CaltechAUTHORS
  A Caltech Library Service

Application of Machine Learning to Hyperspectral Radiative Transfer Simulations

Le, Tianhao and Liu, Chao and Yao, Bin and Natraj, Vijay and Yung, Yuk L. (2020) Application of Machine Learning to Hyperspectral Radiative Transfer Simulations. Journal of Quantitative Spectroscopy and Radiative Transfer, 246 . Art. No. 106928. ISSN 0022-4073. https://resolver.caltech.edu/CaltechAUTHORS:20200304-091512556

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20200304-091512556

Abstract

Hyperspectral observations have become one of the most popular and powerful methods for atmospheric remote sensing, and are widely used for temperature, gas, aerosol, and cloud retrievals. However, accurate forward radiative transfer simulations are computationally expensive since typical line-by-line approaches involve a larger number of monochromatic radiative transfer calculations. This study explores the feasibility of machine learning techniques for fast hyperspectral radiative transfer (HRT) simulations, which essentially performs calculations at a small fraction of hyperspectral wavelengths and extends them across the entire spectral range. A neural network (NN) model is used as an example for the development of the fast HRT, and its results are compared with those from a principal component analysis (PCA) model, which shares a similar principle. We consider hyperspectral radiances from both actual satellite observations and accurate line-by-line simulations. The NN model can alleviate the computational burden by two to three orders of magnitude, and generates radiances with small relative errors (generally less than 0.5% compared to exact calculations); the performance of the NN model is better than that of the PCA model. The model can be further improved by optimizing the training procedure and parameters, the representative wavelengths, and the machine learning technique itself.


Item Type:Article
Related URLs:
URLURL TypeDescription
https://doi.org/10.1016/j.jqsrt.2020.106928DOIArticle
ORCID:
AuthorORCID
Liu, Chao0000-0001-7049-493X
Natraj, Vijay0000-0003-3154-9429
Yung, Yuk L.0000-0002-4263-2562
Additional Information:© 2020 Elsevier Ltd. Received 30 September 2019, Revised 4 January 2020, Accepted 22 February 2020, Available online 28 February 2020.
Group:Astronomy Department
Subject Keywords:Radiative transfer; hyperspectral; machine learning; principal component analysis
Record Number:CaltechAUTHORS:20200304-091512556
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20200304-091512556
Official Citation:Tianhao Le, Chao Liu, Bin Yao, Vijay Natraj, Yuk L. Yung, Application of machine learning to hyperspectral radiative transfer simulations, Journal of Quantitative Spectroscopy and Radiative Transfer, Volume 246, 2020, 106928, ISSN 0022-4073, https://doi.org/10.1016/j.jqsrt.2020.106928. (http://www.sciencedirect.com/science/article/pii/S0022407319307010)
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:101698
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:04 Mar 2020 18:38
Last Modified:09 Mar 2020 13:19

Repository Staff Only: item control page