Improved estimation of stomatal conductance by combining high-throughput plant phenotyping data and weather variables through machine learning

Stomatal conductance (gs) quantifies the rate of exchange of carbon dioxide for photosynthesis and water vapor for transpiration between plant leaves and the atmosphere. gs is usually measured by handheld devices like porometers, and readings are manually taken in the field, which is time-consuming and labor-intensive. In this study, we investigated the use of high-throughput phenotyping (HTP) data combined with weather data to estimate gs through machine-learning (ML) modeling. The experiment was conducted in a research field equipped with an HTP platform in 2020 and 2021 involving maize, sorghum, soybean, sunflower, and winter wheat. Weather variables including dew point temperature, wind speed, air temperature, solar radiation, and relative humidity were collected by an onsite weather station. Plot-level canopy temperature, soil temperature, and seven vegetation indices were acquired using a thermal infrared camera, a multispectral camera, and a visible near-infrared spectrometer integrated on the HTP platform. Three supervised ML methods (Partial Least Squares Regression (PLSR), Random Forest Regression (RFR), and Support Vector Regression (SVR)) were employed to train the estimation models for gs, and model performance was evaluated by Coefficient of Determination (R2) and Root Mean Squared Error (RMSE). The result showed that RFR and SVR outperformed PLSR in gs modeling. The RFR model achieved R2 of 0.63 and RMSE of 0.16 mol m−2·s−1 with the combination of phenotyping data and weather data. It outperformed the model using only the weather data (R2=0.35 and RMSE=0.21 mol m−2·s−1), or the model using only the phenotyping data (R2=0.46 and RMSE=0.19 mol m−2·s−1). This result suggested that high-throughput plant phenotyping data effectively complement weather data in estimating gs rapidly and non-destructively through ML. With the wide adoption of HTP technologies in aerial and ground-based platforms, this research provides a practical framework to estimate gs at large scale for crop breeding and irrigation management.