Analyzing Historical Snow Water Equivalent (SWE) Data: Trends, Economic and Social Impacts, and Prediction Accuracy Assessment

Authors

  • Anping Huang Center for Spatial Information Science and Systems, Department of Geography and Geoinformation Science, George Mason University, Fairfax, VA
  • Shourya Mehta Center for Spatial Information Science and Systems, Department of Geography and Geoinformation Science, George Mason University, Fairfax, VA
  • Yaron Li Center for Spatial Information Science and Systems, Department of Geography and Geoinformation Science, George Mason University, Fairfax, VA
  • Zeinab Yassin Center for Spatial Information Science and Systems, Department of Geography and Geoinformation Science, George Mason University, Fairfax, VA
  • Sai Vivek Vangaveti Center for Spatial Information Science and Systems, Department of Geography and Geoinformation Science, George Mason University, Fairfax, VA
  • Ziheng Sun Center for Spatial Information Science and Systems, Department of Geography and Geoinformation Science, George Mason University, Fairfax, VA

Abstract

The accumulation and melting of snow water significantly impacts water resources, energy systems, agricultural
productivity, and ecological balances across diverse regions. This study analyzes trends and variability in Snow Water
Equivalent (SWE) over the past decade, focusing on its effects on agriculture, social dynamics, and economic factors in the
Western United States. Analysis of SWE data collected over 10 years (2013-2023) reveals significant shifts in SWE
patterns, with earlier declines in spring and more severe reductions during summer, driven by accelerated temperature
increases and altered precipitation dynamics. Although SWE variability has known effects on various sectors, there is a
significant gap in integrated studies that combine agricultural, social, and economic impacts, particularly in the Western
U.S. This research addresses this gap by employing advanced machine-learning techniques to analyze the effect of SWE
variability on agricultural productivity and associated economic outcomes. Regression models and machine learning
techniques were utilized to analyze 10 years of SWE data, crop yields, and water availability, focusing on the Western US.
We employed statistical methods and machine learning algorithms based on SWE variability to identify patterns and
relationships within the data and seek actionable insights into agricultural outcomes and their economic impacts,
offering strategies for better water resource management and improved economic resilience in agriculture. We identified
strong correlations between SWE variability and crop yields, with specific impacts on water-intensive crops. This research
provides actionable insights for agricultural planning and water resource management in the face of changing SWE
patterns.

Published

2024-10-13

Issue

Section

College of Science: Department of Geography and Geoinformation Science