A spatiotemporal collaborative approach for precise crop planting structure mapping based on multi-source remote-sensing data

Abstract

ABSTRACT In order to ensure food security, it is crucial to collect agricultural information efficiently and accurately. Remote sensing has become increasingly important in obtaining crop distribution information on a large scale. However, current research based on satellite platforms struggles to meet the requirements of high-precision and large-scale crop monitoring simultaneously. To address this challenge, we propose a method for achieving fine-scale crop classification by integrating remote-sensing data from various satellite platforms by constructing temporal-scale crop features within the parcels using Sentinel-2A, Landsat-8, and Gaofen-6. We adopt a feature-matching method to fill in missing values in the time-series feature construction process, to avoid issues with unidentifiable crops. The classification results of the Yellow River basin of the Ningxia region show that our method can achieve a wide range of crop discrimination on a fine scale, with an overall accuracy of 80%. Our proposed method demonstrates the potential of integrating multi-platform remote-sensing data to achieve fine-scale crop classification, which can aid decision-making for farmers, government agencies, and other stakeholders involved in the agricultural sector.