Forward-inverse modeling based on scalar and vector radiative transfer models for coupled atmosphere-surface systems and machine learning tools

Reliable retrieval of atmospheric and surface properties from sensors deployed on satellite platforms rely on accurate simulations of the electromagnetic (EM) signal measured by such sensors. A forward radiative transfer (RT) model of the coupled atmosphere-surface system can be used to simulate how the EM signal responds to changes in atmospheric and surface properties. Realistic RT modeling is a prerequisite for solving the inverse problem, i.e. to infer atmospheric and surface parameters from the EM signals measured at the top of the atmosphere. The surface may consist of a soil-plant canopy, a snow/ice covered surface or an open water body (ocean, lake, river system). An overview will be provided of forward and inverse RT in such coupled atmosphere-surface systems. A coupled system consisting of two adjacent slabs separated by an interface across which the refractive index changes abruptly from its value in air to that in water /ice [1] will be used as an example. Several examples of how to formulate and solve inverse problems involving coupled atmosphere-water systems [2] will be provided to illustrate how solutions to the RT equation can be used as a forward model to solve practical inverse problems. Cloud screening [3], atmospheric correction [4], treatment of two-dimensional surface roughness, Earth curvature effects, and ocean bottom reflection for shallow water in coastal areas will be discussed, and the advantage of using powerful machine learning techniques to solve the inverse problem will be emphasized.

References

[1] Stamnes, K., and J. J. Stamnes, Radiative Transfer in Coupled Environmental Systems, , 2015.

[2] Stamnes, K., B. Hamre, S. Stamnes, N. Chen, Y. Fan, W. Li, Z. Lin, and J. J. Stamnes, Progress in forward-inverse modeling based on radiative transfer tools for coupled atmosphere-snow/ice-ocean systems: A review and description of the AccuRT model, , 8, 2682, 2018.

[3] Chen N., W. Li, C. Gatebe, T. Tanikawa, M. Hori, R. Shimada; T. Aoki, and K. Stamnes, New cloud mask algorithm based on machine learning methods and radiative transfer simulations, , 219, 62-71, 2018.

[4] Fan, Y., W. Li, C. K. Gatebe, C. Jamet, G. Zibordi, T. Schroeder, and K. Stamnes, Atmospheric correction and aerosol retrieval over coastal waters using multilayer neural networks, , 199, 218-240, 2017.