a changing climate.
Biography
Dr Shuchang Liu is a second-year postdoctoral researcher at MIT (funded by Swiss National Science Foundation fellowship), working with Prof. Paul O’Gorman.
Dr Liu completed her PhD in Atmospheric and Climate Science at ETH Zürich, advised by Prof. Christoph Schär, and hold a Master’s degree from Tsinghua University and a Bachelor’s degree from Nanjing University.
Dr Liu’s research interests centers on improving regional climate projections through the combined use of high-resolution climate models and machine learning.