Nonlinear Unmixing of Hyperspectral Images: Models and Algorithms
Open accessThe DOI matches its Crossref record; 55 of the 57 references it cites were found in a registry or an index.
Abstract
When considering the problem of unmixing hyperspectral images, most of the literature in the geoscience and image processing areas relies on the widely used linear mixing model (LMM). However, the LMM may be not valid, and other nonlinear models need to be considered, for instance, when there are multiscattering effects or intimate interactions. Consequently, over the last few years, several significant contributions have been proposed to overcome the limitations inherent in the LMM. In this article, we present an overview of recent advances in nonlinear unmixing modeling.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“However, when nonlinear interactions become significant, more intricate models are required (96).”
From Hyperspectral unmixing for Raman spectroscopy via physics-constrained autoencoders (2024) · cites this paper as [96]
The cited source says what the claim attributes to it.
In the citing paper
“However, accounting for nonlinear mixing interactions increases the complexity and computational cost of unmixing (96, 97), an issue of especial relevance in Raman spectroscopy where datasets (e.g., imaging/volumetric scans) are typically larger than in remote sensing.”
From Hyperspectral unmixing for Raman spectroscopy via physics-constrained autoencoders (2024) · cites this paper as [96]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
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 4×
“In [1], it is explained that linear mixtures are reasonable when two assumptions are wholly fulfilled.”
BackgroundMethodInfluentialKeshava, N., & Mustard, J. F. (2002) · IEEE Signal Processing Magazine · doi:10.1109/79.974727 · Cited by 2,549 · cited 2×
“More than 10 years after Keshava and Mustard’s comprehensive review article on spectral unmixing [11], this article provides an updated review focusing on non-linear unmixing techniques introduced in the past decade.”
BackgroundReflectance spectroscopy: Quantitative analysis techniques for remote sensing applications
Clark, R. N., & Roush, T. L. (1984) · Journal of Geophysical Research: Solid Earth · doi:10.1029/jb089ib07p06329 · Cited by 2,055 · cited 1×
“Secondly, the photons that reach the sensor must interact with only one material, as is the case in checkerboard type scenes [13].”
BackgroundBidirectional reflectance spectroscopy: 1. Theory
Hapke, B. (1981) · Journal of Geophysical Research: Solid Earth · doi:10.1029/jb086ib04p03039 · Cited by 1,888 · cited 3×
“In [2], the author derives an analytical model to express the measured reflectances as a function of parameters intrinsic to the mixtures, e.”
BackgroundMethodInfluentialTheory of Reflectance and Emittance Spectroscopy
Hapke, B. (1993) · Cambridge University Press eBooks · doi:10.1017/cbo9780511524998 · Cited by 1,849 · cited 4×
“The abundances can be interpreted as the relative areas occupied by the materials in a given image pixel [3].”
BackgroundInfluentialHeinz, D. C., & Chein-I-Chang (2001) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/36.911111 · Cited by 1,847 · cited 2×
“The fully constrained least square (FCLS) algorithm [35] was used for linear mixtures.”
