Remote sensing is an efficient technology for mapping soil organic matter (SOM) of croplands during potential bare soil periods. However, since the effects of agricultural practices on the image spectra are different within a region with interleaved drylands and paddy fields in terms of degree and timing, the common multi-temporal image synthesis method and joint modeling of drylands and paddy fields pose challenges of accurate SOM prediction. Therefore, this study introduced two improvements: (1) separate modeling for drylands and paddy fields, and (2) a new multi-temporal image synthesis method, termed the optimal image synthesis method. The proposed synthesis method ranked images based on the SOM prediction accuracy of each image and then selected the first few images for synthesis to improve the prediction. In the study, we collected 103 surface soil samples from Youyi Farm in the Sanjiang Plain of Northeast China, with 46 from drylands and 57 from paddy fields. Multi-temporal Sentinel 2 images acquired during a potential bare soil period between April and June from 2019 to 2023 were used to build the SOM prediction models. Cross-validation results showed that for single-date images, while the optimal joint model of drylands and paddy fields reached a coefficient of determination (R) of 0.56 and a root mean square error (RMSE) of 0.71 %, the individual statistical accuracy was low for paddy fields, with an R of 0.24 and an RMSE of 0.78 %. In contrast, separate modeling achieved higher accuracy in both drylands (R = 0.65 and RMSE = 0.58 %) and paddy fields (R = 0.43 and RMSE = 0.67 %). The common multi-temporal image synthesis method showed similar results. These imply that joint modeling probably masks the inferior performance in paddy fields, and its prediction accuracy could not be improved when jointly modeled with drylands. Compared to the prediction results from single-date images and the common multi-temporal image synthesis method, the optimal image synthesis method improved the prediction accuracy for both drylands and paddy fields, achieving Rs of 0.74 and 0.52 with RMSEs of 0.50 % and 0.62 %, respectively. Our study proves the necessity and validity of separate modeling for drylands and paddy fields, and demonstrates the potential of the proposed optimal image synthesis method for accurate prediction of SOM.

中文翻译：

---

基于最优图像合成方法的东北三江平原旱地和水田土壤有机质分离预测


遥感是一种绘制潜在裸土时期农田土壤有机质 (SOM) 地图的有效技术。然而，由于旱地和水田交错的区域内农业实践对图像光谱的影响在程度和时间上存在差异，常见的多时相图像合成方法和旱地和水田联合建模对准确的旱地和水田提出了挑战。 SOM 预测。因此，本研究引入了两项改进：（1）对旱地和稻田进行单独建模，以及（2）一种新的多时相图像合成方法，称为最优图像合成方法。所提出的合成方法根据每幅图像的 SOM 预测精度对图像进行排序，然后选择前几幅图像进行合成以提高预测。本研究在东北三江平原友谊农场采集了103个表层土壤样品，其中46个来自旱地，57个来自水田。使用在 2019 年至 2023 年 4 月至 6 月期间潜在裸露土壤期间获取的多时相 Sentinel 2 图像来构建 SOM 预测模型。交叉验证结果表明，对于单数据图像，虽然旱地和水田的最佳联合模型达到了0.56的决定系数（R）和0.71%的均方根误差（RMSE），但个体统计精度为稻田的 R 为 0.24，RMSE 为 0.78%。相比之下，单独建模在旱地（R = 0.65 和 RMSE = 0.58%）和水田（R = 0.43 和 RMSE = 0.67%）中都取得了更高的精度。常见的多时相图像合成方法显示出类似的结果。 这意味着联合建模可能掩盖了水田的较差性能，并且与旱地联合建模时其预测精度无法提高。与单数据图像和常见的多时相图像合成方法的预测结果相比，最优图像合成方法提高了旱地和水田的预测精度，分别实现了 Rs 0.74 和 0.52，RMSE 分别为 0.50% 和 0.62% ， 分别。我们的研究证明了旱地和稻田单独建模的必要性和有效性，并证明了所提出的最佳图像合成方法在准确预测 SOM 方面的潜力。