Deep Learning in Hyperspectral Unmixing: A Review
The DOI matches its Crossref record; 22 of the 23 references it cites were found in a registry or an index.
Abstract
In remote sensing, hyperspectral unmixing is very challenging inverse ill-posed problem which does not have closed-form solution. Since more than three decades, several researchers and practitioners have proposed remarkable algorithmic approaches for estimating endmembers and abundances from the data. Typically they construct a forward model (function) and then invert it for the unknowns. Meanwhile a few researchers have reported the use of artificial neural networks for unmixing. With the growth in computer technology, recently the researchers have started exploring deep learning to handle this critical issue. In deep neural networks, the underlying function is learned either by supervised training or by learning the hidden structures from the data. In this paper (within space constraint), we review the learning-based approaches and provide deep learning perspective to the spectral unmixing. We discuss spectral unmixing using three deep learning architectures, viz., autoencoders, convolutional neural network, and generative model. Further, we highlight unattended research problems in the unmixing and brief about possible use of deep learning. Finally, we attempt to discuss some of the practical challenges to be addressed and possible opportunities.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Deep Learning in Remote Sensing: A Comprehensive Review and List of Resources
Zhu, X. X., Tuia, D., Mou, L., Xia, G.-S., Zhang, L., Xu, F., & Fraundorfer, F. (2017) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2017.2762307 · Cited by 3,400
Hyperspectral Unmixing Overview: Geometrical, Statistical, and Sparse Regression-Based Approaches
Bioucas-Dias, J. M., Plaza, A., Dobigeon, N., Parente, M., Du, Q., Gader, P., & Chanussot, J. (2012) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2012.2194696 · Cited by 2,836 · cited 1×
“…manuscript. researchers have proposed linear/ nonlinear mixing models for representing the hyperspectral data, and developed several algorithms for extracting the spectral signatures (end-members) and estimating the underlying fractions (abundances) of each endmember from the scene [3, 4].”
BackgroundDeep Learning for Remote Sensing Data: A Technical Tutorial on the State of the Art
Zhang, L., Zhang, L., & Du, B. (2016) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2016.2540798 · Cited by 2,208 · cited 1×
“With the recent growth in computer technology and available data resources, researchers have started investigating the role of deep learning based technology for remote sensing data [11], and found success in many application areas [12].”
BackgroundImaging Spectrometry for Earth Remote Sensing
Goetz, A. F. H., Vane, G., Solomon, J. E., & Rock, B. N. (1985) · Science · doi:10.1126/science.228.4704.1147 · Cited by 1,928 · cited 1×
“Hyperspectral remote sensing has been started with ambitious goals of characterizing the materials, updating the spectral library, and estimating material maps on the Earth [1].”
BackgroundGhamisi, P., Yokoya, N., Li, J., Liao, W., Liu, S., Plaza, J., Rasti, B., & Plaza, A. (2017) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2017.2762087 · Cited by 909 · cited 1×
“Over the years, this technology has shown tremendous growth and expansion in the areas of spectral unmixing, classification, denoising, superresolution, land cover, object detection, multitemporal data analysis, and many more [2].”
BackgroundThe application of artificial neural networks to the analysis of remotely sensed data
Mas, J. F., & Flores, J. J. (2008) · International Journal of Remote Sensing · doi:10.1080/01431160701352154 · Cited by 616 · cited 1×
“Meanwhile the researchers have started using artificial neural networks (ANNs) for remote sensing data [8].”
BackgroundA Review of Nonlinear Hyperspectral Unmixing Methods
Heylen, R., Parente, M., & Gader, P. (2014) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2014.2320576 · Cited by 591 · cited 1×
“…manuscript. researchers have proposed linear/ nonlinear mixing models for representing the hyperspectral data, and developed several algorithms for extracting the spectral signatures (end-members) and estimating the underlying fractions (abundances) of each endmember from the scene [3, 4].”
