Learning Generative Models for Lumped Rainfall-Runoff Modeling

TL;DR

This paper introduces a generative neural network approach for rainfall-runoff modeling that uses latent variables to synthesize realistic runoff time series, achieving comparable accuracy to existing models across global catchments.

Contribution

It proposes a novel low-dimensional latent variable framework for catchment runoff modeling, capturing intrinsic properties with neural networks trained on extensive global data.

Findings

Achieved prediction accuracy comparable to deep learning and conventional models.

Successfully modeled runoff across diverse global catchments.

Identified challenges like equifinality and latent variable interpretation.

Abstract

This study presents a novel generative modeling approach to rainfall-runoff modeling, focusing on the synthesis of realistic daily catchment runoff time series in response to catchment-averaged climate forcing. Unlike traditional process-based lumped hydrologic models that depend on predefined sets of variables describing catchment physical properties, our approach uses a small number of latent variables to characterize runoff generation processes. These latent variables encapsulate the intrinsic properties of a catchment and can be inferred from catchment climate forcing and discharge data. By sampling from the latent variable space, the model generates runoff time series that closely resemble real-world observations. In this study, we trained the generative models using neural networks on data from over 3,000 global catchments and achieved prediction accuracies comparable to current deep learning models and various conventional lumped models, both within the catchments from the training set and from other regions worldwide. This suggests that the runoff generation process of catchments can be effectively captured by a low-dimensional latent representation. Yet, challenges such as equifinality and optimal determination of latent variables remain. Future research should focus on refining parameter estimation methods and exploring the physical meaning of these latent dimensions to improve model applicability and robustness. This generative approach offers a promising alternative for hydrological modeling that requires minimal assumptions about the physical processes of the catchment.