Machine Learning to Retrieve Gap-Free Land Surface Temperature from Infrared Atmospheric Sounding Interferometer Observations
Retrieving LST from infrared spectral observations is challenging because it needs separation from emissivity in surface radiation emission, which is feasible only when the state of the surface–atmosphere system is known. Thanks to its high spectral resolution, the Infrared Atmospheric Sounding Inte...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-02-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/4/694 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850081197841973248 |
|---|---|
| author | Fabio Della Rocca Pamela Pasquariello Guido Masiello Carmine Serio Italia De Feis |
| author_facet | Fabio Della Rocca Pamela Pasquariello Guido Masiello Carmine Serio Italia De Feis |
| author_sort | Fabio Della Rocca |
| collection | DOAJ |
| description | Retrieving LST from infrared spectral observations is challenging because it needs separation from emissivity in surface radiation emission, which is feasible only when the state of the surface–atmosphere system is known. Thanks to its high spectral resolution, the Infrared Atmospheric Sounding Interferometer (IASI) instrument onboard Metop polar-orbiting satellites is the only sensor that can simultaneously retrieve LST, the emissivity spectrum, and atmospheric composition. Still, it cannot penetrate thick cloud layers, making observations blind to surface emissions under cloudy conditions, with surface and atmospheric parameters being flagged as voids. The present paper aims to discuss a downscaling–fusion methodology to retrieve LST missing values on a spatial field retrieved from spatially scattered IASI observations to yield level 3, regularly gridded data, using as proxy data LST from the Spinning Enhanced Visible and Infrared Imager (SEVIRI) flying on Meteosat Second Generation (MSG) platform, a geostationary instrument, and from the Advanced Very High-Resolution Radiometer (AVHRR) onboard Metop polar-orbiting satellites. We address this problem by using machine learning techniques, i.e., Gradient Boosting, Random Forest, Gaussian Process Regression, Neural Network, and Stacked Regression. We applied the methodology over the Po Valley region, a very heterogeneous area that allows addressing the trained models’ robustness. Overall, the methods significantly enhanced spatial sampling, keeping errors in terms of Root Mean Square Error (RMSE) and bias (Mean Absolute Error, MAE) very low. Although we demonstrate and assess the results primarily using IASI data, the paper is also intended for applications to the IASI follow-on, that is, IASI Next Generation (IASI-NG), and much more to the Infrared Sounder (IRS), which is planned to fly this year, 2025, on the Meteosat Third Generation platform (MTG). |
| format | Article |
| id | doaj-art-3e80c8d6d80c462a8a7ab8da43d6aaed |
| institution | DOAJ |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-3e80c8d6d80c462a8a7ab8da43d6aaed2025-08-20T02:44:47ZengMDPI AGRemote Sensing2072-42922025-02-0117469410.3390/rs17040694Machine Learning to Retrieve Gap-Free Land Surface Temperature from Infrared Atmospheric Sounding Interferometer ObservationsFabio Della Rocca0Pamela Pasquariello1Guido Masiello2Carmine Serio3Italia De Feis4Dipartimento di Biologia, Università di Napoli Federico II, 80126 Napoli, ItalyDipartimento di Ingegneria, Università della Basilicata, 85100 Potenza, ItalyDipartimento di Ingegneria, Università della Basilicata, 85100 Potenza, ItalyDipartimento di Ingegneria, Università della Basilicata, 85100 Potenza, ItalyIstituto per le Applicazioni del Calcolo “Mauro Picone”, CNR, 80131 Napoli, ItalyRetrieving LST from infrared spectral observations is challenging because it needs separation from emissivity in surface radiation emission, which is feasible only when the state of the surface–atmosphere system is known. Thanks to its high spectral resolution, the Infrared Atmospheric Sounding Interferometer (IASI) instrument onboard Metop polar-orbiting satellites is the only sensor that can simultaneously retrieve LST, the emissivity spectrum, and atmospheric composition. Still, it cannot penetrate thick cloud layers, making observations blind to surface emissions under cloudy conditions, with surface and atmospheric parameters being flagged as voids. The present paper aims to discuss a downscaling–fusion methodology to retrieve LST missing values on a spatial field retrieved from spatially scattered IASI observations to yield level 3, regularly gridded data, using as proxy data LST from the Spinning Enhanced Visible and Infrared Imager (SEVIRI) flying on Meteosat Second Generation (MSG) platform, a geostationary instrument, and from the Advanced Very High-Resolution Radiometer (AVHRR) onboard Metop polar-orbiting satellites. We address this problem by using machine learning techniques, i.e., Gradient Boosting, Random Forest, Gaussian Process Regression, Neural Network, and Stacked Regression. We applied the methodology over the Po Valley region, a very heterogeneous area that allows addressing the trained models’ robustness. Overall, the methods significantly enhanced spatial sampling, keeping errors in terms of Root Mean Square Error (RMSE) and bias (Mean Absolute Error, MAE) very low. Although we demonstrate and assess the results primarily using IASI data, the paper is also intended for applications to the IASI follow-on, that is, IASI Next Generation (IASI-NG), and much more to the Infrared Sounder (IRS), which is planned to fly this year, 2025, on the Meteosat Third Generation platform (MTG).https://www.mdpi.com/2072-4292/17/4/694land surface temperatureradiativetransferIASIdownscalingmachine learning |
| spellingShingle | Fabio Della Rocca Pamela Pasquariello Guido Masiello Carmine Serio Italia De Feis Machine Learning to Retrieve Gap-Free Land Surface Temperature from Infrared Atmospheric Sounding Interferometer Observations Remote Sensing land surface temperature radiative transfer IASI downscaling machine learning |
| title | Machine Learning to Retrieve Gap-Free Land Surface Temperature from Infrared Atmospheric Sounding Interferometer Observations |
| title_full | Machine Learning to Retrieve Gap-Free Land Surface Temperature from Infrared Atmospheric Sounding Interferometer Observations |
| title_fullStr | Machine Learning to Retrieve Gap-Free Land Surface Temperature from Infrared Atmospheric Sounding Interferometer Observations |
| title_full_unstemmed | Machine Learning to Retrieve Gap-Free Land Surface Temperature from Infrared Atmospheric Sounding Interferometer Observations |
| title_short | Machine Learning to Retrieve Gap-Free Land Surface Temperature from Infrared Atmospheric Sounding Interferometer Observations |
| title_sort | machine learning to retrieve gap free land surface temperature from infrared atmospheric sounding interferometer observations |
| topic | land surface temperature radiative transfer IASI downscaling machine learning |
| url | https://www.mdpi.com/2072-4292/17/4/694 |
| work_keys_str_mv | AT fabiodellarocca machinelearningtoretrievegapfreelandsurfacetemperaturefrominfraredatmosphericsoundinginterferometerobservations AT pamelapasquariello machinelearningtoretrievegapfreelandsurfacetemperaturefrominfraredatmosphericsoundinginterferometerobservations AT guidomasiello machinelearningtoretrievegapfreelandsurfacetemperaturefrominfraredatmosphericsoundinginterferometerobservations AT carmineserio machinelearningtoretrievegapfreelandsurfacetemperaturefrominfraredatmosphericsoundinginterferometerobservations AT italiadefeis machinelearningtoretrievegapfreelandsurfacetemperaturefrominfraredatmosphericsoundinginterferometerobservations |