Google Research

A Deep Learning Architecture for Conservative Dynamical Systems: Application to Rainfall-Runoff Modeling

  • Grey Nearing
  • Frederik Kratzert
  • Daniel Klotz
  • Pieter-Jan Hoedt
  • Günter Klambauer
  • Sepp Hochreiter
  • Hoshin Gupta
  • Sella Nevo
  • Yossi Matias
NeurIPS AI for Earth Sciences workshop (2020)

Abstract

The most accurate and generalizable rainfall-runoff models produced by the hydrological sciences community to-date are based on deep learning, and in particular, on Long Short Term Memory networks (LSTMs). Although LSTMs have an explicit state space and gates that mimic input-state-output relationships, these models are not based on physical principles. We propose a deep learning architecture that is based on the LSTM and obeys conservation principles. The model is benchmarked on the mass-conservation problem of simulating streamflow

Learn more about how we do research

We maintain a portfolio of research projects, providing individuals and teams the freedom to emphasize specific types of work