Estimating fall‐harvested alfalfa (Medicago sativa L.) yield using unmanned aerial vehicle–based multispectral and thermal images in southern California

Abstract

This study aims to evaluate the efficacy of simple linear, multiple, and robust regression methods to predict fall‐harvested alfalfa (Medicago sativa L.) yield using unmanned aerial vehicle (UAV)‐acquired multispectral and thermal images. Four alfalfa fields in southern California were selected, and a composite dataset containing 180 ground truth sampling points was formed to build and test the performance of the regression models. The UAV was flown in September 2020, 5–29 days before the ground truth data collection. A total of nine crop indices, canopy temperature, and the difference between canopy temperature and air temperature were used as input predictors. Among the simple linear models, the model with normalized difference vegetation index as input showed a strong performance (coefficient of determination [R2] = 0.76; root mean square error [RMSE] = 170.29 kg ha−1; and mean absolute error [MAE] = 132.18 kg ha−1). A multiple linear regression model with three input predictors showed the highest accuracy with R2 = 0.83, RMSE = 142.99 kg ha−1, and MAE = 109.30 kg ha−1. The top‐performing models accurately estimated mean yield at the field level and differentiated fields with low and high alfalfa productivity. Including canopy temperature‐related inputs did not improve the yield prediction power of the models. The error in the yield prediction increased as the days between UAV flights and field harvest increased. Results here suggested that UAV‐based remote sensing has the potential to estimate fall‐harvested alfalfa yield in southern California.