MethodThe discrete-dipole approximation and its application to interstellar graphite grains
Draine, B. T. (1988) · The Astrophysical Journal · doi:10.1086/166795 · Cited by 1,528 · cited 1×
“Other popular approximating models include the discrete-dipole approximation [16] and the Shkuratov’s model [17] (interested readers are invited”
MethodA Model of Spectral Albedo of Particulate Surfaces: Implications for Optical Properties of the Moon
Shkuratov, Y., Starukhina, L., Hoffmann, H., & Arnold, G. (1999) · Icarus · doi:10.1006/icar.1998.6035 · Cited by 471
A Signal Processing Perspective on Hyperspectral Unmixing: Insights from Remote Sensing
Ma, W.-K., Bioucas-Dias, J. M., Chan, T.-H., Gillis, N., Gader, P., Plaza, A. J., Ambikapathi, A., & Chi, C.-Y. (2014) · IEEE Signal Processing Magazine · doi:10.1109/msp.2013.2279731 · Cited by 456
Nonlinear Unmixing of Hyperspectral Images Using a Generalized Bilinear Model
Halimi, A., Altmann, Y., Dobigeon, N., & Tourneret, J.-Y. (2011) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2010.2098414 · Cited by 443 · cited 2×
“linear model (GBM) has been proposed in [22] by setting βi,j,p = γi,j,pai,paj,p”
BackgroundMethodSelf-citation
Research works printed but not linked: 6
- [30] J. Plaza, P. Martinez, R. Perez, and A. Plaza, 'Nonlinear neural network mixture models for fractional abundance estimation in AVIRIS hyperspectral images,' in Proc. XIII NASA/Jet Propulsion Laboratory Airborne Earth Science Workshop , Pasadena, CA, USA, 2004. -
- [59] N. Dobigeon and C. F´ evotte, 'Robust nonnegative matrix factorization for nonlinear unmixing of hyperspectral images,' in Proc. IEEE GRSS Workshop Hyperspectral Image SIgnal Process.: Evolution in Remote Sens. (WHISPERS) , Gainesville, FL, June 2013. -
- [54] M. Winter, 'Fast autonomous spectral end-member determination in hyperspectral data,' in Proc. 13th Int. Conf. on Applied Geologic Remote Sensing , vol. 2, Vancouver, April 1999, pp. 337-344. -
- [53] RSI (Research Systems Inc.), ENVI User's guide Version 4.0 , Boulder, CO 80301 USA, Sept. 2003. -
- [12] R. B. Singer and T. B. McCord, 'Mars: Large scale mixing of bright and dark surface materials and implications for analysis of spectral reflectance,' in Proc. 10th Lunar and Planetary Sci. Conf. , March 1979, pp. 1835-1848. -
- [49] --, 'Nonlinear abundance estimation of hyperspectral images with L1-norm spatial regularization,' IEEE Trans. Geosci. and Remote Sensing , 2013, submitted. -
Cited by
Items 201–300 of 472
Nonlinear unmixing of minerals based on the log and continuum removal model
Zhao, H., & Zhao, X. (2019) · European Journal of Remote Sensing · doi:10.1080/22797254.2019.1601999 · Cited by 12
“Usually, the reconstruction error is used to display the accuracy distribution of different spectral unmixing methods (Dobigeon et al., 2013; Plaza et al., 2011), but the relationship between reconstruction error and spectral unmixing accuracy has not previously been effectively validated.”
MethodCluster-Wise Weighted NMF for Hyperspectral Images Unmixing with Imbalanced Data
Lv, X., Wang, W., & Liu, H. (2021) · Remote Sensing · doi:10.3390/rs13020268 · Cited by 12
“, the linear mixture model (LMM) and nonlinear mixture model [8], are commonly used.”
MethodAn infinite Gaussian mixture model with its application in hyperspectral unmixing
Deng, S., Xu, Y., Li, X., & He, Y. (2014) · Expert Systems with Applications · doi:10.1016/j.eswa.2014.09.059 · Cited by 12
“For the endmember extraction, most popular algorithms exploit the geometric perspective and assume that the data set contains at least one pure pixel of each member (Dobigeon et al., 2014; Du, Raksuntorn, & Younan, 2014; Fu, Ma, Chan, Bioucas-Dias, & Iordache, 2013).”
MethodMultiobjective Endmember Extraction Based on Bilinear Mixture Model
Jiang, X., Gong, M., Zhan, T., & Zhang, M. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.2988519 · Cited by 12
“To settle these problems, various kinds of nonlinear mixture models and unmixing algorithms have been proposed [28], [29], of which the most appealing one in tackling intimate mixtures is the Hapke’s model [30].”
