How Effective are Large Time Series Models in Hydrology? A Study on Water Level Forecasting in Everglades

TL;DR

This study evaluates the effectiveness of large time series models, especially foundation models like Chronos, in predicting water levels in the Everglades, highlighting their potential and limitations in environmental applications.

Contribution

It provides a comprehensive comparison of twelve task-specific and five foundation models for hydrological water level forecasting in the Everglades, revealing the superior performance of Chronos.

Findings

Chronos significantly outperforms other models

Foundation models show varied performance

Task-specific models' effectiveness depends on architecture

Abstract

The Everglades play a crucial role in flood and drought regulation, water resource planning, and ecosystem management in the surrounding regions. However, traditional physics-based and statistical methods for predicting water levels often face significant challenges, including high computational costs and limited adaptability to diverse or unforeseen conditions. Recent advancements in large time series models have demonstrated the potential to address these limitations, with state-of-the-art deep learning and foundation models achieving remarkable success in time series forecasting across various domains. Despite this progress, their application to critical environmental systems, such as the Everglades, remains underexplored. In this study, we fill the gap by investigating twelve task-specific models and five time series foundation models across six categories for a real-world application focused on water level prediction in the Everglades. Our primary results show that the foundation model Chronos significantly outperforms all other models while the remaining foundation models exhibit relatively poor performance. We also noticed that the performance of task-specific models varies with the model architectures, and discussed the possible reasons. We hope our study and findings will inspire the community to explore the applicability of large time series models in hydrological applications. The code and data are available at https://github.com/rahuul2992000/Everglades-Benchmark.