Using Ambient Noise Tomography and Machine Learning Techniques to Track Groundwater Levels across Western Montana
For western Montana’s irrigation, municipal water supply, and industrial use, groundwater is vital. However, sparse monitoring wells and geophysical techniques with relatively low temporal or spatial resolutions have limited current groundwater monitoring. Because seismic velocity is sensitive to groundwater fluctuations, this project proposes using ambient noise tomography and machine learning methods to analyze the relationship between daily changes in groundwater levels and daily variations in seismic velocity at monitoring well locations. By analyzing these patterns, the project aims to estimate changes in groundwater levels and storage across the region based on seismic velocity variations observed between monitoring wells. This project will use broadband seismic data from the Montana Regional Seismic Network (MRSN) and groundwater level data from the Ground Water Information Center (GWIC). Ultimately, this research will provide continuous, cost-effective, non-invasive groundwater monitoring with improved spatial coverage, contributing to the sustainable management of water resources in western Montana.
Dr. Muchen Sun is an Assistant Professor in the Department of Geological Engineering at Montana Technological University. Dr. Sun’s research focuses on investigating the structure and dynamics of the crust and mantle in active regions, such as continental rifts, faults, volcanoes, and subduction zones, using passive seismological methods like receiver functions, shear wave splitting, and seismic tomography. Additionally, his research involves microseismic monitoring during hydraulic fracturing processes in unconventional oil and gas development, seismic signal analysis, and 3-D seismic data interpretation during oil and gas exploration.