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

Simple item page
dc.contributor.authorDong, Yunen
dc.contributor.authorSpinei, Elenaen
dc.contributor.authorKarpatne, Anujen
dc.contributor.departmentElectrical and Computer Engineeringen
dc.contributor.departmentComputer Scienceen
dc.date.accessioned2021-01-29T15:24:05Zen
dc.date.available2021-01-29T15:24:05Zen
dc.date.issued2020-10-16en
dc.description.abstractIn 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.en
dc.format.mimetypeapplication/pdfen
dc.identifier.doihttps://doi.org/10.5194/amt-13-5537-2020en
dc.identifier.eissn1867-8548en
dc.identifier.issn1867-1381en
dc.identifier.issue10en
dc.identifier.urihttp://hdl.handle.net/10919/102128en
dc.identifier.volume13en
dc.language.isoenen
dc.rightsCreative Commons Attribution 4.0 Internationalen
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/en
dc.titleA feasibility study to use machine learning as an inversion algorithm for aerosol profile and property retrieval from multi-axis differential absorption spectroscopy measurementsen
dc.title.serialAtmospheric Measurement Techniquesen
dc.typeArticle - Refereeden
dc.type.dcmitypeTexten
dc.type.dcmitypeStillImageen

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
amt-13-5537-2020.pdf
Size:
1.72 MB
Format:
Adobe Portable Document Format
Description:
Download

Collections

Scholarly Works, Electrical and Computer Engineering
Scholarly Works, Computer Science