Date of Award

2024

Document Type

Open Access Master's Thesis

Degree Name

Master of Science in Integrated Geospatial Technology (MS)

Administrative Home Department

Department of Civil, Environmental, and Geospatial Engineering

Advisor 1

Tao Liu

Advisor 2

Jae Sung Kim

Committee Member 1

Parth Parimalbhai Bhatt

Abstract

Accurately estimating Aboveground Biomass Density (AGBD) is crucial for managing Earth's carbon cycle and informing climate strategies. NASA's GEDI mission advances global forest mapping, but traditional linear models often yield less reliable AGBD estimates. This study enhances AGBD estimation using deep learning models with NEON ground-truth data and simulated GEDI waveforms. We compared 1D CNNs, LSTMs, and pre-trained CNNs to traditional models. The ResNet152 model outperformed linear regression, achieving an R² of 0.68, demonstrating a 17% improvement. Our experiments also demonstrate the importance of large, diverse datasets, particularly for training deep learning models.

Share

COinS