Surrogate models of radiative transfer codes for atmospheric trace gas retrievals from satellite observations
-
Published:2022-03-22
Issue:4
Volume:112
Page:1337-1363
-
ISSN:0885-6125
-
Container-title:Machine Learning
-
language:en
-
Short-container-title:Mach Learn
Author:
Brence JureORCID, Tanevski JovanORCID, Adams JenniferORCID, Malina EdwardORCID, Džeroski SašoORCID
Abstract
AbstractInversion 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%.
Funder
Javna Agencija za Raziskovalno Dejavnost RS European Commission
Publisher
Springer Science and Business Media LLC
Subject
Artificial Intelligence,Software
Reference47 articles.
1. Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., Kudlur, M. (2016). Tensorflow: A system for large-scale machine learning. In 12th {USENIX} Symposium on Operating Systems Design and Implementation {OSDI} (pp. 265–283). 2. Bovensmann, H., Burrows, J. P., Buchwitz, M., Frerick, J., Noël, S., Rozanov, V. V., Chance, K. V., & Goede, A. P. H. (1999). SCIAMACHY: Mission objectives and measurement modes. Journal of the Atmospheric Sciences, 56(2), 127–150. 3. Brence, J., Tanevski, J., Adams, J., Malina, E., Džeroski, S. (2020). Learning surrogates of a radiative transfer model for the sentinel 5p satellite. In International Conference on Discovery Science. Springer (pp. 217–230). 4. Brodrick, P. G., Thompson, D. R., Fahlen, J. E., Eastwood, M. L., Sarture, C. M., Lundeen, S. R., Olson-Duvall, W., Carmon, N., & Green, R. O. (2021). Generalized radiative transfer emulation for imaging spectroscopy reflectance retrievals. Remote Sensing of Environment. https://doi.org/10.1016/j.rse.2021.112476 5. Butz, A., Galli, A., Hasekamp, O., Landgraf, J., Tol, P., & Aben, I. (2012). TROPOMI aboard Sentinel-5 Precursor: Prospective performance of CH4 retrievals for aerosol and cirrus loaded atmospheres. Remote Sensing of Environment, 120, 267–276. https://doi.org/10.1016/j.rse.2011.05.030
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|