Grain yield prediction of rice using multi-temporal UAV-based RGB and multispectral images and model transfer - a case study of small farmlands in the South of China

lNDYI could be proxy for leaf chlorophyll content to monitor rice growth.lFusion of multi-temporal UAV image data achieved the best prediction of grain yield.lThe initial heading stage was the optimal growth stage for grain yield prediction.lModel transfer between two years improved the accuracy of grain yield prediction.