Attention-based Models for Snow-Water Equivalent Prediction

TL;DR

This paper introduces an attention-based machine learning framework for predicting Snow Water-Equivalent (SWE), leveraging spatial and temporal attention mechanisms to improve accuracy over existing methods, aiding water management decisions.

Contribution

It presents a novel attention-based modeling framework for SWE prediction, incorporating spatial and temporal attention, and demonstrates superior performance over existing ML approaches.

Findings

Attention models outperform other ML methods.

Spatial and temporal attention capture different correlation patterns.

Framework provides a pathway for complete SWE mapping.

Abstract

Snow Water-Equivalent (SWE) -- the amount of water available if snowpack is melted -- is a key decision variable used by water management agencies to make irrigation, flood control, power generation and drought management decisions. SWE values vary spatiotemporally -- affected by weather, topography and other environmental factors. While daily SWE can be measured by Snow Telemetry (SNOTEL) stations with requisite instrumentation, such stations are spatially sparse requiring interpolation techniques to create spatiotemporally complete data. While recent efforts have explored machine learning (ML) for SWE prediction, a number of recent ML advances have yet to be considered. The main contribution of this paper is to explore one such ML advance, attention mechanisms, for SWE prediction. Our hypothesis is that attention has a unique ability to capture and exploit correlations that may exist across locations or the temporal spectrum (or both). We present a generic attention-based modeling framework for SWE prediction and adapt it to capture spatial attention and temporal attention. Our experimental results on 323 SNOTEL stations in the Western U.S. demonstrate that our attention-based models outperform other machine learning approaches. We also provide key results highlighting the differences between spatial and temporal attention in this context and a roadmap toward deployment for generating spatially-complete SWE maps.