I am currently a Ph.D. Candidate with Dornsife Spatial Sciences Institute at University of Southern California (USC). I was an RA with the University of Hong Kong. I received my B.S. degree from Sun Yat-Sen University.
My research integrates cutting-edge machine learning with satellite data to tackle global challenges, particularly in support of the United Nations Sustainable Development Goals. My work so far encompasses crop mapping, radar and hyperspectral imaging, artificial light at night, and, more recently, the impacts of daily temperature variations on human health. To analyze remote sensing data, I develop AI models to address problems such as open-world classification, image classification with limited resources, and temperature data reconstruction. So far, I've published more than 10 first-author peer-reviewed papers in leading journals and conferences, including ISPRS Journal P&RS, IEEE TGRS, IEEE GRSL, IEEE JSTARS, Social Science & Medicine, JGR Atmospheres, and PNAS Nexus.
Open Science (Code & Data)MDL4OW (Multitask Deep Learning for Open World) for open-set hyperspectral image classification
DFGP (Deep Feature Gaussian Processes) for single-scene AOD reconstruction
LCZNet for local climate zone mapping
Remote Sensing Image Classification: baseline method implementation for classic remote sensing image classification