Ginting Frisa Irawan, Rudiyanto Rudiyanto, Mohd Shah Ramisah, Che Soh Norhidayah, Eng Giap Sunny Goh, Fiantis Dian, Setiawan Budi Indra, Schiller Sam, Davitt Aaron, Minasny Budiman
Program of Crop Science, Faculty of Food Science and Agrotechnology, Universiti Malaysia Terengganu, Kuala Nerus, 21030, Terengganu, Malaysia.
Department of Soil Science and Land Resources, Faculty of Agriculture, Andalas University, Kampus Limau Manis, Padang, 25163, Indonesia.
Sci Data. 2025 Aug 12;12(1):1408. doi: 10.1038/s41597-025-05722-1.
Southeast Asia contributes 20% of the world's rice production and 29% of global rice methane emissions, highlighting the need for accurate data on harvested areas to support food security and greenhouse gas accounting. However, existing paddy rice maps often lack information on cropping intensity, spatial resolution, and accuracy due to diverse cultivation practices. This study presents a 10-m resolution, open-access dataset of rice cropping intensity, enabling the precise estimation of growing and harvested areas across Southeast Asia. The Local Unsupervised Classification with Phenological Labelling (LUCK-PALM) was used to generate the map by combining Sentinel-1A and Sentinel-2A/B data (2020-2021). Validation at the pixel level (n = 58,885) shows an overall accuracy of 0.98, a kappa coefficient of 0.870, and an F1 score of 0.879 in identifying rice areas. This comprehensive dataset is available in a public repository and can be used to enhance food and water security strategies and refines estimates of methane emissions.
东南亚的水稻产量占世界的20%,甲烷排放量占全球水稻甲烷排放的29%,这凸显了获取准确收获面积数据以支持粮食安全和温室气体核算的必要性。然而,由于种植方式多样,现有的水稻田地图往往缺乏关于种植强度、空间分辨率和准确性的信息。本研究展示了一个分辨率为10米的、可公开获取的水稻种植强度数据集,能够精确估算东南亚各地的种植和收获面积。通过结合哨兵-1A和哨兵-2A/B数据(2020 - 2021年),利用带物候标记的局部无监督分类法(LUCK - PALM)生成了该地图。在像素级别(n = 58,885)进行验证时,识别水稻种植区域的总体准确率为0.98,卡帕系数为0.870,F1分数为0.879。这个全面的数据集存于公共存储库中,可用于加强粮食和水资源安全战略,并完善甲烷排放估算。