Gaussian Process and Deep Learning Atmospheric Correction
Atmospheric correction is the processes of converting radiance values measured at a spectral sensor to the reflectance values of the materials in a multispectral or hyperspectral image. This is an important step for detecting or identifying the materials present in the pixel spectra. We present two...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/3/649 |
| _version_ | 1797623324175499264 |
|---|---|
| author | Bill Basener Abigail Basener |
| author_facet | Bill Basener Abigail Basener |
| author_sort | Bill Basener |
| collection | DOAJ |
| description | Atmospheric correction is the processes of converting radiance values measured at a spectral sensor to the reflectance values of the materials in a multispectral or hyperspectral image. This is an important step for detecting or identifying the materials present in the pixel spectra. We present two machine learning models for atmospheric correction trained and tested on 100,000 batches of 40 reflectance spectra converted to radiance using MODTRAN, so the machine learning model learns the radiative transfer physics from MODTRAN. We created a theoretically interpretable Bayesian Gaussian process model and a deep learning autoencoder treating the atmosphere as noise. We compare both methods for estimating gain in the correction model to process for estimating gain within the well-know QUAC method which assumes a constant mean endmember reflectance. Prediction of reflectance using the Gaussian process model outperforms the other methods in terms of both accuracy and reliability. |
| first_indexed | 2024-03-11T09:27:09Z |
| format | Article |
| id | doaj.art-533a8df7748c45a089be7656d1722029 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T09:27:09Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-533a8df7748c45a089be7656d17220292023-11-16T17:52:15ZengMDPI AGRemote Sensing2072-42922023-01-0115364910.3390/rs15030649Gaussian Process and Deep Learning Atmospheric CorrectionBill Basener0Abigail Basener1Department of Systems and Information Engineering, School of Data Science, University of Virginia, Charlottesville, VA 22904, USAApplied Math, Virginia Military Institute, Lexington, VA 24450, USAAtmospheric correction is the processes of converting radiance values measured at a spectral sensor to the reflectance values of the materials in a multispectral or hyperspectral image. This is an important step for detecting or identifying the materials present in the pixel spectra. We present two machine learning models for atmospheric correction trained and tested on 100,000 batches of 40 reflectance spectra converted to radiance using MODTRAN, so the machine learning model learns the radiative transfer physics from MODTRAN. We created a theoretically interpretable Bayesian Gaussian process model and a deep learning autoencoder treating the atmosphere as noise. We compare both methods for estimating gain in the correction model to process for estimating gain within the well-know QUAC method which assumes a constant mean endmember reflectance. Prediction of reflectance using the Gaussian process model outperforms the other methods in terms of both accuracy and reliability.https://www.mdpi.com/2072-4292/15/3/649atmospheric compensationGaussian processhyperspectral |
| spellingShingle | Bill Basener Abigail Basener Gaussian Process and Deep Learning Atmospheric Correction Remote Sensing atmospheric compensation Gaussian process hyperspectral |
| title | Gaussian Process and Deep Learning Atmospheric Correction |
| title_full | Gaussian Process and Deep Learning Atmospheric Correction |
| title_fullStr | Gaussian Process and Deep Learning Atmospheric Correction |
| title_full_unstemmed | Gaussian Process and Deep Learning Atmospheric Correction |
| title_short | Gaussian Process and Deep Learning Atmospheric Correction |
| title_sort | gaussian process and deep learning atmospheric correction |
| topic | atmospheric compensation Gaussian process hyperspectral |
| url | https://www.mdpi.com/2072-4292/15/3/649 |
| work_keys_str_mv | AT billbasener gaussianprocessanddeeplearningatmosphericcorrection AT abigailbasener gaussianprocessanddeeplearningatmosphericcorrection |