The Visible Infrared Imaging Radiometer Suite (VIIRS) has observed the Earth since 2011 and will continue for several decades. Unfortunately, few high-level land surface products have been produced and publicly released. The numerical inversion of radiative transfer model (RTM) has long been used for the retrieval of land surface and atmospheric variables from satellite data; however, it is computationally intensive. Some methods (e.g., using look-up tables) are efficient but are most suitable for estimating individual variable. Various machine learning (ML) models have been developed, mostly trained by either ground measurements that may not be adequate to represent different conditions, or RTM simulations that may not be realistic due to model uncertainty and unnecessary combinations of illumination-viewing geometries and variable values. In this study, we replaced the numerical inversion scheme by the ML algorithm that is trained using RTM inversion for estimating multiple variables simultaneously. Our training dataset for the ML models was generated by inverting the land and atmospheric variables from VIIRS top-of-atmosphere (TOA) reflectance data using a coupled land-surface–atmosphere RT model. Two multi-output ML algorithms were explored: backpropagation neural networks and random forest (RF) regression. The best-performing RF model was then applied to estimate seven land and atmospheric variables globally from VIIRS TOA data: the leaf area index (LAI), incident photosynthetically active radiation (PAR), fraction of absorbed photosynthetically active radiation (FAPAR), incident shortwave radiation (ISR), land surface albedo, land surface reflectance, and TOA albedo. The inversion results were validated using ground measurements at 54 sites and showed comparable accuracy to the numerical inversion scheme that is suitable for only small regions. An experiment was also conducted to test this method on a much larger region for detailed evaluation. Finally, seven global estimates in 2013 were experimentally produced. Inter-comparison with the existing satellite products showed that the VIIRS estimates had high consistency with the LAI and FAPAR products of the Global LAnd Surface Satellite (GLASS) products suite. Moreover, the VIIRS officially released the VNP43MA3 albedo and VNP09A1 surface reflectance products, the retrieved estimates also matched them well. It was also shown that simultaneous estimation of all seven variables was more accurate and efficient than estimating individual variable sequentially.

可见红外成像辐射计套件 (VIIRS) 自 2011 年以来一直在观测地球，并将持续数十年。不幸的是，很少有高水平的地表产品被生产和公开发布。辐射传输模型（RTM）的数值反演长期以来一直用于从卫星数据中反演地表和大气变量；但是，它是计算密集型的。一些方法（例如，使用查找表）是有效的，但最适合估计单个变量。已经开发了各种机器学习 (ML) 模型，主要是通过可能不足以代表不同条件的地面测量，或者由于模型不确定性和照明观察几何形状和变量值的不必要组合而可能不现实的 RTM 模拟进行训练. 在这项研究中，我们将数值反演方案替换为使用 RTM 反演训练的 ML 算法，以同时估计多个变量。我们的 ML 模型训练数据集是通过使用耦合的地表大气 RT 模型从 VIIRS 大气层顶 (TOA) 反射率数据反演陆地和大气变量而生成的。探索了两种多输出 ML 算法：反向传播神经网络和随机森林 (RF) 回归。然后应用性能最佳的 RF 模型从 VIIRS TOA 数据估计全球七个陆地和大气变量：叶面积指数 (LAI)、入射光合有效辐射 (PAR)、吸收的光合有效辐射分数 (FAPAR)、入射短波辐射 (ISR)、地表反照率、地表反射率和 TOA 反照率。使用 54 个地点的地面测量验证了反演结果，并显示出与仅适用于小区域的数值反演方案相当的精度。还进行了一项实验，以在更大的区域上测试该方法以进行详细评估。最后，通过实验得出了 2013 年的七项全球估计值。与现有卫星产品的比较表明，VIIRS 估计与全球陆地表面卫星 (GLASS) 产品套件的 LAI 和 FAPAR 产品具有高度一致性。此外，VIIRS 正式发布了 VNP43MA3 反照率和 VNP09A1 表面反射率产品，检索到的估计值也与它们很好地匹配。还表明同时估计所有七个变量比顺序估计单个变量更准确和有效。