Abstract
Accurate crop planting area information is of significance for understanding regional food security and agricultural development planning. While increasing numbers of medium resolution satellite imagery and improved classification algorithms have been used for crop mapping, limited efforts have been made in feature selection, despite its vital impacts on crop classification. Furthermore, different crop types have their unique spectral and phenology characteristics; however, the different features of individual crop types have not been well understood and considered in previous studies of crop mapping. Here, we examined an optimized strategy to integrate specific features of individual crop types for mapping an improved crop type layer in the Sanjiang Plain, a new food bowl in China, by using all Sentinel-2 time series images in 2018. First, an automatic spectro-temporal feature selection (ASTFS) method was used to obtain optimal features for individual crops (rice, corn, and soybean), including sorting all features by the global separability indices for each crop and removing redundant features by accuracy changes when adding new features. Second, the ASTFS-based optimized feature sets for individual crops were used to produce three crop probability maps with the Random Forest classifier. Third, the probability maps were then composited into the final crop layer by considering the probability of each crop at every pixel. The resultant crop layer showed an improved accuracy (overall accuracy = 93.94%, Kappa coefficient = 0.92) than the other classifications without such a feature optimizing process. Our results indicate the potential of the ASTFS method for improving regional crop mapping.
Highlights
Information about crop planting area and spatial distribution is of significance for understanding regional crop production and food security [1,2]
This paper proposes an automatic spectro-temporal feature selection (ASTFS) method for improved crop mapping based on Sentinel-2 time series images in 2018 and the Google Earth Engine (GEE) platform
This is because the corn and soybean in the Sanjiang Plain have similar growth processes and spectral characteristics, which greatly increases the difficulty of separating corn and soybean
Summary
Information about crop planting area and spatial distribution is of significance for understanding regional crop production and food security [1,2]. Multi-temporal remote sensing based on a single spectral feature is mainly to analyze the time series profiles of a certain spectral feature, to find the key phenological phases that are easy to extract specific crops from other crops. Foerster et al [18] extracted crop planting pattern information in the northeastern part of Germany by constructing a normalized difference vegetation index (NDVI) time series from TM/ETM+ images and analyzing the spectral mean and standard deviation values of various crops in each critical phenological phase. For areas with more complex planting structure, especially in the presence of crops with similar spectral characteristics, it is difficult to extract various crops with a single spectral feature at the same time [20,21]. Most studies directly input all available time series images in a certain period into the classifier as temporal features. Direct classification using all temporal features increases computation complexity and reduces classification accuracy, so-called the “curse of dimensionality” [22,23]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