BackgroundBenhalouche, F. Z., Karoui, M. S., Deville, Y., & Ouamri, A. (2017) · Journal of Applied Remote Sensing · doi:10.1117/1.jrs.11.025008 · Cited by 12
Modelling Spectral Unmixing of Geological Mixtures: An Experimental Study Using Rock Samples
Sahoo, M. M., Rajendran, K., Arun, P. V., Porwal, A. K., & Mathew, S. K. (2023) · Remote Sensing · doi:10.3390/rs15133300 · Cited by 12
Spectral–Spatial Fusion Sub-Pixel Mapping Based on Deep Neural Network
He, D., Shi, Q., Liu, X., Zhong, Y., & Liu, X. (2021) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2021.3101499 · Cited by 14
Nonlinear Unmixing via Deep Autoencoder Networks for Generalized Bilinear Model
Zhang, J., Zhang, X., Meng, H., Sun, C., Wang, L., & Cao, X. (2022) · Remote Sensing · doi:10.3390/rs14205167 · Cited by 11
“LMM assumes that each observed pixel is a linear combination of endmember spectral signatures [17,18].”
InfluentialNascimento, J. M. P., & Martín, G. (2019) · Data handling in science and technology · doi:10.1016/b978-0-444-63977-6.00008-0 · Cited by 15
Yang, B., Chen, Z., & Wang, B. (2020) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2019.2962609 · Cited by 12
“, nonlinear mixing effects) among different materials in real scenarios, which can result in observable unmixing errors [3], [4].”
BackgroundWang, Z., He, M., Ye, Z., Xu, K., Nian, Y., & Huang, B. (2020) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2020.2994334 · Cited by 11
“At this point, nonlinearly mixing spectral signatures should be considered [30], [33].”
BackgroundCiotola, M., Guarino, G., Mazza, A., Poggi, G., & Scarpa, G. (2025) · Remote Sensing · doi:10.3390/rs17121983 · Cited by 10
DTU-Net: A Multi-Scale Dilated Transformer Network for Nonlinear Hyperspectral Unmixing
Wang, C., Gao, J., Zhu, F., Halimi, A., & Richard, C. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3658361 · Cited by 14
“This phenomenon is particularly significant in forested regions, where interactions between soil and vegetation are prominent [1].”
Self-citationNon-linear hyperspectral unmixing by polytope decomposition
Marinoni, A., & Gamba, P. E. (2014) · Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing · doi:10.1109/whispers.2014.8077611 · Cited by 10
“Therefore, although linear unmixing is still a huge research field [1], non-linear models are more and more used [2].”
BackgroundMethodMiao, Y., & Yang, B. (2022) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2022.3203990 · Cited by 10
Hyperspectral sparse unmixing based on a novel adaptive total variation regularization
Ma, M., Xu, C., Zhang, J., Wang, S., Deng, C., & Wang, Y. (2022) · Infrared Physics & Technology · doi:10.1016/j.infrared.2022.104362 · Cited by 10
A Multisensor Hyperspectral Benchmark Dataset for Unmixing of Intimate Mixtures
Koirala, B., Rasti, B., Bnoulkacem, Z., Ribeiro, A. D. L., Madriz, Y., Herrmann, E., Gestels, A., Kerf, T. D., Lorenz, S., Fuchs, M., et al. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3343552 · Cited by 12
Advanced calibration to improve robustness of drone-acquired hyperspectral remote sensing data
Singh, K. D., & Nansen, C. (2017) · International Conference on Agro-Geoinformatics · doi:10.1109/agro-geoinformatics.2017.8047061 · Cited by 11
“The documented mixing models [18], [19], [20] are often time consuming, complex and associated with uncertainties [21] [22], there-”
BackgroundAhmed, A. M., Duran, O., Zweiri, Y., & Smith, M. J. (2019) · Remote Sensing · doi:10.3390/rs11161938 · Cited by 10
“The two main approaches to spectral unmixing are linear and nonlinear models [21,22,25,26,28].”
BackgroundMulti-Task Learning with Low-Rank Matrix Factorization for Hyperspectral Nonlinear Unmixing
Su, Y., Li, J., Qi, H., Gamba, P. E., Plaza, A., & Plaza, J. (2019) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2019.8899343 · Cited by 10
“In contrast, NSMMs assume that the mixing should be nonlinear in real scenarios, due to physical interactions between the sunlight scattered by multiple materials [10].”
