Comparison of Machine-Learning and CASA Models for Predicting Apple Fruit Yields from Time-Series Planet Imageries

Apple (Malus domestica Borkh. cv. "Fuji"), an important cash crop, is widely consumed around the world. Accurately predicting preharvest apple fruit yields is critical for planting policy making and agricultural management. This study attempted to explore an effective approach for predicting apple fruit yields based on time-series remote sensing data. In this study, time-series vegetation indices (VIs) were derived from Planet images and analyzed to further construct an accumulated VI (Sigma VIs)-based random forest (RF Sigma VI) model and a Carnegie-Ames-Stanford approach (CASA) model for predicting apple fruit yields. The results showed that (1) Sigma NDVI was the optimal predictor to construct an RF model for apple fruit yield, and the R-2, RMSE, and RPD values of the RF Sigma NDVI model reached 0.71, 16.40 kg/tree, and 1.83, respectively. (2) The maximum light use efficiency was determined to be 0.499 g C/MJ, and the CASA(SR) model (R-2 = 0.57, RMSE = 19.61 kg/tree, and RPD = 1.53) performed better than the CASA(NDVI) model and the CASA(Average) model (R-2, RMSE, and RPD = 0.56, 24.47 kg/tree, 1.22 and 0.57, 20.82 kg/tree, 1.44, respectively). (3) This study compared the yield prediction accuracies obtained by the models using the same dataset, and the RF Sigma NDVI model (RPD = 1.83) showed a better performance in predicting apple fruit yields than the CASA(SR) model (RPD = 1.53). The results obtained from this study indicated the potential of the RF Sigma NDVI model based on time-series Planet images to accurately predict apple fruit yields. The models could provide spatial and quantitative information of apple fruit yield, which would be valuable for agronomists to predict regional apple production to inform and develop national planting policies, agricultural management, and export strategies.