Abstract Tremendous efforts have been made for obtaining surface soil moisture (SM) at high spatial resolutions from microwave-based products via spatial downscaling. In recent years, machine learning has been one of the most advanced techniques in SM spatial downscaling. The performance of a machine learning technique in SM spatial downscaling varies with the algorithm and the underlying surface; however, despite the importance of machine learning for SM downscaling, there are still only few inter-comparisons, particularly over different surfaces. In this study, the performance of multiple machine learning algorithms in downscaling the ECV (the Essential Climate Variable Program initiated by the European Space Agency) SM dataset was validated over different underlying surfaces. Six machine learning algorithms: artificial neural network (ANN), Bayesian (BAYE), classification and regression trees (CART), K nearest neighbor (KNN), random forest (RF), and support vector machine (SVM), were implemented to establish the spatial downscaling models with reliable continuous in-situ SM observations over four case study areas, including the Okalahoma Mesonet (OKM) in North America, Naqu network (NAN) in the Tibetan Plateau, REMEDHUS (REM) network in northeast Spain, and OZNNET (OZN) in southeast Australia. The land surface temperature (LST), normalized difference vegetation index (NDVI), albedo, digital elevation model (DEM), and geographic coordinates were the explanatory variables, and their contributions to the downscaling models over different surfaces were quantified. The conclusions of the experiments can be summarized as follows: (1) The RF achieved excellent performance with a high correlation coefficient and a low regression error. The BAYE and KNN also demonstrated favorable capabilities for SM downscaling; however, the robustness of their algorithms needed further improvements. Numerous abnormal values were obtained in the scale-down process by the ANN, CART, and SVM methods, suggesting their comparative inadequacy in SM downscaling. (2) Downscaled 1-km resolution SM in REM generally presented a close correlation with the in-situ measurements, and its bias was larger than that in the other three regions. Comparatively, the smallest bias with the second highest correlation was found in the OZN region. It was primarily deduced that regions that located in one single climate zone and had mild topography variation and medium vegetation coverage tended to produce high-accuracy results. (3) The feature importance index (FII) calculated by the RF model revealed that the DEM, daytime LST, and NDVI were dominant during reconstruction, particularly DEM in a study region with a large height difference. The specific FII of each independent variable varied remarkably across the different case study areas, probably owing to the complex hydrothermal as well as physical geography conditions. The results of this study demonstrate that the RF model outperforms the other models considered herein; furthermore, the effect of the FII of the variables over different underlying surfaces was demonstrated.

中文翻译：

---

使用空间降尺度技术生成高分辨率土壤水分：六种机器学习算法的比较

摘要 为了通过空间降尺度从基于微波的产品以高空间分辨率获得表层土壤水分 (SM)，已经做出了巨大的努力。近年来，机器学习已成为 SM 空间降尺度中最先进的技术之一。机器学习技术在 SM 空间降尺度中的性能因算法和底层表面而异；然而，尽管机器学习对于 SM 降尺度很重要，但仍然只有很少的相互比较，尤其是在不同的表面上。在这项研究中，多种机器学习算法在缩减 ECV（由欧洲航天局发起的基本气候变量计划）SM 数据集方面的性能在不同的下垫面得到了验证。六种机器学习算法：人工神经网络（ANN）、实施贝叶斯 (BAYE)、分类和回归树 (CART)、K 最近邻 (KNN)、随机森林 (RF) 和支持向量机 (SVM) 以建立具有可靠连续原位 SM 观测的空间降尺度模型超过四个案例研究区域，包括北美的奥克拉荷马中子网 (OKM)、青藏高原的那曲网络 (NAN)、西班牙东北部的 REMEDHUS (REM) 网络和澳大利亚东南部的 OZNNET (OZN)。地表温度（LST）、归一化植被指数（NDVI）、反照率、数字高程模型（DEM）和地理坐标是解释变量，量化了它们对不同表面降尺度模型的贡献。实验结论可总结如下：(1) RF 实现了优异的性能，具有高相关系数和低回归误差。BAYE 和 KNN 也展示了对 SM 降尺度的有利能力；然而，他们算法的鲁棒性需要进一步改进。通过ANN、CART和SVM方法在缩小过程中获得了许多异常值，表明它们在SM缩小方面相对不足。(2) REM 降尺度 1 km 分辨率 SM 与原位测量值普遍呈现密切相关，其偏差大于其他三个区域。相比之下，在 OZN 区域发现了具有第二高相关性的最小偏差。初步推断，位于单一气候带、地形变异温和、植被覆盖中等的区域往往产生高精度结果。(3)RF模型计算的特征重要指数(FII)显示，DEM、白天LST和NDVI在重建过程中占主导地位，尤其是高差较大的研究区域的DEM。每个独立变量的特定 FII 在不同的案例研究区域中显着不同，可能是由于复杂的热液和自然地理条件。这项研究的结果表明，RF 模型优于此处考虑的其他模型；此外，还证明了变量的 FII 对不同下垫面的影响。(3)RF模型计算的特征重要指数(FII)显示，DEM、白天LST和NDVI在重建过程中占主导地位，尤其是高差较大的研究区域的DEM。每个自变量的特定 FII 在不同的案例研究区域中显着不同，可能是由于复杂的热液和自然地理条件。这项研究的结果表明，RF 模型优于本文考虑的其他模型；此外，还证明了变量的 FII 对不同下垫面的影响。(3)RF模型计算的特征重要指数(FII)显示，DEM、白天LST和NDVI在重建过程中占主导地位，尤其是高差较大的研究区域的DEM。每个自变量的特定 FII 在不同的案例研究区域中显着不同，可能是由于复杂的热液和自然地理条件。这项研究的结果表明，RF 模型优于本文考虑的其他模型；此外，还证明了变量的 FII 对不同下垫面的影响。每个独立变量的特定 FII 在不同的案例研究区域中显着不同，可能是由于复杂的热液和自然地理条件。这项研究的结果表明，RF 模型优于本文考虑的其他模型；此外，还证明了变量的 FII 对不同下垫面的影响。每个自变量的特定 FII 在不同的案例研究区域中显着不同，可能是由于复杂的热液和自然地理条件。这项研究的结果表明，RF 模型优于本文考虑的其他模型；此外，还证明了变量的 FII 对不同下垫面的影响。