Skip to main content
ARS Home » Pacific West Area » Parlier, California » San Joaquin Valley Agricultural Sciences Center » Water Management Research » Research » Publications at this Location » Publication #372872
Research Project: Develop Water Management Strategies to Sustain Water Productivity and Protect Water Quality in Irrigated Agriculture

Location: Water Management Research

Title: Estimating actual crop evapotranspiration using deep stochastic configuration networks model and UAV-based crop coefficients in a pomegranate orchard

Author
item NIU, HAOYU - University Of California
item Wang, Dong
item CHEN, YANGQUAN - University Of California

Submitted to: Proceedings of SPIE
Publication Type: Proceedings
Publication Acceptance Date: 2/29/2020
Publication Date: 4/21/2020
Citation: Niu, H., Wang, D., Chen, Y. 2020. Estimating actual crop evapotranspiration using deep stochastic configuration networks model and UAV-based crop coefficients in a pomegranate orchard. Proceedings of SPIE. V, 114140C. https://doi.org/10.1117/12.2558221.
DOI: https://doi.org/10.1117/12.2558221

Interpretive Summary:

Technical Abstract: Crop coefficient (Kc) methods have been commonly used for evapotranspiration estimation. Researchers estimate Kc as a function of the vegetation index because of similarities between the Kc curve and the vegetation index curve. A linear regression model is usually developed between the Kc and the normalized difference vegetation index (NDVI) derived from satellite imagery. However, the spatial resolution of satellite imagery is in the range of meters or larger, which is often not enough for crops with clumped canopy structures, such as trees and vines. In this study, the Unmanned Aerial Vehicles (UAVs) were used to collect high-resolution images in an experimental pomegranate orchard located at the USDA-ARS San Joaquin Valley Agricultural Sciences Center, Parlier, California. The NDVI values were derived from UAV images. The Kc values were measured from a weighing lysimeter in the pomegranate field. The relationship between the NDVI and Kc was established using both a linear regression model and a deep stochastic configuration networks (DeepSCNs) model. Results show that the linear regression model has an R2 and RMSE value of 0.975 and 0.05, respectively. The DeepSCNs regression model has an R2 and RMSE value of 1 and 0.046, respectively. The DeepSCNs model showed improved performance than the linear regression model in predicting Kc from NDVI.