Machine learning-based aerosol characterization using OCO-2 O2 A-band observations

TL;DR

This paper presents a neural network approach to accurately characterize aerosols from OCO-2 satellite data, improving the retrieval of CO2 measurements by accounting for aerosol effects over land surfaces.

Contribution

It generalizes a spectral sorting method and uses a two-step neural network to enhance aerosol parameter retrieval, leading to more accurate CO2 measurements from satellite data.

Findings

Neural network accurately predicts aerosol optical depth and layer height.

Improved aerosol estimates enhance XCO2 retrieval accuracy.

Simulations reveal potential biases in current satellite CO2 data due to aerosols.

Abstract

Aerosol scattering influences the retrieval of the column-averaged dry-air mole fraction of CO2 (XCO2) from the Orbiting Carbon Observatory-2 (OCO-2). This is especially true for surfaces with reflectance close to a critical value where there is very low sensitivity to aerosol loading. A spectral sorting approach was introduced to improve the characterization of aerosols over coastal regions. Here, we generalize this procedure to land surfaces and use a two-step neural network to retrieve aerosol parameters from OCO-2 measurements. We show that, by using a combination of radiance measurements in the continuum and inside the absorption band, both the aerosol optical depth and layer height, as well as their uncertainties, can be accurately predicted. Using the improved aerosol estimates as a priori, we demonstrate that the accuracy of the XCO2 retrieval can be significantly improved compared to the OCO-2 Level-2 Standard product. Furthermore, using simulated observations, we obtain estimates of the error in the retrieved XCO2. These simulations indicate that the bias-corrected OCO-2 Lite data, which is used for flux inversions, may have remaining biases due to misinterpretation of aerosol effects.