Wheat Yield Prediction Using Unmanned Aerial Vehicle RGB-Imagery-Based Convolutional Neural Network and Limited Training Samples

• Published in: Remote sensing (Basel, Switzerland) Vol. 15; no. 23; p. 5444
• Main Authors: Ma, Juncheng, Wu, Yongfeng, Liu, Binhui, Zhang, Wenying, Wang, Bianyin, Chen, Zhaoyang, Wang, Guangcai, Guo, Anqiang
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.12.2023
• Subjects: Adaptability; Agricultural production; Artificial neural networks; Cameras; canopy height; convolutional neural network; Crop management; Crop yield; Crop yields; Deep learning; Drone aircraft; Environmental aspects; Experiments; Feature selection; filling period; Grain; Growth; Image processing; Imagery; Irrigation; Machine learning; Methods; Neural networks; Performance prediction; Precipitation; Predictions; split-merge; Training; Triticum aestivum; UAV RGB imagery; Unmanned aerial vehicles; Water treatment; Wheat; Winter; Winter wheat; yield forecasting; yield prediction; China
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs15235444

Low-cost UAV RGB imagery combined with deep learning models has demonstrated the potential for the development of a feasible tool for field-scale yield prediction. However, collecting sufficient labeled training samples at the field scale remains a considerable challenge, significantly limiting the...