BackgroundPhenology and Spectral Unmixing-Based Invasive Kudzu Mapping: A Case Study in Knox County, Tennessee
Ming, S., Tang, M., & Li, Y. (2021) · Remote Sensing · doi:10.3390/rs13224551 · Cited by 10
Hyperspectral Target Detection Using a Bilinear Sparse Binary Hypothesis Model
Shi, Y., Li, J., Li, Y., & Gamba, P. E. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3133135 · Cited by 11
A Multiobjective Group Sparse Hyperspectral Unmixing Method With High Correlation Library
Wei, Y., Xu, X., Pan, B., Li, T., & Shi, Z. (2022) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2022.3200693 · Cited by 11
“In this article, we propose a multiobjective sparse unmixing method, multiobjective group sparse hyperspectral un-mixing (MO-GSU), which integrates a group sparsity structure to address high correlation of the spectral library induced by spectral variability.”
A Novel Preunmixing Framework for Efficient Detection of Linear Mixtures in Hyperspectral Images
Marinoni, A., Plaza, A., & Gamba, P. E. (2017) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2017.2691319 · Cited by 10
Abundance Estimation Using Discontinuity Preserving and Sparsity-Induced Priors
Patel, J. R., Joshi, M. V., & Bhatt, J. S. (2019) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2019.2906756 · Cited by 10
“Nonlinear unmixing models (NLMMs) are also introduced to address the nonlinearity in the data [28].”
BackgroundRobust adaptive target detection in hyperspectral imaging
Vincent, F., & Besson, O. (2020) · Signal Processing · doi:10.1016/j.sigpro.2020.107905 · Cited by 10
Bayesian fusion of multi-band images : A powerful tool for super-resolution
Wei, Q. (2015) · theses.fr (ABES) · doi:10.70675/56dc4b7ez2775z4b91zbb0fze3c43c47e7e3 · Cited by 14
Wang, G., Zhang, Y. M., Xie, W., Qu, Y., & Feng, L. (2021) · International Journal of Remote Sensing · doi:10.1080/01431161.2021.1996653 · Cited by 9
“Although many complex factors, such as spectral non-linearity and variability, should be taken into consideration in the hyperspectral unmixing problem, the spectral mixing model is generally classified into Linear Mixing Model (LMM) and Non-linear Mixing Model (NLMM) (Prasad, Bruce, and Chanussot 2011; Dobigeon et al…”
MethodIftene, M., Benhalouche, F. Z., Benkouider, Y. K., & Karoui, M. S. (2023) · Digital Signal Processing · doi:10.1016/j.dsp.2023.104264 · Cited by 10
Feedback Information-Guided Spectral Variability Attention Network for Hyperspectral Unmixing
Xiang, S., Li, X., & Chen, S. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3452323 · Cited by 10
“Therefore, a single pixel often contains multiple materials, which is referred to as a mixed pixel [5].”
BackgroundHarris, J. K., & Grindrod, P. M. (2018) · Meteoritics and Planetary Science · doi:10.1111/maps.13065 · Cited by 11
“Deconvolving these spectral signatures with nonlinear unmixing models is a complicated, computer-intensive, and potentially nonunique process (e.g., Hapke 1981; Mustard and Pieters 1989; Dobigeon et al. 2014; Pilorget et al. 2016; Lapotre et al. 2017).”
BackgroundOccurrence of secondary minerals at Tharsis Montes of Mars: A critical assessment
Ahmad, A., Patel, R. R., Deka, B., Nagori, R., Arya, A. S., & Nair, A. M. (2022) · Icarus · doi:10.1016/j.icarus.2022.114953 · Cited by 10
Jia, X., & Guo, B. (2022) · Sensors · doi:10.3390/s22145417 · Cited by 9
“Thus, the mixed pixels should be decomposed into a series of end members and their proportional fractions to improve the performance of HSI analysis [3].”
