Generative Artificial Intelligence for Hyperspectral Sensor Data: A Review
Airborne platforms and satellites provide rich sensor data in the form of hyperspectral images (HSI), which are crucial for numerous vision-related tasks, such as feature extraction, image enhancement, and data synthesis. This article reviews the contextual importance and applications of generative...
Saved in:
| Main Authors: | , , , |
|---|---|
| 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/10870282/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850072165681987584 |
|---|---|
| author | Diaa Addeen Abuhani Imran Zualkernan Raghad Aldamani Mohamed Alshafai |
| author_facet | Diaa Addeen Abuhani Imran Zualkernan Raghad Aldamani Mohamed Alshafai |
| author_sort | Diaa Addeen Abuhani |
| collection | DOAJ |
| description | Airborne platforms and satellites provide rich sensor data in the form of hyperspectral images (HSI), which are crucial for numerous vision-related tasks, such as feature extraction, image enhancement, and data synthesis. This article reviews the contextual importance and applications of generative artificial intelligence (GAI) in the advancement of HSI processing. GAI methods address the inherent challenges of HSI data, such as high dimensionality, noise, and the need to preserve spectral-spatial correlations, rendering them indispensable for modern HSI analysis. Generative neural networks, including generative adversarial networks and denoising diffusion probabilistic models, are highlighted for their superior performance in classification, segmentation, and object identification tasks, often surpassing traditional approaches, such as U-Nets, autoencoders, and deep convolutional neural networks. Diffusion models showed competitive performance in tasks, such as feature extraction and image resolution enhancement, particularly in terms of inference time and computational cost. Transformer architectures combined with attention mechanisms further improved the accuracy of generative methods, particularly for preserving spectral and spatial information in tasks, such as image translation, data augmentation, and data synthesis. Despite these advancements, challenges remain, particularly in developing computationally efficient models for super-resolution and data synthesis. In addition, novel evaluation metrics tailored to the complex nature of HSI data are needed. This review underscores the potential of GAI in addressing these challenges while presenting its current strengths, limitations, and future research directions. |
| format | Article |
| id | doaj-art-73f7afe9ddff4267b0fc8f91452b5ce8 |
| 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-73f7afe9ddff4267b0fc8f91452b5ce82025-08-20T02:47:08ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01186422643910.1109/JSTARS.2025.353875910870282Generative Artificial Intelligence for Hyperspectral Sensor Data: A ReviewDiaa Addeen Abuhani0https://orcid.org/0009-0009-6675-1185Imran Zualkernan1https://orcid.org/0000-0002-1048-5633Raghad Aldamani2https://orcid.org/0009-0007-0748-4158Mohamed Alshafai3https://orcid.org/0009-0005-2388-5205Department of Computer Science and Engineering, American University of Sharjah, Sharjah, UAEDepartment of Computer Science and Engineering, American University of Sharjah, Sharjah, UAEDepartment of Computer Science and Engineering, American University of Sharjah, Sharjah, UAEDepartment of Computer Science and Engineering, American University of Sharjah, Sharjah, UAEAirborne platforms and satellites provide rich sensor data in the form of hyperspectral images (HSI), which are crucial for numerous vision-related tasks, such as feature extraction, image enhancement, and data synthesis. This article reviews the contextual importance and applications of generative artificial intelligence (GAI) in the advancement of HSI processing. GAI methods address the inherent challenges of HSI data, such as high dimensionality, noise, and the need to preserve spectral-spatial correlations, rendering them indispensable for modern HSI analysis. Generative neural networks, including generative adversarial networks and denoising diffusion probabilistic models, are highlighted for their superior performance in classification, segmentation, and object identification tasks, often surpassing traditional approaches, such as U-Nets, autoencoders, and deep convolutional neural networks. Diffusion models showed competitive performance in tasks, such as feature extraction and image resolution enhancement, particularly in terms of inference time and computational cost. Transformer architectures combined with attention mechanisms further improved the accuracy of generative methods, particularly for preserving spectral and spatial information in tasks, such as image translation, data augmentation, and data synthesis. Despite these advancements, challenges remain, particularly in developing computationally efficient models for super-resolution and data synthesis. In addition, novel evaluation metrics tailored to the complex nature of HSI data are needed. This review underscores the potential of GAI in addressing these challenges while presenting its current strengths, limitations, and future research directions.https://ieeexplore.ieee.org/document/10870282/Diffusion modelsgenerative adversarial networks (GANs)generative artificial intelligence (GAI)generative neural networks (GNNs)hyperspectral images |
| spellingShingle | Diaa Addeen Abuhani Imran Zualkernan Raghad Aldamani Mohamed Alshafai Generative Artificial Intelligence for Hyperspectral Sensor Data: A Review IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Diffusion models generative adversarial networks (GANs) generative artificial intelligence (GAI) generative neural networks (GNNs) hyperspectral images |
| title | Generative Artificial Intelligence for Hyperspectral Sensor Data: A Review |
| title_full | Generative Artificial Intelligence for Hyperspectral Sensor Data: A Review |
| title_fullStr | Generative Artificial Intelligence for Hyperspectral Sensor Data: A Review |
| title_full_unstemmed | Generative Artificial Intelligence for Hyperspectral Sensor Data: A Review |
| title_short | Generative Artificial Intelligence for Hyperspectral Sensor Data: A Review |
| title_sort | generative artificial intelligence for hyperspectral sensor data a review |
| topic | Diffusion models generative adversarial networks (GANs) generative artificial intelligence (GAI) generative neural networks (GNNs) hyperspectral images |
| url | https://ieeexplore.ieee.org/document/10870282/ |
| work_keys_str_mv | AT diaaaddeenabuhani generativeartificialintelligenceforhyperspectralsensordataareview AT imranzualkernan generativeartificialintelligenceforhyperspectralsensordataareview AT raghadaldamani generativeartificialintelligenceforhyperspectralsensordataareview AT mohamedalshafai generativeartificialintelligenceforhyperspectralsensordataareview |