B102-01
Analysis of Synthetic Aperture Radar (SAR) over the Seward Peninsula using Machine Learning Techniques

Tuesday, 15 December 2020: 11:30
Virtual
Julian Dann1, Katrina E Bennett1, Emma Lathrop2, Richard H Chen3, Mahta Moghaddam4 and Cathy Jean Wilson2, (1)Los Alamos National Laboratory, Los Alamos, NM, United States, (2)Los Alamos National Laboratory, Earth and Environmental Science Division, Los Alamos, NM, United States, (3)Jet Propulsion Laboratory, Pasadena, CA, United States, (4)University of Southern California, Ming Hsieh Department of Electrical and Computer Engineering, Los Angeles, CA, United States
Abstract:
Soil moisture exerts a fundamental control on vegetation, energy balance, and the carbon cycle in Arctic ecosystems, but it is still not well understood in vast, remote, and understudied regions of the North. Using P-Band synthetic aperture radar (SAR) backscatter from the Airborne Microwave Observatory of Subcanopy and Subsurface (AirMOSS) instrument it is possible to extract information on the seasonally-thawed active layer which lies directly above permafrost including: the active layer thickness and soil moisture. In this case, remotely-sensed soil moisture is derived from the SAR imagery using a time series three-layer dielectric forward inversion model.(Chen et al. 2019) This project is a collaboration between researchers in the DOE Office of Science Next-Generation Ecosystem Experiments (NGEE-Arctic) and the NASA Arctic Boreal Vulnerability Experiment (ABoVE) to develop regional soil moisture data products to improve and assess Earth System Model predictions. Here we present a random forest model that quantifies the impact of topography, geomorphology, and vegetation on the SAR-derived soil moisture product across a large swath of the Seward Peninsula. Results of this study suggest that soil moisture on the Seward Peninsula is driven primarily by elevation, precipitation, and NDVI.

LA-UR-20-25667

Previous Abstract | Next Abstract >>