Dissertation Proposal - Ibrahim Alabi

Advancing Snow Water Equivalent Monitoring with Machine Learning and L-band InSAR Data

Presented by Ibrahim Alabi, Data Science emphasis

Hybrid presentation: Attend in-person at Environmental Research Building Room 1127 or register to attend online via Zoom

Abstract

In many parts of the world, the arrival of snow is not just a sign of changing seasons or a reason to reach for that cup of hot cocoa—it signifies the replenishment of a life-essential resource: water. Snow-dependent basins across the northern hemisphere currently serve an estimated 2 billion people. Therefore, accurately quantifying snow water equivalent (SWE) is paramount for water resource managers and the communities they serve. However, in-situ observations, while reliable, are logistically challenging, time-consuming, and impractical for extensive use. Consequently, remote sensing technologies have emerged as a viable alternative to ground-based measurements. Unlike in-situ measurements, remote sensing allows data collection over vast and remote areas, presenting a more complete picture of snowpack conditions. However, existing satellite technologies, such as passive microwave sensors, suffer from coarse resolution (~25 km), and optical remote sensing is weather-dependent and unable to penetrate dense forest cover. L-band Interferometric Synthetic Aperture Radar (InSAR), which operates at frequencies that penetrate cloud cover and tree canopy, emerges as a potential solution. My research aims to advance snow monitoring capabilities by applying state-of-the-art Machine Learning (ML) techniques to L-band InSAR data. With the anticipated launch of the NASA-ISRO SAR satellite in January 2024, this work has the potential to complement existing snow monitoring practices by facilitating cost-effective, high-resolution, and extensive snow data acquisition.

Committee

Dr. Hans-Peter Marshall (Chair), Dr. Jodi Mead (Co-Chair), Dr. Kyungduk Ko, Dr. Ernesto Trujillo