BackgroundHyperspectral unmixing using weighted sparse regression with total variation regularization
Ren, L., Ma, Z., Bovolo, F., Hu, J., & Bruzzone, L. (2022) · International Journal of Remote Sensing · doi:10.1080/01431161.2021.2018151 · Cited by 10
“We also refer readers to (Dobigeon et al. 2014) and (Heylen, Parente and Gader 2014) for a detailed review of the NLMM. Based on the LMM, we can distinguish between blind and semi-blind unmixing methods, depending on whether using the spectral library (or dictionary) or not.”
MethodBilinear matrix factorization using a gradient method for hyperspectral endmember spectra extraction
Benhalouche, F. Z., Deville, Y., Karoui, M. S., & Ouamri, A. (2016) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2016.7730715 · Cited by 9
“When facing flat landscape and irradiance homogeneity in the observed area, the mixing model used in unsupervised SU techniques is linear [7].”
BackgroundMethodRecent Advances in Hyperspectral Unmixing Using Sparse Techniques and Deep Learning
Zhang, S., Su, Y., Xu, X., Li, J., Deng, C., & Plaza, A. (2020) · Advances in Computer Vision and Pattern Recognition · doi:10.1007/978-3-030-38617-7_13 · Cited by 8
“Unmixing algorithms rely on specific mixing models, which can be characterized as either linear or nonlinear [5, 6].”
BackgroundHashemi-Nazari, Y., Saberi-Movahed, F., Tajaddini, A., Moreira, C., Ning, X., & Tiwari, P. (2025) · Machine Learning · doi:10.1007/s10994-025-06793-2 · Cited by 8
“Linear models operate under the assumption that various endmembers function independently (Miao & Qi, 2007), whereas nonlinear models suggest that the observed spectrum results from a nonlinear relationship between the abundances of endmembers (Dobigeon et al., 2014).”
Liu, J., Li, T., Yu, Z., Lyu, S., Fu, Q., & Yu, X. (2025) · npj Heritage Science · doi:10.1038/s40494-025-02241-5 · Cited by 8
“For local unmixing, we evaluated Fully Constrained Least Squares (FCLS) and its regularized variants, as well as nonlinear models such as the Generalized Bilinear Model (GBM) and the Polynomial Post-Nonlinear Mixing Model (PPNMM) 41,47,48 .”
Hyperspectral data multi-sharpening based on linear-quadratic nonnegative matrix factorization
Benhalouche, F. Z., Karoui, M. S., Deville, Y., & Ouamri, A. (2015) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2015.7326521 · Cited by 8
“When facing non-flat landscape and/or irradiance heterogeneity in the observed scene (such as in urban environments), the linear mixing model used in LSU techniques is not valid any more, and it should be replaced by a nonlinear mixing model [6].”
MethodBlind Unmixing Using Dispersion Model-Based Autoencoder to Address Spectral Variability
Zheng, H., Li, Z. X., Sun, C., Zhang, H., Liu, H., & Wei, Z. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3399003 · Cited by 9
“For example, the intimate mixture may undergo multiple reflections in a nonsmooth surface, in which case the LMM is no longer applicable [11], [25], [26], [27], [28].”
BackgroundA multi-domain dual-stream network for hyperspectral unmixing
Hu, J., Wang, T., Jin, Q., Peng, C., & Liu, Q. (2024) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2024.104247 · Cited by 12
Xu, L., Su, X., Wang, K., Zhou, T., Lu, C., Niu, J., Jin, X., Huang, J., & Feng, H. (2025) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2025.109977 · Cited by 8
Sparse Grassmannian Embeddings for Hyperspectral Data Representation and Classification
Chepushtanova, S., & Kirby, M. J. L. (2017) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2017.2648514 · Cited by 8
Drumetz, L., Chanussot, J., & Iwasaki, A. (2018) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2018.8462256 · Cited by 8
“sand), and require more complex mixture models such as bilinear mixture models [4, 5].”
