ChinaSoyArea10m: a dataset of soybean planting areas with a spatial resolution of 10 m across China from 2017 to 2021

Abstract

Abstract. Soybean, an essential food crop, has witnessed a steady rise in demand in recent years. There is a lack of high-resolution annual maps depicting soybean planting areas in China, despite China being the world’s largest consumer and fourth largest producer of soybeans. To address this gap, we developed a novel method called phenological- and pixel-based soybean area mapping (PPS) based on Sentinel-2 remote sensing images from the Google Earth Engine (GEE) platform. We utilized various auxiliary data (e.g., cropland layer, detailed phenology observations) to select the distinct features that differentiate soybeans most effectively from other crops across various regions. These features were then input for an unsupervised classifier (K-means), and the most likely type was determined by a post-classification method based on dynamic time warping (DTW). For the first time, we generated a dataset of soybean planting areas across China, with a high spatial resolution of 10 meters, spanning from 2017 to 2021 (ChinaSoyArea10m). The R2 values between the mapping results and the census data at both county- and prefecture-level were consistently around 0.85 in 2017–2020. Moreover, the overall accuracy of mapping results at the field level in 2017, 2018, and 2019 were 77 %, 84 % and 88 %, respectively. Compared with the existing 10-m crop-type maps in Northeast China (Cropland Data Layer, CDL) based on field samples and supervised classification methods, the mapping accuracy is significantly improved by 31 % (R2 increases from 0.53 to 0.84) according to their consistency with census data, particularly at the county level. ChinaSoyArea10m is spatially consistent well with the two existing datasets (CDL and GLAD maize-soybean map). ChinaSoyArea10m provides important information for sustainable soybean production and management, as well as agricultural system modeling and optimization. ChinaSoyArea10m can be downloaded from an open-data repository (DOI: https://zenodo.org/doi/10.5281/zenodo.10071426, Mei et al., 2023).