Deep-Learning-Based Approach in Imaging Radiometry by Aperture Synthesis: Application to Real SMOS Data

A novel image reconstruction algorithm for aperture synthesis measurements using deep learning techniques was introduced recently. This algorithm is specifically designed to retrieve brightness temperature (BT) from interferometric data, similar to those collected by the European Space Agency's...

Full description

Saved in:
Bibliographic Details
Main Authors: Ali Khazaal, Richard Faucheron, Nemesio J. Rodriguez-Fernandez, Eric Anterrieu
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10943169/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849739201200783360
author Ali Khazaal
Richard Faucheron
Nemesio J. Rodriguez-Fernandez
Eric Anterrieu
author_facet Ali Khazaal
Richard Faucheron
Nemesio J. Rodriguez-Fernandez
Eric Anterrieu
author_sort Ali Khazaal
collection DOAJ
description A novel image reconstruction algorithm for aperture synthesis measurements using deep learning techniques was introduced recently. This algorithm is specifically designed to retrieve brightness temperature (BT) from interferometric data, similar to those collected by the European Space Agency's (ESA) Soil Moisture and Ocean Salinity (SMOS) mission, launched in 2009. The algorithm employs a deep neural network (DNN) architecture that features a fully connected layer followed by a contracting and expansive path, enabling the network to effectively learn the relationship between simulated visibilities and BT maps. Validation with simulated data has confirmed that this approach aligns perfectly with the theoretical framework of the Van-Cittert Zernike theorem. In this study, a new DNN architecture better suited for real SMOS data is proposed. The new architecture integrates a priori information regarding the water content of each observed pixel. It also includes further enhancements to the previous DNN architecture to better accommodate real SMOS data by incorporating the effects of radiometric noise and the Faraday rotation angle, as well as selecting appropriate global BT maps for training. Finally, validation of the proposed DNN approach using large datasets of real SMOS data is presented and compared to the traditional algebraic approach. Globally, the results demonstrate a significant improvement in image quality, with a reduction in reconstruction error, better handling of residual foreign sources, such as radio frequency interference and direct solar radiation, and a notable reduction in land-sea and sea-ice contamination. Overall, the results suggest that the DNN-based approach provides substantial improvements over traditional methods, making it a promising technique for processing SMOS data.
format Article
id doaj-art-520d8d8556724dbeb5b407478fcc3071
institution DOAJ
issn 1939-1404
2151-1535
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-520d8d8556724dbeb5b407478fcc30712025-08-20T03:06:20ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01189321933210.1109/JSTARS.2025.355529910943169Deep-Learning-Based Approach in Imaging Radiometry by Aperture Synthesis: Application to Real SMOS DataAli Khazaal0https://orcid.org/0000-0003-1854-8595Richard Faucheron1https://orcid.org/0009-0004-8630-153XNemesio J. Rodriguez-Fernandez2https://orcid.org/0000-0003-3796-149XEric Anterrieu3https://orcid.org/0009-0007-2233-9098RDIS Conseils, Toulouse, FranceCentre d'Etudes Spatiales de la Biosphère, Université de Toulouse, CNRS, CNES, INRA, and IRD, Toulouse, FranceCentre d'Etudes Spatiales de la Biosphère, Université de Toulouse, CNRS, CNES, INRA, and IRD, Toulouse, FranceCentre d'Etudes Spatiales de la Biosphère, Université de Toulouse, CNRS, CNES, INRA, and IRD, Toulouse, FranceA novel image reconstruction algorithm for aperture synthesis measurements using deep learning techniques was introduced recently. This algorithm is specifically designed to retrieve brightness temperature (BT) from interferometric data, similar to those collected by the European Space Agency's (ESA) Soil Moisture and Ocean Salinity (SMOS) mission, launched in 2009. The algorithm employs a deep neural network (DNN) architecture that features a fully connected layer followed by a contracting and expansive path, enabling the network to effectively learn the relationship between simulated visibilities and BT maps. Validation with simulated data has confirmed that this approach aligns perfectly with the theoretical framework of the Van-Cittert Zernike theorem. In this study, a new DNN architecture better suited for real SMOS data is proposed. The new architecture integrates a priori information regarding the water content of each observed pixel. It also includes further enhancements to the previous DNN architecture to better accommodate real SMOS data by incorporating the effects of radiometric noise and the Faraday rotation angle, as well as selecting appropriate global BT maps for training. Finally, validation of the proposed DNN approach using large datasets of real SMOS data is presented and compared to the traditional algebraic approach. Globally, the results demonstrate a significant improvement in image quality, with a reduction in reconstruction error, better handling of residual foreign sources, such as radio frequency interference and direct solar radiation, and a notable reduction in land-sea and sea-ice contamination. Overall, the results suggest that the DNN-based approach provides substantial improvements over traditional methods, making it a promising technique for processing SMOS data.https://ieeexplore.ieee.org/document/10943169/Aperture synthesisdeep learning (DL)imaging radiometryinverse problems
spellingShingle Ali Khazaal
Richard Faucheron
Nemesio J. Rodriguez-Fernandez
Eric Anterrieu
Deep-Learning-Based Approach in Imaging Radiometry by Aperture Synthesis: Application to Real SMOS Data
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Aperture synthesis
deep learning (DL)
imaging radiometry
inverse problems
title Deep-Learning-Based Approach in Imaging Radiometry by Aperture Synthesis: Application to Real SMOS Data
title_full Deep-Learning-Based Approach in Imaging Radiometry by Aperture Synthesis: Application to Real SMOS Data
title_fullStr Deep-Learning-Based Approach in Imaging Radiometry by Aperture Synthesis: Application to Real SMOS Data
title_full_unstemmed Deep-Learning-Based Approach in Imaging Radiometry by Aperture Synthesis: Application to Real SMOS Data
title_short Deep-Learning-Based Approach in Imaging Radiometry by Aperture Synthesis: Application to Real SMOS Data
title_sort deep learning based approach in imaging radiometry by aperture synthesis application to real smos data
topic Aperture synthesis
deep learning (DL)
imaging radiometry
inverse problems
url https://ieeexplore.ieee.org/document/10943169/
work_keys_str_mv AT alikhazaal deeplearningbasedapproachinimagingradiometrybyaperturesynthesisapplicationtorealsmosdata
AT richardfaucheron deeplearningbasedapproachinimagingradiometrybyaperturesynthesisapplicationtorealsmosdata
AT nemesiojrodriguezfernandez deeplearningbasedapproachinimagingradiometrybyaperturesynthesisapplicationtorealsmosdata
AT ericanterrieu deeplearningbasedapproachinimagingradiometrybyaperturesynthesisapplicationtorealsmosdata