Physics-informed deep learning framework to model intense precipitation events at super resolution

Bernardo Teufel, Fernanda Custodio Pereira do Carmo, Laxmi Sushama, Lijun Sun, M. Naveed Khaliq, Stéphane Bélair, Asaad Yahia Shamseldin, D. Nagesh Kumar, Jai Vaze

Geoscience Letters · 18 April 2023 · Environment and Climate Change Canada (ECCC)

Paper PDF

In one sentence. A physics-informed recurrent deep learning model super-resolves regional climate precipitation from 2.5 km to 250 m, producing realistic intense short-duration events over Montreal.

Abstract

Physical modeling of precipitation at fine (sub-kilometer) spatial scales is computationally very expensive. This study develops a highly efficient framework for this task by coupling deep learning (DL) and physical modeling. This framework is developed and tested using regional climate simulations performed over a domain covering Montreal and adjoining regions, for the summers of 2015-2020, at 2.5 km and 250 m resolutions. The DL framework uses a recurrent approach and considers atmospheric physical processes, such as advection, to generate high-resolution information from low-resolution data, which enables it to recreate fine details and produce temporally consistent fields. The DL framework generates realistic high-resolution precipitation estimates, including intense short-duration precipitation events, which allows it to be applied in engineering problems, such as evaluating the climate resiliency of urban storm drainage systems. The results portray the value of the proposed DL framework, which can be extended to other resolutions, periods, and regions.

Labels

Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.