A near real-time deep learning approach for detecting rice phenology based on UAV images

• Published in: Agricultural and forest meteorology Vol. 287; p. 107938
• Main Authors: Yang, Qi, Shi, Liangsheng, Han, Jingye, Yu, Jin, Huang, Kai
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 15.06.2020
• Subjects: China; Convolutional neural network; crop management; cultivation area; Deep learning; forests; harvest date; meteorology; neural networks; Oryza sativa; phenology; rice; Rice phenology detection; Shape model fitting; time series analysis; UAV; unmanned aerial vehicles; vegetation index; China; Deep learning; UAV; Convolutional neural network; Shape model fitting; Rice phenology detection

•Using CNN to detect rice phenology by a mono-temporal imagery of UAV was investigated.•Shape-model-fitting method underperformed with short length of time-series data.•Integrating regional mean thermal time into CNN improve the detection accuracy.•The estimated harvest dates was in close agreement...