Assessing maize silage yield and quality using UAV-based hyperspectral imagery and machine learning

PI: Zhou Zhang


Zhang is an assistant professor of biological systems engineering at UW–Madison. Her research interests include multi-source remote sensing data fusion (e.g. hyperspectral, LiDAR, RGB), machine learning for high dimensional data analysis, UAV-based imaging platform developments for precision agriculture, crop yield prediction using remote sensing and machine learning, and high-throughput image-based plant phenotyping.

Graduate student: Jiahao Fan (pictured above) received both his bachelor’s and master’s degrees in geographic information systems from Wuhan University in China. He was a PhD student in the Department of Informatics at the New Jersey Institute of Technology for two years. Fan is now pursuing a PhD in biological systems engineering, mentored by Zhou Zhang from the Department of Biological Systems Engineering.

Fan is working alongside Zhang to explore genetic and management technologies and innovations that enhance dairy forage production and nutritional value. The overarching goal is to help maintain and stabilize profitability while reducing the carbon footprint of high-quality dairy forages. Using corn silage as a model crop, the research team conducts in-field assessments of forage yield and quality by combining cutting-edge hyperspectral imaging and artificial intelligence technologies. This technique is non-destructive and non-invasive. The developed phenotyping methods can be adapted to access the quality traits of other forage crops beyond corn and could lead to a change in how forage yield and composition is accessed. This change could help speed up crop breeding. Additionally, there is also potential to improve timing in forage harvesting to optimize quality and production.

Publication in Remote Sensing – June 2022

Natalia de Leon