Di Yang
Assistant Professor | University of Florida
Gainesville, FL, UNITED STATES
Di Yang is an expert in remote sensing and geospatial AI, integrating citizen science and Earth observation for environmental monitoring.
Biography
Di Yang's research focuses on advancing geospatial artificial intelligence (GeoAI) and remote sensing applications for understanding human-environment interactions. She develops innovative deep-learning approaches to analyze satellite imagery and citizen science data for monitoring forest management practices, land use change, and ecosystem dynamics. Currently, she leads projects integrating multi-source Earth observation data with artificial intelligence to improve our understanding of landscape-scale environmental processes and support evidence-based land management decisions. Her work bridges the gap between cutting-edge machine learning techniques and practical environmental challenges, with particular emphasis on forest disturbance patterns, land use legacies, and citizen-driven environmental monitoring.
Areas of Expertise (9)
Forest Management
Geospatial Artificial Intelligence (GeoAI)
Cloud-based Geospatial Computing
Machine Learning and Artificial Intelligence for Geospatial Applications
Remote Sensing
Earth Observation
Citizen Sciene
Environmental Monitoring and Modeling
Multi-source Data Fusion
Articles (3)
Classification and clustering analysis of standing dead trees and associated park asset wildfire vulnerability in Yellowstone National Park
Forest EcosystemsCarolyn Prescott, et. al
2025-04-01
In the Rocky Mountain and Pacific Northwest regions of the United States, forests include extensive portions of standing dead trees. These regions showcase an intriguing phenomenon where the combined biomass of standing dead trees surpasses that of fallen and decomposing woody debris.
GLOBE Observer: A Case Study in Advancing Earth System Knowledge with AI-Powered Citizen Science
Citizen SciencePeder V. Nelson, et. al
2024-10-28
Citizen science and artificial intelligence (AI) complement each other by harnessing the strengths of both human and machine capabilities. Citizen science generates terabytes of raw numerical, text, and image data, the analysis of which requires automated techniques to process in an efficient manner.
Land cover mapping via crowdsourced multi-directional views: The more directional views, the better
International Journal of Applied Earth Observation and GeoinformationXiao Huang, et. al
2023-08-01
In the last decades, a number of crowdsourced land cover datasets have been developed, owning to their great potential to provide human-centric ground observations. In this study, we investigated the GLOBE Observer Land Cover program by assessing the efficacy of its multi-directional data-collecting protocol.
