HydroVision: LiDAR-Guided Hydrometric Prediction with Vision Transformers and Hybrid Graph Learning

TL;DR

HydroVision introduces a novel approach combining LiDAR data, Vision Transformers, and hybrid graph learning to improve hydrometric predictions, achieving significant error reduction over multiple water stations.

Contribution

The paper presents a hybrid graph learning framework integrating static and dynamic graphs with Vision Transformers for enhanced hydrometric forecasting.

Findings

Reduces prediction error by 10% on average across stations.

Improves long-term forecast accuracy up to 12 days ahead.

Demonstrates effectiveness on Quebec water station data.

Abstract

Hydrometric forecasting is crucial for managing water resources, flood prediction, and environmental protection. Water stations are interconnected, and this connectivity influences the measurements at other stations. However, the dynamic and implicit nature of water flow paths makes it challenging to extract a priori knowledge of the connectivity structure. We hypothesize that terrain elevation significantly affects flow and connectivity. To incorporate this, we use LiDAR terrain elevation data encoded through a Vision Transformer (ViT). The ViT, which has demonstrated excellent performance in image classification by directly applying transformers to sequences of image patches, efficiently captures spatial features of terrain elevation. To account for both spatial and temporal features, we employ GRU blocks enhanced with graph convolution, a method widely used in the literature. We propose a hybrid graph learning structure that combines static and dynamic graph learning. A static graph, derived from transformer-encoded LiDAR data, captures terrain elevation relationships, while a dynamic graph adapts to temporal changes, improving the overall graph representation. We apply graph convolution in two layers through these static and dynamic graphs. Our method makes daily predictions up to 12 days ahead. Empirical results from multiple water stations in Quebec demonstrate that our method significantly reduces prediction error by an average of 10\% across all days, with greater improvements for longer forecasting horizons.