Timezone: »

 
Physics-Constrained Deep Learning for Climate Downscaling
Paula Harder · Qidong Yang · Venkatesh Ramesh · Prasanna Sattigeri · Alex Hernandez-Garcia · Campbell Watson · Daniela Szwarcman · David Rolnick

@
in Women in Machine Learning »

The availability of reliable, high-resolution climate and weather data is important to inform long-term decisions on climate adaptation and mitigation and to guide rapid responses to extreme events. Forecasting models are limited by computational costs and therefore often predict quantities at a coarse spatial resolution. Statistical downscaling can provide an efficient method of upsampling low-resolution data. In this field, deep learning has been applied successfully, often using methods from the super-resolution domain in computer vision. Despite often achieving visually compelling results, such models often violate conservation laws when predicting physical variables. In order to conserve important physical quantities, we develop methods that guarantee physical constraints are satisfied by a deep downscaling model while also increasing their performance according to traditional metrics. We introduce two ways of constraining the network: A renormalization layer added to the end of the neural network and a successive approach that scales with increasing upsampling factors. We show the applicability of our methods across different popular architectures and upsampling factors using ERA5 reanalysis data.

[ Poster]  [ Topia] 

Author Information

Paula Harder (Fraunhofer ITWM)
Qidong Yang (New York University)
Venkatesh Ramesh (Mila)
Prasanna Sattigeri (IBM Research)
Alex Hernandez-Garcia (Mila - Quebec AI Institute)
Campbell Watson (IBM Research)

I'm an atmospheric scientist at IBM Research where my research spans climate, weather and water. I was a postdoc at Yale University with Prof. Ron Smith, and completed a PhD at the University of Melbourne with Prof. Todd Lane. Currently leading AI for Climate initiatives with the Future of Climate at IBM Research.

Daniela Szwarcman (IBM-Research Brazil)
David Rolnick (McGill / Mila)

More from the Same Authors