BackgroundNouri, T., Oskouei, M. M., Alizadeh, B., Gamba, P. E., & Marinoni, A. (2018) · Journal of the Indian Society of Remote Sensing · doi:10.1007/s12524-018-0885-9 · Cited by 8
Resmini, R. G., Rand, R. S., Allen, D. W., & Deloye, C. J. (2014) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2051434 · Cited by 8
“[1], [2], and [3] and references cited therein.”
BackgroundBenhalouche, F. Z., Deville, Y., Karoui, M. S., & Ouamri, A. (2016) · Machine learning for signal processing ... · doi:10.1109/mlsp.2016.7738868 · Cited by 8
Estimating Nonlinearities in p-Linear Hyperspectral Mixtures
Marinoni, A., Plaza, J., Plaza, A., & Gamba, P. E. (2018) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2018.2840524 · Cited by 8
Blind Sparse Nonlinear Hyperspectral Unmixing Using an $\ell_{q}$ Penalty
Sigurðsson, J., Ulfarsson, M. O., & Sveinsson, J. R. (2018) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2018.2862895 · Cited by 9
“In the last decade, nonlinear mixtures have received increased attention by HU researchers [3], [4], with a focus on intimate and bilinear mixtures.”
BackgroundInfluentialMultivariate analysis of Brillouin imaging data by supervised and unsupervised learning
Xiang, Y., Seow, K. L. C., Paterson, C., & Török, P. (2021) · Journal of Biophotonics · doi:10.1002/jbio.202000508 · Cited by 11
“undance of the hidden endmembers would then depend on that of endmembers on top, therefore requires non-linear unmixing, which is far less developed and remains a key area of research for future work [63]. To the best of our knowledge, we have also demonstrated for the rst time feature identication in Brillouin images…”
BackgroundSpectral-spatial joint sparsity unmixing of hyperspectral images based on framelet transform
Xu, C., Wu, Z., Li, F., Zhang, S., Deng, C., & Wang, Y. (2020) · Infrared Physics & Technology · doi:10.1016/j.infrared.2020.103564 · Cited by 8
Miao, Y., & Yang, B. (2021) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2021.3115177 · Cited by 11
Low Dimensional Manifold Model in Hyperspectral Image Reconstruction
Zhu, W., Shi, Z., & Osher, S. (2020) · Advances in computer vision and pattern recognition · doi:10.1007/978-3-030-38617-7_10 · Cited by 8
Sparse signal reconstruction for nonlinear models via piecewise rational optimization
Marmin, A., Castella, M., Pesquet, J.-C., & Duval, L. C. (2020) · Signal Processing · doi:10.1016/j.sigpro.2020.107835 · Cited by 8
Identifiability-Guaranteed Simplex-Structured Post-Nonlinear Mixture Learning via Autoencoder
Lyu, Q., & Fu, X. (2021) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2021.3096806 · Cited by 8
Image patch analysis of sunspots and active regions. I. Intrinsic dimension and correlation analysisPreprint
Moon, K. R., Li, J. J., Delouille, V., De Visscher, R., Watson, F., & Hero, A. O. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1503.04127 · Cited by 8
“However, it is not guaranteed that natural images are best represented using linear methods as there are cases where non-linear models have superior performance (Dobigeon et al. 2014).”
BackgroundSelf-citationHierarchical homogeneity-based superpixel segmentation: application to hyperspectral image analysis
Ayres, L. C., Almeida, S., Bermudez, J. C. M., & Borsoi, R. A. (2024) · International Journal of Remote Sensing · doi:10.1080/01431161.2024.2384098 · Cited by 7
“A data-dependent multiscale regularization model was proposed taking into account the spectral variability of the end-members, where both the abundances and the endmember signatures were constrained to vary smoothly inside each superpixel (Borsoi, Imbiriba, and Carlos Moreira Bermudez 2020).”
