MT-CYP-Net: Multi-Task Network for Pixel-Level Crop Yield Prediction Under Very Few Samples
This addresses the challenge of fine-grained yield estimation for agriculture using satellite data, but it is incremental as it builds on existing multi-task and deep learning approaches.
The paper tackled the problem of pixel-level crop yield prediction with scarce ground truth data by proposing MT-CYP-Net, a multi-task network that uses feature-sharing between yield prediction and crop classification decoders, achieving superior results compared to benchmark methods on a dataset of 1,859 yield points from eight farms in China.
Accurate and fine-grained crop yield prediction plays a crucial role in advancing global agriculture. However, the accuracy of pixel-level yield estimation based on satellite remote sensing data has been constrained by the scarcity of ground truth data. To address this challenge, we propose a novel approach called the Multi-Task Crop Yield Prediction Network (MT-CYP-Net). This framework introduces an effective multi-task feature-sharing strategy, where features extracted from a shared backbone network are simultaneously utilized by both crop yield prediction decoders and crop classification decoders with the ability to fuse information between them. This design allows MT-CYP-Net to be trained with extremely sparse crop yield point labels and crop type labels, while still generating detailed pixel-level crop yield maps. Concretely, we collected 1,859 yield point labels along with corresponding crop type labels and satellite images from eight farms in Heilongjiang Province, China, in 2023, covering soybean, maize, and rice crops, and constructed a sparse crop yield label dataset. MT-CYP-Net is compared with three classical machine learning and deep learning benchmark methods in this dataset. Experimental results not only indicate the superiority of MT-CYP-Net compared to previous methods on multiple types of crops but also demonstrate the potential of deep networks on precise pixel-level crop yield prediction, especially with limited data labels.