A feasibility study to use machine learning as an inversion algorithm for aerosol profile and property retrieval from multi-axis differential absorption spectroscopy measurements

Abstract

Abstract. In this study, we explore a new approach based on machine learning (ML) for deriving aerosol extinction coefficient profiles, single-scattering albedo and asymmetry parameter at 360 nm from a single multi-axis differential optical absorption spectroscopy (MAX-DOAS) sky scan. Our method relies on a multi-output sequence-to-sequence model combining convolutional neural networks (CNNs) for feature extraction and long short-term memory networks (LSTMs) for profile prediction. The model was trained and evaluated using data simulated by Vector Linearized Discrete Ordinate Radiative Transfer (VLIDORT) v2.7, which contains 1 459 200 unique mappings. From the simulations, 75 % were randomly selected for training and the remaining 25 % for validation. The overall error of estimated aerosol properties (1) for total aerosol optical depth (AOD) is -1.4±10.1 %, (2) for the single-scattering albedo is 0.1±3.6 %, and (3) for the asymmetry factor is -0.1±2.1 %. The resulting model is capable of retrieving aerosol extinction coefficient profiles with degrading accuracy as a function of height. The uncertainty due to the randomness in ML training is also discussed.

Stacking Machine Learning Models Empowered High Time-Height-Resolved Ozone Profiling from the Ground to the Stratopause Based on MAX-DOAS Observation

“…addressed this limitation by employing a parametrized lookup table, resulting in more resilient and consistent retrievals of aerosol profiles. The ML model is also capable of retrieving aerosol profiles with high efficiency and accuracy . Utilizing a multiband analysis approach in the ultraviolet (UV) spectra can further improve the retrieval accuracy and the resolution of O 3 within 10–60 km.…”

“…The ML model is also capable of retrieving aerosol profiles with high efficiency and accuracy. 47 Utilizing a multiband analysis approach in the ultraviolet (UV) spectra can further improve the retrieval accuracy and the resolution of O 3 within 10−60 km. Nonetheless, addressing the challenge of weaker light intensity closer to the UV band necessitates the exploration of UV spectra amplification methods to be developed in forthcoming research endeavors.…”