Caiwang Zheng, Ph.D.

IGCAST 

Background

Caiwang Zheng, Ph.D., is an Assistant Professor of Plant Phenomics and Image Analysis in the Department of Plant and Soil Science and the Institute of Genomics for Crop Abiotic Stress Tolerance (IGCAST) at Texas Tech University. His research integrates agricultural remote sensing, high-throughput plant phenotyping, and AI-driven image analysis to better understand crop responses to abiotic stress and support plant breeding programs through data-driven selection.

Prior to joining Texas Tech, Dr. Zheng served as a Postdoctoral Research Associate at North Carolina State University and the University of Florida. He holds a Ph.D. in Geomatics from the University of Florida’s School of Forest, Fisheries, and Geomatics Sciences, an M.S. in Global Environmental Change from Beijing Normal University, and a B.S. in Remote Sensing Science and Technology from Southwest Jiaotong University.

Research Interests

His research integrates multi-scale remote sensing, high-throughput phenotyping, image processing, and AI-driven data science to understand and improve crop responses and resilience to environmental stresses, with a particular focus on drought and heat. This work spans two complementary scales:

High-throughput Phenomics - His lab leverages the state-of-the-art LemnaTec phenotyping system at the IGCAST Phytotron Complex to generate high-resolution phenotypic data. The research utilizes advanced imaging technologies—such as RGB, hyperspectral, thermal, and 3D imaging—to quantify plant architecture, physiology, and stress responses. By applying image processing and machine learning, the lab aims to integrate these phenotypic data with physiological and environmental measurements to better understand stress-related traits and predict crop performance under challenging environments.

Field & Regional Remote Sensing - The lab extends its research to field and regional scales using UAV and satellite platforms. By combining remote sensing observations with ground-based field measurements (e.g., water use, crop type, and yield), the research aims to quantify how environmental conditions influence crop productivity. These scalable approaches provide valuable insights for agricultural monitoring, with a particular emphasis on water-limited agricultural systems in West Texas.