Leveraging Geospatial Foundation Model to estimate Aboveground Biomass and studying it's effect on forest temperature (Proposals Track)
Arnav Goel (Purdue University); Gaia Cervini (Purdue University); Jinha Jung (Purdue University); Songlin Fei (Purdue University)
Abstract
Accurate above-ground biomass (AGB) estimation is critical for assessing forest health and understanding its role in the global carbon cycle. This study shall leverage NASA/IBM's Prithvi 2.0, a geospatial foundation model trained on Harmonized Landsat-Sentinel 2 (HLS) data, to estimate AGB using Sentinel-1 radar and Sentinel-2 multispectral imagery. By training on data covering different forest biomes, we aim to develop a robust and transferable model. We shall also investigate the relationship between AGB and land surface temperature (LST) using ECOSTRESS sensor data to understand forest-climate interactions.