Mitigating coarse spatial reconstruction to generate missing bands for the HLS dataset

The Harmonized LandSat-Sentinel (HLS) dataset has significantly advanced Earth Observation by integrating data from Landsat and Sentinel satellites. However, challenges persist in achieving spectral band parity between LandSat and Sentinel-derived HLS products. This paper presents an extended invest...

Full description

Saved in:
Bibliographic Details
Main Authors: V. Tsironis, A. Psalta, K. Karantzalos
Format: Article
Language:English
Published: Copernicus Publications 2024-11-01
Series:The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Online Access:https://isprs-archives.copernicus.org/articles/XLVIII-3-2024/553/2024/isprs-archives-XLVIII-3-2024-553-2024.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850197835936432128
author V. Tsironis
A. Psalta
K. Karantzalos
author_facet V. Tsironis
A. Psalta
K. Karantzalos
author_sort V. Tsironis
collection DOAJ
description The Harmonized LandSat-Sentinel (HLS) dataset has significantly advanced Earth Observation by integrating data from Landsat and Sentinel satellites. However, challenges persist in achieving spectral band parity between LandSat and Sentinel-derived HLS products. This paper presents an extended investigation aimed at enhancing spatial reconstruction accuracy to enable spectral band parity within HLS products. Building upon our previous work, which utilized generative neural networks to address partial feature mismatches between S30 and L30 products, we introduce a refined approach that fully integrates a Self-Supervised Learning (SSL)-pretrained encoder into a U-Net architecture. This method aims to access multi-scale features and improve spatial reconstruction accuracy, addressing the limitations in spatial resolution observed in our earlier study. Our methodology incorporates a comprehensive ablation study to assess various SSL-pretrained backbone architectures. Preliminary results demonstrate significant improvements in spatial reconstruction accuracy compared to our previous work. The adapted U-Net architecture, leveraging SSL-pretrained encoders, shows enhanced capability in capturing intricate spatial features within the HLS dataset. Our experiments demonstrate a substantial improvement in spatial resolution and feature reconstruction for L30 products, particularly in bands not natively present in Landsat data, paving the way for more accurate multi-sensor analyses.
format Article
id doaj-art-8fbb7857dab04916be343d4f540efb98
institution OA Journals
issn 1682-1750
2194-9034
language English
publishDate 2024-11-01
publisher Copernicus Publications
record_format Article
series The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
spelling doaj-art-8fbb7857dab04916be343d4f540efb982025-08-20T02:13:02ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342024-11-01XLVIII-3-202455355810.5194/isprs-archives-XLVIII-3-2024-553-2024Mitigating coarse spatial reconstruction to generate missing bands for the HLS datasetV. Tsironis0A. Psalta1K. Karantzalos2NTUA, Remote Sensing Lab, 15772 Zografou Athens, GreeceNTUA, Remote Sensing Lab, 15772 Zografou Athens, GreeceNTUA, Remote Sensing Lab, 15772 Zografou Athens, GreeceThe Harmonized LandSat-Sentinel (HLS) dataset has significantly advanced Earth Observation by integrating data from Landsat and Sentinel satellites. However, challenges persist in achieving spectral band parity between LandSat and Sentinel-derived HLS products. This paper presents an extended investigation aimed at enhancing spatial reconstruction accuracy to enable spectral band parity within HLS products. Building upon our previous work, which utilized generative neural networks to address partial feature mismatches between S30 and L30 products, we introduce a refined approach that fully integrates a Self-Supervised Learning (SSL)-pretrained encoder into a U-Net architecture. This method aims to access multi-scale features and improve spatial reconstruction accuracy, addressing the limitations in spatial resolution observed in our earlier study. Our methodology incorporates a comprehensive ablation study to assess various SSL-pretrained backbone architectures. Preliminary results demonstrate significant improvements in spatial reconstruction accuracy compared to our previous work. The adapted U-Net architecture, leveraging SSL-pretrained encoders, shows enhanced capability in capturing intricate spatial features within the HLS dataset. Our experiments demonstrate a substantial improvement in spatial resolution and feature reconstruction for L30 products, particularly in bands not natively present in Landsat data, paving the way for more accurate multi-sensor analyses.https://isprs-archives.copernicus.org/articles/XLVIII-3-2024/553/2024/isprs-archives-XLVIII-3-2024-553-2024.pdf
spellingShingle V. Tsironis
A. Psalta
K. Karantzalos
Mitigating coarse spatial reconstruction to generate missing bands for the HLS dataset
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
title Mitigating coarse spatial reconstruction to generate missing bands for the HLS dataset
title_full Mitigating coarse spatial reconstruction to generate missing bands for the HLS dataset
title_fullStr Mitigating coarse spatial reconstruction to generate missing bands for the HLS dataset
title_full_unstemmed Mitigating coarse spatial reconstruction to generate missing bands for the HLS dataset
title_short Mitigating coarse spatial reconstruction to generate missing bands for the HLS dataset
title_sort mitigating coarse spatial reconstruction to generate missing bands for the hls dataset
url https://isprs-archives.copernicus.org/articles/XLVIII-3-2024/553/2024/isprs-archives-XLVIII-3-2024-553-2024.pdf
work_keys_str_mv AT vtsironis mitigatingcoarsespatialreconstructiontogeneratemissingbandsforthehlsdataset
AT apsalta mitigatingcoarsespatialreconstructiontogeneratemissingbandsforthehlsdataset
AT kkarantzalos mitigatingcoarsespatialreconstructiontogeneratemissingbandsforthehlsdataset