Preprints
https://doi.org/10.5194/essd-2025-326
https://doi.org/10.5194/essd-2025-326
30 Jun 2025
 | 30 Jun 2025
Status: this preprint is currently under review for the journal ESSD.

CN_Wheat10: A 10 m resolution dataset of spring and winter wheat distribution in China (2018–2024) derived from time-series remote sensing

Man Liu, Wei He, and Hongyan Zhang

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).

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.
Share
Man Liu, Wei He, and Hongyan Zhang

Status: open (until 06 Aug 2025)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
Man Liu, Wei He, and Hongyan Zhang

Data sets

CN_Wheat10 Man Liu, Wei He, Hongyan Zhang https://doi.org/10.6084/m9.figshare.28852220.v2

Man Liu, Wei He, and Hongyan Zhang
Metrics will be available soon.
Latest update: 30 Jun 2025
Download
Short summary
This study provides a 10-meter resolution wheat distribution dataset that maps both spring and winter wheat across 15 provinces in China from 2018 to 2024. It was developed using large-scale wheat sample generation combined with region-specific feature selection strategies. The dataset demonstrates high accuracy (overall accuracy > 0.91) and offers detailed spatial information to support agricultural monitoring and food security efforts in China.
Share
Altmetrics