Article
Version 1
Preserved in Portico This version is not peer-reviewed
Gaussian Process and Deep Learning Atmospheric Correction
Version 1
: Received: 20 October 2022 / Approved: 1 November 2022 / Online: 1 November 2022 (03:47:57 CET)
A peer-reviewed article of this Preprint also exists.
Basener, B.; Basener, A. Gaussian Process and Deep Learning Atmospheric Correction. Remote Sens. 2023, 15, 649. Basener, B.; Basener, A. Gaussian Process and Deep Learning Atmospheric Correction. Remote Sens. 2023, 15, 649.
Abstract
Atmospheric correction is the processes of converting radiance measured at a spectral 1 sensor to the reflectance of the materials in a multispectral or hyperspectral image. This is an 2 important step for detecting or identifying the materials present in the pixel spectra. We present 3 two machine learning models for atmospheric correction trained and tested on 100,000 batches of 40 4 reflectance spectra converted to radiance using MODTRAN, so the machine learning model learns 5 the radiative transfer physics from MODTRAN. We created a theoretically interpretable Bayesian 6 Gaussian process model and a deep learning autoencoder treating the atmosphere as noise. We 7 compare both methods for estimating gain in the correction model to the well-know QUAC method 8 of assuming a constant mean endmember reflectance. Prediction of reflectance using the Gaussian 9 process model outperforms the other methods in terms of both accuracy and reliability.
Keywords
atmospheric compensation; Gaussian process; hyperspectral
Subject
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright: This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Comments (0)
We encourage comments and feedback from a broad range of readers. See criteria for comments and our Diversity statement.
Leave a public commentSend a private comment to the author(s)
* All users must log in before leaving a comment