| 30 Jun 2025
CN_Wheat10: A 10 m resolution dataset of spring and winter wheat distribution in China (2018–2024) derived from time-series remote sensing
Abstract. Wheat, as one of the main food crops in the world, plays a vital role in shaping agricultural trade patterns. China is the largest producer and consumer of wheat globally, characterized by extensive cultivation areas and diverse planting systems. However, current remote sensing-based wheat mapping studies often rely on uniform phenological feature variables, without adequately accounting for the significant differences in wheat growth cycles across China’s diverse agro-ecological zones. In addition, the lack of large-scale training samples severely limits both the accuracy and the spatial-temporal generalization capacity. Furthermore, existing research in China has primarily focused on the monitoring and mapping of winter wheat, while spring wheat remains largely understudied—particularly in major spring wheat-producing regions in northern China—leading to limited availability of targeted remote sensing products. These limitations hinder the development of high-accuracy, spatially comprehensive wheat mapping datasets and reduce the completeness of agricultural monitoring and food security assessments. To address these issues, this study proposes a cross-regional training sample generation method that integrates time-series remote sensing data with crop distribution products. Furthermore, a province-level, differentiated feature selection strategy is introduced to enhance the regional adaptability and classification performance of the model. Based on these methods, we developed 10 m resolution wheat distribution dataset (CN_Wheat10) covering the years 2018–2024. The dataset includes spring and winter wheat harvested area maps for 15 provinces and detailed winter wheat planted area maps for 10 provinces across China. Validation using a large-scale reference dataset built from field surveys and high-resolution imagery visual interpretation indicates that CN_Wheat10 achieves mapping accuracies above 0.93 for winter wheat and above 0.91 for spring wheat. When compared with wheat area statistics from the China Statistical Yearbook, the coefficient of determination (R2) exceeds 0.94 at the provincial level and remains above 0.88 at the municipal level. Spatially, wheat cultivation in China is characterized by a pattern of concentration in the east, dispersion in the west, a dominance of winter wheat, and a supplementary role of spring wheat. CN_Wheat10 provides spatial distribution information on both spring and winter wheat harvested areas and winter wheat planted regions in key production areas. Compared with existing products that mainly focus on winter wheat, this dataset expands both the spatial coverage and the crop types, offering more comprehensive data support for agricultural monitoring and management in China. The CN_Wheat10 product is freely accessible at https://doi.org/10.6084/m9.figshare.28852220.v2 (Liu et al., 2025).
Line 174-175: “A spatially stratified sampling strategy based on quadrilateral grids was adopted to mitigate the effects of spatial autocorrelation.” Could the authors specify the spataially stratified sampling strategy?
Line 177: “more than 50,000 valid sample points were collected annually” How much of the sample points are from the field survey? Also, how did the authors distringuish winter wheat fields from other crop types based on visual inspection? Some examples can be provided.
Line 234-235: “all non-wheat pixels (Section 3.1) were classified into two types: non-wheat winter crops vs. non-winter crops and non-wheat spring crops vs. non-spring crops, according to their respective growth stages”: I think there are four types?
Line 238: What is the definition of the “spectral separability indices (SI)”?
Section 3.2: what would the accuracy be if you do not do the Selection of provincial feature set?
Line 256: It is not clear why (Yang et al. 2023) is cited here.
Line 264-269: it is not clear to me why does the model can map planeted winter wheat and harvested winter wheat by changing the time window of the feature set.
Line 269: “The final products include harvested area maps of spring and winter wheat for 15 provinces, as well as planted area maps of winter wheat for 10 provinces.” What cause the difference number of available provinces for harvested area maps and planted area maps of winter wheat?