English

A Deep State Space Model for Rainfall-Runoff Simulations

Machine Learning 2025-01-28 v1 Artificial Intelligence Atmospheric and Oceanic Physics

Abstract

The classical way of studying the rainfall-runoff processes in the water cycle relies on conceptual or physically-based hydrologic models. Deep learning (DL) has recently emerged as an alternative and blossomed in hydrology community for rainfall-runoff simulations. However, the decades-old Long Short-Term Memory (LSTM) network remains the benchmark for this task, outperforming newer architectures like Transformers. In this work, we propose a State Space Model (SSM), specifically the Frequency Tuned Diagonal State Space Sequence (S4D-FT) model, for rainfall-runoff simulations. The proposed S4D-FT is benchmarked against the established LSTM and a physically-based Sacramento Soil Moisture Accounting model across 531 watersheds in the contiguous United States (CONUS). Results show that S4D-FT is able to outperform the LSTM model across diverse regions. Our pioneering introduction of the S4D-FT for rainfall-runoff simulations challenges the dominance of LSTM in the hydrology community and expands the arsenal of DL tools available for hydrological modeling.

Keywords

Cite

@article{arxiv.2501.14980,
  title  = {A Deep State Space Model for Rainfall-Runoff Simulations},
  author = {Yihan Wang and Lujun Zhang and Annan Yu and N. Benjamin Erichson and Tiantian Yang},
  journal= {arXiv preprint arXiv:2501.14980},
  year   = {2025}
}
R2 v1 2026-06-28T21:17:10.250Z