Data for "A Two-Step Method for Monitoring Annual Paddy Rice Planted Area in Tropical Region by Integrating Rice Identification and Cropping Intensity Estimation"

This dataset accompanies the research article "A Two-Step Method for Monitoring Annual Paddy Rice Planted Area in Tropical Region by Integrating Rice Identification and Cropping Intensity Estimation" , comprising two primary components for Vietnam in 2020: (1) the high-resolution paddy rice spatial distribution data and (2) the paddy rice cropping intensity data.
The paddy rice spatial distribution data was generated through a machine learning workflow where Random Forest classifier was trained using rice/non-rice samples and features extracted from Sentinel-1 SAR and Sentinel-2 MSI images. This classification process was specifically constrained within the Rice Potential Zone (RPZ) to enhance accuracy. Based on the fine spatial distribution of paddy rice, the Sentinel-1 SAR time series images were smoothed by Harmonic Analysis of Time Series (HANTS), and then the quadratic difference method was used to generate the cropping intensity information of rice.
Please refer to the original article for more details on the methodology and implementation. DOI: https://doi.org/10.1109/tgrs.2025.3549296

本数据集配套于研究论文《整合水稻识别与种植强度估算的热带区域年度水稻种植面积监测双步方法》，包含2020年越南的两项核心组成部分：(1) 高分辨率水稻空间分布数据；(2) 水稻种植强度数据。

水稻空间分布数据通过机器学习流程生成：以水稻/非水稻样本与哨兵1号合成孔径雷达（Sentinel-1 SAR）、哨兵2号多光谱成像仪（Sentinel-2 MSI）影像提取的特征，训练随机森林（Random Forest）分类器。该分类过程专门限定在水稻潜在区域（Rice Potential Zone, RPZ）内实施，以提升分类精度。基于精细的水稻空间分布结果，研究团队通过时间序列谐波分析（Harmonic Analysis of Time Series, HANTS）对哨兵1号合成孔径雷达时间序列影像进行平滑处理，随后采用二次差分法生成水稻种植强度信息。

有关方法学与具体实现的更多细节，请参阅原研究论文。DOI：https://doi.org/10.1109/tgrs.2025.3549296