Hierarchically Disentangled Recurrent Network for Factorizing System Dynamics of Multi-scale Systems: An application on Hydrological Systems

TL;DR

This paper introduces a hierarchical recurrent neural network that models multi-scale hydrological processes, improving streamflow forecasting accuracy across diverse conditions and demonstrating robustness with limited data.

Contribution

The paper proposes a novel hierarchical recurrent neural architecture that factorizes multi-scale system dynamics and captures their interactions for improved hydrological forecasting.

Findings

Outperforms standard baselines including physics-based and transformer models.

Effective in low runoff and cold climate catchments.

Maintains accuracy with limited training data through pre-training and global models.

Abstract

We present a framework for modeling multi-scale processes, and study its performance in the context of streamflow forecasting in hydrology. Specifically, we propose a novel hierarchical recurrent neural architecture that factorizes the system dynamics at multiple temporal scales and captures their interactions. This framework consists of an inverse and a forward model. The inverse model is used to empirically resolve the system's temporal modes from data (physical model simulations, observed data, or a combination of them from the past), and these states are then used in the forward model to predict streamflow. Experiments on several catchments from the National Weather Service North Central River Forecast Center show that FHNN outperforms standard baselines, including physics-based models and transformer-based approaches. The model demonstrates particular effectiveness in catchments with low runoff ratios and colder climates. We further validate FHNN on the CAMELS (Catchment Attributes and MEteorology for Large-sample Studies), which is a widely used continental-scale hydrology benchmark dataset, confirming consistent performance improvements for 1-7 day streamflow forecasts across diverse hydrological conditions. Additionally, we show that FHNN can maintain accuracy even with limited training data through effective pre-training strategies and training global models.