Classification of Medicinal Plants Astragalus Mongholicus Bunge and Sophora Flavescens Aiton Using GaoFen-6 and Multitemporal Sentinel-2 Data

Abstract

Accurate information regarding cultivated areas of medicinal plants is useful for taking macro-level decisions for medicinal plant management and contingency plans. In this study, the capabilities and limitations of mapping Astragalus mongholicus Bunge and Sophora flavescens Aiton using GaoFen-6 and multitemporal Sentinel-2 data were assessed through a case study in Naiman Banner, Inner Mongolia, China. First, an object-based approach was used to produce a cropland mask based on the GaoFen-6 images. Then, different spectral indices were generated from multitemporal Sentinel-2 imagery acquired in 2019, and a temporal phonological pattern analysis was conducted. Subsequently, optimal feature selection was carried out for each of the crops (Astragalus mongholicus Bunge, Sophora flavescens Aiton and Zea mays L.). The selection was performed by sorting all features according to their global separability index and removing those whose contribution to the model accuracy was negligible. Finally, the medicinal crops were distinguished using the random forest classification algorithm. An overall accuracy and a kappa coefficient of 94.51% and 0.90 were achieved, respectively, demonstrating that the synergistic use of time series GaoFen-6 and Sentinel-2 data were more suitable for Astragalus mongholicus Bunge and Sophora flavescens Aiton mapping.