Hyperspectral Vision Transformers for Greenhouse Gas Estimations from Space

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Avilés, Ruben Gonzalez, Scheibenreif, Linus, Braham, Nassim Ait Ali, Blumenstiel, Benedikt, Brunschwiler, Thomas, Guruprasad, Ranjini, Borth, Damian, Albrecht, Conrad, Fraccaro, Paolo, Lambhate, Devyani, Jakubik, Johannes
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917996294832128
author Avilés, Ruben Gonzalez
Scheibenreif, Linus
Braham, Nassim Ait Ali
Blumenstiel, Benedikt
Brunschwiler, Thomas
Guruprasad, Ranjini
Borth, Damian
Albrecht, Conrad
Fraccaro, Paolo
Lambhate, Devyani
Jakubik, Johannes
author_facet Avilés, Ruben Gonzalez
Scheibenreif, Linus
Braham, Nassim Ait Ali
Blumenstiel, Benedikt
Brunschwiler, Thomas
Guruprasad, Ranjini
Borth, Damian
Albrecht, Conrad
Fraccaro, Paolo
Lambhate, Devyani
Jakubik, Johannes
contents Hyperspectral imaging provides detailed spectral information and holds significant potential for monitoring of greenhouse gases (GHGs). However, its application is constrained by limited spatial coverage and infrequent revisit times. In contrast, multispectral imaging offers broader spatial and temporal coverage but often lacks the spectral detail that can enhance GHG detection. To address these challenges, this study proposes a spectral transformer model that synthesizes hyperspectral data from multispectral inputs. The model is pre-trained via a band-wise masked autoencoder and subsequently fine-tuned on spatio-temporally aligned multispectral-hyperspectral image pairs. The resulting synthetic hyperspectral data retain the spatial and temporal benefits of multispectral imagery and improve GHG prediction accuracy relative to using multispectral data alone. This approach effectively bridges the trade-off between spectral resolution and coverage, highlighting its potential to advance atmospheric monitoring by combining the strengths of hyperspectral and multispectral systems with self-supervised deep learning.
format Preprint
id arxiv_https___arxiv_org_abs_2504_16851
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Hyperspectral Vision Transformers for Greenhouse Gas Estimations from Space
Avilés, Ruben Gonzalez
Scheibenreif, Linus
Braham, Nassim Ait Ali
Blumenstiel, Benedikt
Brunschwiler, Thomas
Guruprasad, Ranjini
Borth, Damian
Albrecht, Conrad
Fraccaro, Paolo
Lambhate, Devyani
Jakubik, Johannes
Computer Vision and Pattern Recognition
Hyperspectral imaging provides detailed spectral information and holds significant potential for monitoring of greenhouse gases (GHGs). However, its application is constrained by limited spatial coverage and infrequent revisit times. In contrast, multispectral imaging offers broader spatial and temporal coverage but often lacks the spectral detail that can enhance GHG detection. To address these challenges, this study proposes a spectral transformer model that synthesizes hyperspectral data from multispectral inputs. The model is pre-trained via a band-wise masked autoencoder and subsequently fine-tuned on spatio-temporally aligned multispectral-hyperspectral image pairs. The resulting synthetic hyperspectral data retain the spatial and temporal benefits of multispectral imagery and improve GHG prediction accuracy relative to using multispectral data alone. This approach effectively bridges the trade-off between spectral resolution and coverage, highlighting its potential to advance atmospheric monitoring by combining the strengths of hyperspectral and multispectral systems with self-supervised deep learning.
title Hyperspectral Vision Transformers for Greenhouse Gas Estimations from Space
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.16851