Crop Yield Prediction Based on Agrometeorological Indexes and Remote Sensing Data

Timely and reliable estimations of crop yield are essential for crop management and successful food trade. In previous studies, remote sensing data or climate data are often used alone in statistical yield estimation models. In this study, we synthetically used agrometeorological indicators and remote sensing vegetation parameters to estimate maize yield in Jilin and Liaoning Provinces of China. We applied two methods to select input variables, used the random forest method to establish yield estimation models, and verified the accuracy of the models in three disaster years (1997, 2000, and 2001). The results show that the R2 values of the eight yield estimation models established in the two provinces were all above 0.7, Lin’s concordance correlation coefficients were all above 0.84, and the mean absolute relative errors were all below 0.14. The mean absolute relative error of the yield estimations in the three disaster years was 0.12 in Jilin Province and 0.13 in Liaoning Province. A model built using variables selected by a two-stage importance evaluation method can obtain a better accuracy with fewer variables. The final yield estimation model of Jilin province adopts eight independent variables, and the final yield estimation model of Liaoning Province adopts nine independent variables. Among the 11 adopted variables in two provinces, ATT (accumulated temperature above 10 °C) variables accounted for the highest proportion (54.54%). In addition, the GPP (gross primary production) anomaly in August, NDVI (Normalized Difference Vegetation Index) anomaly in August, and standardized precipitation index with a two-month scale in July were selected as important modeling variables by all methods in the two provinces. This study provides a reference method for the selection of modeling variables, and the results are helpful for understanding the impact of climate on potential yield.