Defense Presentation Title: Advancing Near Real-Time Deforestation Monitoring via Multi-Source Remote Sensing Data, Landscape Processes and End-User Contributions

Advisor: Dr. Josh Gray, faculty fellow and associate professor in the Department of Forestry and Environmental Resources

Abstract: The proliferation of satellite imagery has facilitated the analysis of deforestation trends using multi-source time series approaches. This long-term combination of data sources can be crucial for near real-time (NRT) monitoring in tropical regions with extensive cloud cover. Yet despite recent progress, methods in multi-source, NRT deforestation monitoring have experienced issues with trade-offs between accuracy and latency, the lack of external spatial data and general inability to incorporate users into the workflow. To address these limitations, my dissertation focused on three main topics: first, a novel NRT detection algorithm was created to explicitly assess multiple spectra of trade-offs; second, landscape processes were incorporated into the algorithm using a Bayesian approach; and finally, we expanded the methodology to develop a continuously-improving model by integrating input from in-situ users.