Twin Cities WRS Seminar
Physics Guided Deep Learning Models for Hydrology
Surface runoff prediction is one of the key challenges in the field of hydrology due to the complex interplay between multiple non-linear physical mechanisms behind runoff generation. While physical models are rooted in rich understanding of the physical processes, a significant performance gap still remains which can be potentially addressed by leveraging the recent advances in machine learning. The goal of this work is to incorporate our understanding of physical processes and constraints in hydrology into machine learning algorithms, and thus bridge the performance gap while reducing the need for large amounts of data compared to traditional data-driven approaches. In particular, we propose an LSTM based deep learning architecture that is coupled with SWAT (Soil and Water Assessment Tool) which is widely used by the hydrology community to model surface runoff. The key idea of the approach is to model auxiliary intermediate processes that connect weather drivers to surface runoff, instead of directly modeling runoff from weather variables. The efficacy of the approach is being analyzed on a small catchment located in the South Branch of the Root River Watershed in southeast Minnesota. Apart from observation data on runoff, the approach also makes use of a 200-year synthetic dataset generated by SWAT to improve the performance while reducing convergence time. In the early phases of this study, simpler versions of the SWAT model are being used in order to achieve a system understanding of the coupling of physics and machine learning. As more complexity is introduced into the present implementation, the research result of this case study will be generalized to more sophisticated cases where spatial heterogeneities are evolved.
Join the Zoom Meeting
Meeting ID: 943 2193 2246