Surrogate models of radiative transfer codes for atmospheric trace gas retrievals from satellite observations
Open Access
- 22 March 2022
- journal article
- research article
- Published by Springer Nature in Machine Learning
- Vol. 112 (4) , 1337-1363
Abstract
Inversion of radiative transfer models (RTMs) is key to interpreting satellite observations of air quality and greenhouse gases, but is computationally expensive. Surrogate models that emulate the full forward physical RTM can speed up the simulation, reducing computational and timing costs and allowing the use of more advanced physics for trace gas retrievals. In this study, we present the development of surrogate models for two RTMs: the RemoTeC algorithm using the LINTRAN RTM and the SCIATRAN RTM. We estimate the intrinsic dimensionality of the input and output spaces and embed them in lower dimensional subspaces to facilitate the learning task. Two methods are tested for dimensionality reduction, autoencoders and principle component analysis (PCA), with PCA consistently outperforming autoencoders. Different sampling methods are employed for generating the training datasets: sampling focused on expected atmospheric parameters and latin hypercube sampling. The results show that models trained on the smaller (n = 1000) uniformly sampled dataset can perform as well as those trained on the larger (n = 50000), more focused dataset. Surrogate models for both datasets are able to accurately emulate Sentinel 5P spectra within a millisecond or less, as compared to the minutes or hours needed to simulate the full physical model. The SCIATRAN-trained forward surrogate models are able to generalize the emulation to a broader set of parameters and can be used for less constrained applications, while achieving a normalized RMSE of 7.3%. On the other hand, models trained on the LINTRAN dataset can completely replace the RTM simulation in more focused expected ranges of atmospheric parameters, as they achieve a normalized RMSE of 0.3%.Keywords
Funding Information
- The Slovenian Research and Innovation Agency (P2-0103, N2-0128)
- European Commission
- European Commission (825619)
This publication has 36 references indexed in Scilit:
- Efficient Emulation of Radiative Transfer Codes Using Gaussian Processes and Application to Land Surface Parameter InferencesRemote Sensing, 2016
- Replacing radiative transfer models by surrogate approximations through machine learning2015
- Radiative transfer through terrestrial atmosphere and ocean: Software package SCIATRANJournal of Quantitative Spectroscopy and Radiative Transfer, 2014
- Requirements for the GMES Atmosphere Service and ESA's implementation concept: Sentinels-4/-5 and -5pRemote Sensing of Environment, 2012
- TROPOMI on the ESA Sentinel-5 Precursor: A GMES mission for global observations of the atmospheric composition for climate, air quality and ozone layer applicationsRemote Sensing of Environment, 2012
- TROPOMI aboard Sentinel-5 Precursor: Prospective performance of CH4 retrievals for aerosol and cirrus loaded atmospheresRemote Sensing of Environment, 2012
- Extremely randomized treesMachine Learning, 2006
- A linearized vector radiative transfer model for atmospheric trace gas retrievalJournal of Quantitative Spectroscopy and Radiative Transfer, 2002
- Design and Analysis of Computer ExperimentsStatistical Science, 1989
- LIII. On lines and planes of closest fit to systems of points in spaceJournal of Computers in Education, 1901