InfluentialSelf-citationZapiola, A. G., Boselli, A., Menafoglio, A., & Vantini, S. (2025) · Applied Computing and Geosciences · doi:10.1016/j.acags.2025.100297 · Cited by 9
Campos-Delgado, D. U., Mendoza-Chavarría, J. N., Gutiérrez-Navarro, O., Quintana, L., León, R., Ortega, S., Fabelo, H. A., López, C., Lejeune, M., & Callicó, G. M. (2025) · IEEE Access · doi:10.1109/access.2025.3552439 · Cited by 7
“On the other hand, there are also nonlinear mixing models (NMM) [6], [7], as the generalized bilinear [8], post-nonlinear and multilinear [9], [10] models.”
Nouri, T., & Oskouei, M. M. (2016) · International Journal of Remote Sensing · doi:10.1080/01431161.2016.1225176 · Cited by 7
“The RMSE is expressed as below: RMSE ¼ 1 nq Xn i¼1 Xq z¼1 Si;z Ŝi;z 2" #1=2 : (15) In the case of real data set, the average reconstruction error (ARE) (Dobigeon et al. 2014) between primary (Y) and reconstructed (Ŷ) hyperspectral data is calculated using the following equation: ARE ¼ 1 nl Xn i¼1…”
MethodCompressive sensing unmixing algorithm for breast cancer detection
Obermeier, R., & Martinez-Lorenzo, J. A. (2018) · IET Microwaves Antennas & Propagation · doi:10.1049/iet-map.2017.0599 · Cited by 7
Fast Hyperspectral Unmixing Using a Multiscale Sparse Regularization
İnce, T., & Nicolas Dobigeon, B. (2022) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2022.3217872 · Cited by 7
“Even if light interactions occurring in the scene can suffer from multiple scattering effects [2], these interactions are often negligible [1], which eases the mathematical formulation of the hyperspectral unmixing [3] problem.”
BackgroundBarankin-Type Bound for Constrained Parameter Estimation
Nitzan, E., Routtenberg, T., & Tabrikian, J. (2023) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2023.3322777 · Cited by 7
Development of deep learning-based hyperspectral remote sensing image unmixing
Su, Y., Ruoqing, X. U., Gao, L., Zhu, H. A. N., & Sun, X. (2024) · National Remote Sensing Bulletin · doi:10.11834/jrs.20243165 · Cited by 8
A map-based NMF approach to hyperspectral image unmixing using a linear-quadratic mixture model
Jarboui, L., Hosseini, S., Guidara, R., Deville, Y., & Hamida, A. B. (2016) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2016.7472299 · Cited by 8
“Index Terms— Unsupervised spectral unmixing, LinearQuadratic mixture, Non-negative Matrix Factorization, Maximum A Posteriori estimation, Hyperspectral image”
Seminonlinear spectral unmixing using a neural network-based forward modeling
Karimpouli, S., Salimi, A., & Ghasemzadeh, S. (2016) · Journal of Applied Remote Sensing · doi:10.1117/1.jrs.10.036006 · Cited by 8
Provably Robust Blind Source Separation of Linear-Quadratic Near-Separable Mixtures
Kervazo, C., Gillis, N., & Nicolas Dobigeon, B. (2021) · SIAM Journal on Imaging Sciences · doi:10.1137/20m1382878 · Cited by 11
“In various applications, the LMM may however suffer from some limitations and can only be considered as a first-order approximation of non-linear mixing models [6, 13, 11].”
BackgroundMethodInfluentialUezato, T., Fauvel, M., & Nicolas Dobigeon, B. (2020) · Remote Sensing · doi:10.3390/rs12142326 · Cited by 7
“This ambiguity shows that distinguishing measurement noise from spectral variability or, more generally any other second-order effects, such as nonlinearity [40] or adjacency effects [41], is a challenging issue.”
