Faye Hsu, Ziheng Sun, Gokul Prathin, Sanjana Achan

In recent years, the scientific community focused on snow dynamics has witnessed a surge in efforts aimed at enhancing Snow Water Equivalent (SWE) monitoring capabilities, largely propelled by the incorporation of Machine Learning (ML) techniques. This comprehensive review delves into the current state of research within this evolving domain, shedding light on the indispensable role of precise SWE predictions in bolstering water resource management strategies and fostering environmental resilience amidst the backdrop of climate variability. By critically examining existing literature, this review underscores the imperative nature of ML-based methodologies in overcoming the inherent limitations of traditional monitoring paradigms. Highlighting the adaptability and promise of various ML algorithms, this paper serves as a cornerstone resource for researchers, practitioners, and policymakers dedicated to advancing SWE estimation practices and, consequently, promoting sustainable water resource management in snow-dominated regions.