BackgroundDeep Learning Meets Hyperspectral Image Analysis: A Multidisciplinary Review
Signoroni, A., Savardi, M., Baronio, A., & Benini, S. (2019) · Journal of Imaging · doi:10.3390/jimaging5050052 · Cited by 385 · cited 1×
“Interestingly, the deep learning based algorithms are still a black-box solution to many professionals [13].”
BackgroundDAEN: Deep Autoencoder Networks for Hyperspectral Unmixing
Su, Y., Li, J., Plaza, A., Marinoni, A., Gamba, P., & Chakravortty, S. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2018.2890633 · Cited by 335 · cited 1×
“Meanwhile, the authors in [18] has developed deep autoencoder networks for performing blind linear spectral unmixing especially addressing the issue of outliers in the data.”
BackgrounduDAS: An Untied Denoising Autoencoder With Sparsity for Spectral Unmixing
Qu, Y., & Qi, H. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2018.2868690 · Cited by 251 · cited 1×
“Recently the idea is improved in [16] that proposes end-to-end au-toencoder network by making encoder/decoder independent while constraining only the decoder as nonnegative.”
Background
Cited by
Hyperspectral Unmixing Using Transformer Network
Ghosh, P., Roy, S. K., Koirala, B., Rasti, B., & Scheunders, P. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3196057 · Cited by 175
Hyperspectral Unmixing Based on Nonnegative Matrix Factorization: A Comprehensive Review
Feng, X.-R., Li, H.-C., Wang, R., Du, Q., Jia, X., & Plaza, A. (2022) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2022.3175257 · Cited by 178
“In the last few years, DL [39], [40] has shown great power and potential in pattern recognition.”
BackgroundGao, L., Li, J., Zheng, K., & Jia, X. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3267890 · Cited by 166
“By virtue of the linear mixing theory, each pixel can be linearly expressed by the product of two matrices with additional residuals [61], [62], [63], [64].”
BackgroundTensor Decompositions for Hyperspectral Data Processing in Remote Sensing: A comprehensive review
Wang, M., Hong, D., Han, Z., Li, J., Yao, J. T., Gao, L., Zhang, B., & Chanussot, J. (2023) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2022.3227063 · Cited by 146
“In addition, the rise of deep learning techniques provides unprecedented success for SU, owing to their powerful learning ability [237], [238], [239], [240], [241], [242], [243].”
BackgroundBlind Hyperspectral Unmixing Using Autoencoders: A Critical Comparison
Palsson, B., Sveinsson, J. R., & Ulfarsson, M. O. (2022) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2021.3140154 · Cited by 107
“The only review paper focusing on DL for spectral unmixing is [28].”
Background
Metadata
- Authors
- Bhatt, J. S., & Joshi, M. V.
- Affiliations
- Indian Institute of Information Technology Vadodara (IN)
- Dhirubhai Ambani University (IN)
- Venue
- IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium
- Publisher
- IEEE
- Published
- 2020-09-26
- Pages
- 2189-2192
- OpenAlex
- W3130365209
- Cited by
- 121
- References
- 23
- Citations by year
- 2026: 20 · 2025: 23 · 2024: 30 · 2023: 24 · 2022: 15 · 2021: 9
- FWCI
- 25.08
- Type
- conference paper
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE International Geoscience and Remote Sensing Symposium (IGARSS) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Remote-Sensing Image Classification
- Physical Sciences › Earth and Planetary Sciences › Geochemistry and Petrology › Geochemistry and Geologic Mapping
- Physical Sciences › Chemistry › Analytical Chemistry › Spectroscopy and Chemometric Analyses
- Keywords
- hyperspectral unmixing, endmember estimation, abundance estimation, deep learning, autoencoder, convolutional neural networks, generative models, ill-posed inverse problems
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Deep Learning in Hyperspectral Unmixing: A Review. https://app.cochat.ai/papers/10.1109/igarss39084.2020.9324546
- The paper
- Bhatt, J. S., & Joshi, M. V. (2020). Deep Learning in Hyperspectral Unmixing: A Review. IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium. https://doi.org/10.1109/igarss39084.2020.9324546
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.