MT-CYP-Net: Multi-Task Network for Pixel-Level Crop Yield Prediction Under Very Few Samples

TL;DR

This paper introduces MT-CYP-Net, a multi-task deep learning framework that predicts detailed pixel-level crop yields from satellite data using very limited ground truth labels, improving accuracy over traditional methods.

Contribution

The paper presents a novel multi-task network with feature sharing that enables accurate pixel-level crop yield prediction with sparse labels, a significant advancement over existing approaches.

Findings

MT-CYP-Net outperforms classical machine learning and deep learning benchmarks.

The method effectively utilizes sparse crop yield and type labels for detailed mapping.

Deep networks show strong potential for precise yield prediction with limited data.

Abstract

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.