Dissertation Proposal - Evi Ofekeze

Machine Learning for Snow Depth Estimation and Avalanche Detection Using Acoustic and Microwave Remote Sensing Measurements

Presented by Evi Ofekeze, Computing PhD Data Science emphasis

Hybrid presentation: Attend in-person at Environmental Research Building (ERB) Room 1161 or register to attend online via Zoom

Abstract

The arrival of snow in winter months worldwide signifies a new snow season for recreational snow activities. However, seasonal snow affects our lives in so much more ways. For instance, seasonal snow significantly affects the earth’s water supply, serving as a primary water source for numerous mountain streams and contributing over 75% of the water resources utilized for human consumption, irrigation in agriculture, and hydroelectric power generation in some downstream regions such as the western United States; Seasonal snow in mountainous forests is also crucial in hydrology and essential for water resource management and climate studies. While having these amazing benefits, fresh snow also signifies the potential arrival of snow avalanches. This natural hazard can negatively affect economic activities. It can sometimes lead to loss of life, such as those experienced recently throughout the Alps in 2018 and 2019, causing considerable damage to the population and infrastructure. In this dissertation proposal, I explore ways to harness the benefits of snow by exploring new ways to improve snow depth estimation, which is a key component of estimating the water a snowpack contains. I also explore ways to mitigate the adverse effects of snow-related hazards through early detection of snow avalanches, thus enabling an efficient and effective emergency response and planning through improved operational forecasting, which is crucial for preventing loss of life and property.

Committee

Dr. Hans-Peter Marshall, Dr. Jodi Mead, Dr. Jeffrey B. Johnson, Dr. Nancy Glenn