Biological Systems Engineering, Department of


First Advisor

Yufeng Ge

Date of this Version



Zhang, J. 2023. Estimating crop stomatal conductance through high-throughput plant phenotyping (Master's Thesis). Biological Systems Engineering--Dissertations, Theses, and Student Research. Department of Biological Systems Engineering, University of Nebraska, Lincoln.


A THESIS Presented to the Faculty of The Graduate College at the University of Nebraska In Partial Fulfillment of Requirements For the Degree of Master of Science, Major: Agricultural and Biological Systems Engineering, Under the Supervision of Dr. Yufeng Ge. Lincoln, Nebraska: April 2023

Copyright © 2023 Junxiao Zhang


During photosynthesis and transpiration, crops exchange carbon dioxide and water with the atmosphere through stomata. When a crop experiences water stress, stomata are closed to reducing water loss. However, the closing of stomata also negatively affects the photosynthetic efficiency of the crop and leads to lower yields. Stomatal conductance (gs) quantifies the degree of stomatal opening and closing by using the rate of gas exchange between the crop and the atmosphere, which helps to understand the water status of the crop for better irrigation management. Unfortunately, gs measurement typically requires contact measuring instruments and manual collection in the field, which is time-consuming and labor-intensive. Thus, this study estimates gs in two ways. Firstly, plant phenotypic data and weather information were used to estimate gs for various types of crops. The plant phenotypic data were extracted from images captured by a thermal infrared camera, a multispectral camera, and a visible and near-infrared spectrometer integrated on field phenotyping platform. Weather information was obtained from a field weather station. The random forest regression (RFR) model performed the best with R2 of 0.69 and RMSE of 0.135 mol*m-2 *s-1 , while the model using weather parameters alone had R2 of 0.58 and RMSE of 0.161, and the model using phenotypic data alone had R2 values of 0.59 and RMSE of 0.158 mol*m-2 *s-1 . The results indicated that there was a complementary relationship between plant phenotypic data and weather information in estimating gs. The second aspect of the study was to estimate maize and soybean gs directly from near-infrared, thermal-infrared and RGB (Red Green Blue) images collected by the same platform. The results showed that the convolutional neural network (CNN) model outperformed the other models with an R2 of 0.52. In addition, adding soil moisture as a variable to the model improved its accuracy, which decreased the RMSE from 0.147 to 0.137 mol*m-2 *s-1 . This study highlights the potential of estimating gs from remote sensing and field phenotyping platforms to help growers obtain information about the water status of crops and plan irrigation more efficiently.

Advisor: Yufeng Ge