Estimates of surface reflectance from observed radiance are fundamentally tied to the accuracy of the radiative transfer models used to simulate the interaction of light with the atmosphere and surface. These radiative transfer models are parameterized by a wide range of quantities, ranging from observation and solar geometries to assumptions about atmospheric conditions, including vertical distributions aerosols and water vapor as well as the atmospheric composition. However, current retrieval approaches cannot represent this variability; they are limited by computational expense to a coarsely-spaced look up table (LUT) of just a few parameters. Here, we propose a new method called sRTMnet that facilitates the efficient creation of dense LUT grids that fully capture radiative transfer's inherent nonlinearity. sRTMnet uses a combination of fast, reduced-order radiative transfer modeling coupled with neural-network-based emulation to realize a computational speedup of over 3000× while maintaining the accuracy of a high-fidelity RTM. We demonstrate the accuracy of sRTMnet in multiple ways. We show that neural-network-based emulation delivers accurate atmospheric properties using robust testing sets. We then use acquisitions from the airborne visible/infrared imaging spectrometer - next generation (AVIRIS-NG) to show near identical surface reflectance estimates with sRTMnet and a high-fidelity radiative transfer model (MODTRAN). Finally, we show how distributions of mapped minerals remain consistent when using the sRTMnet-based reflectance. Given these results, sRTMnet will be utilized for the upcoming Earth Surface Mineral Dust Source Investigation (EMIT, an imaging spectrometer destined for the international space station in 2022). In addition to speed and accuracy, the fully open-source nature of sRTMnet (including simulation and emulation), provides a pathway for high-resolution imaging spectroscopy reflectance retrievals at the global scale.

从观测到的辐射率得出的表面反射率估计值基本上与用于模拟光与大气和地面相互作用的辐射传递模型的准确性有关。这些辐射传递模型的参数设定范围很广，从观测和太阳的几何形状到有关大气条件的假设，包括垂直分布的气溶胶和水蒸气以及大气成分。但是，当前的检索方法不能代表这种可变性。它们受计算费用的限制，只限于几个参数的粗略查找表（LUT）。在这里，我们提出了一种称为sRTMnet的新方法，该方法有助于有效创建密集的LUT网格，从而充分捕获辐射传递固有的非线性。sRTMnet将快速的降阶辐射传递模型与基于神经网络的仿真结合使用，可在保持高保真RTM精度的同时，实现3000倍以上的计算速度。我们以多种方式证明sRTMnet的准确性。我们展示了基于神经网络的仿真使用强大的测试集可提供准确的大气特性。然后，我们使用下一代机载可见/红外成像光谱仪（AVIRIS-NG）进行的采集来显示与sRTMnet和高保真辐射传输模型（MODTRAN）几乎相同的表面反射率估计值。最后，我们展示了使用基于sRTMnet的反射率时映射的矿物分布如何保持一致。鉴于这些结果，sRTMnet将用于即将进行的地球表面矿物粉尘源调查（EMIT，2022年发往国际空间站的成像光谱仪）。除了速度和准确性外，sRTMnet的完全开源性质（包括仿真和仿真）为在全球范围内高分辨率成像光谱反射率的检索提供了途径。