Estimating evapotranspiration of pomegranate trees using Stochastic Configuration Networks (SCN) and UAV Multispectral Imagery

Authors: NIU, HAOYU - University Of California; ZHAO, TIEBIAO - University Of California; Wang, Dong; CHEN, YANQUAN - University Of California

Submitted to: Journal of Intelligent and Robotic Systems
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 1/31/2022
Publication Date: 3/30/2022
Citation: Niu, H., Zhao, T., Wang, D., Chen, Y. 2022. Estimating evapotranspiration of pomegranate trees using Stochastic Configuration Networks (SCN) and UAV Multispectral Imagery. Journal of Intelligent and Robotic Systems. 104. Article 66. https://doi.org/10.1007/s10846-022-01588-2.
DOI: https://doi.org/10.1007/s10846-022-01588-2

Interpretive Summary: Traditionally crop evapotranspiration is determined by crop coefficient using field water balance or meteorological measurements, however these measurements are difficult to make and subject to spatial variability. In this research, we developed strong prediction functions between crop coefficient and pomegranate canopy normalized difference vegetation index using both linear and stochastic configuration networks models. The canopy normalized difference vegetation index was measured weekly using a small unmanned aerial vehicle equipped with multi-spectral cameras over two growing seasons. The findings are valuable to farmers for making informed irrigation decisions.

Technical Abstract: Evapotranspiration (ET) estimation is important in precision agriculture water management, such as evaluating soil moisture, drought monitoring, and assessing crop water stress. As a traditional method, evapotranspiration estimation using crop coefficient (Kc) have been commonly used. Since there are strong similarities between the Kc curve and the vegetation index curve. The crop coefficient Kc is usually estimated as a function of the vegetation index. Researchers have developed different linear regression models for the Kc and the normalized difference vegetation index (NDVI), which are usually derived from satellite imagery. However, the spatial resolution of satellite image is often insufficient for crops with clumped canopy structures, such as vines, and trees. Therefore, in this research, the authors used Unmanned Aerial Vehicles (UAVs) to collect high-resolution imagery in an pomegranate orchard located at the USDA-ARS, San Joaquin Valley Agricultural Sciences Center, Parlier, CA. The Kc values were measured from a weighing lysimeter and the NDVI values were derived from UAV imagery. Then, the authors established a relationship between the NDVI and Kc by using a linear regression model and a stochastic configuration networks (SCN) model, respectively. Based on the research results, for the linear regression model, it has an R2 of 0.975, and RMSE of 0.05. The SCN regression model has an R2 and RMSE value of 0.995 and 0.046, respectively. Compared with the linear regression model, the SCN model improved performance in predicting Kc from NDVI.