BackgroundBenachir, D., Deville, Y., Hosseini, S., & Karoui, M. S. (2020) · Remote Sensing · doi:10.3390/rs12193198 · Cited by 7
Hyperspectral Anomaly Detection and Unmixing via Joint Optimization and Deep Interactive Network
He, X., Wang, Y., Ling, Q., Li, K., Luo, Y., & Zhou, S. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3705375 · Cited by 6
“The model is subject to the abundance nonnegativity constraint (ANC) and the abundance sum-to-one constraint (ASC) [23].”
Quadratic blind linear unmixing: A graphical user interface for tissue characterization
Gutiérrez-Navarro, O., Campos-Delgado, D. U., Arce-Santana, E., & Jo, J. A. (2015) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2015.10.016 · Cited by 6
“In fact, similar methods have been studied and applied since the 90s [16] in the decomposition of satellite imagery based on linear and non-linear mixture models [17,18].”
A Coordinate-Descent-Based Approach to Solving the Sparse Group Elastic Net
Samarov, D. V., Allen, D. W., Hwang, J., Lee, Y. J., & Litorja, M. (2016) · Technometrics · doi:10.1080/00401706.2016.1273138 · Cited by 6
“That being said there is an increasing body of work that has begun looking into capturing various types of nonlinearities, for example, by including pthorder interactions between endmembers (see Dobigeon et al. 2014 for a review).”
BackgroundZhang, H., & Yang, B. (2024) · International Journal of Remote Sensing · doi:10.1080/01431161.2024.2320181 · Cited by 7
“To solve these problems, a variety of non-linear mixture models and nonlinear unmixing algorithms have been proposed (Dobigeon et al. 2014).”
BackgroundHibi, Y., Uesaka, S., & Naito, M. (2024) · The Analyst · doi:10.1039/d4an00624k · Cited by 6
Robust Unmixing Algorithms for Hyperspectral Imagery
Halimi, A., Altmann, Y., Buller, G. S., McLaughlin, S., Oxford, W. J., Clarke, D., & Piper, J. (2016) · Sensor Signal Processing for Defence (SSPD) · doi:10.1109/sspd.2016.7590611 · Cited by 7
“However, this model can be inappropriate for some hyperspectral scenarios, namely in the presence of a nonlinearity (NL) such as multiple scattering [1], [2], endmember variability (EV) [3]–[5], or outliers (rarely represented materials, faulty detector,.”
BackgroundSelf-citationGiordano, S., Mercier, G., & Rudant, J.-P. (2018) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2018.2827258 · Cited by 6
“Linear mixing models are most frequently used for the unmixing but nonlinear methods have also been proposed [11].”
MethodImproved Estimation of the Intrinsic Dimension of a Hyperspectral Image Using Random Matrix Theory
Berman, M. (2019) · Remote Sensing · doi:10.3390/rs11091049 · Cited by 6
A Homogeneity-Based Multiscale Hyperspectral Image Representation for Sparse Spectral Unmixing
Ayres, L. C., Almeida, S., Bermudez, J. C. M., & Borsoi, R. A. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9415024 · Cited by 6
“Most solutions to the unmixing problem are based on a linear mixing model (LMM) [6, 7], which considers each reflectance vector (HI pixel) to be formed by the linear combination of a finite number of endmembers, weighted by their fractional abundances.”
BackgroundInfluentialSelf-citationYe, C., Liu, S., Xu, M., & Yang, Z. (2022) · International Journal of Remote Sensing · doi:10.1080/01431161.2022.2111532 · Cited by 6
Marinoni, A., & Gamba, P. E. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2897430 · Cited by 6
“This procedure may lead to inaccurate understanding and quantification of the physical–chemical composition of the scene, since an epistemic uncertainty is introduced by the arbitrary choice of the metric used to estimate the endmember fractions [8], [10], [11], [13].”
MethodSparse Hyperspectral Unmixing Using Spectral Library Adaptive Adjustment
Zhang, Z., Liao, S., Fang, H., Zhang, H., & Wang, S. (2019) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2019.2939829 · Cited by 6
“According to the endmembers mixing method, the spectral mixing model is mainly divided into two categories: the linear mixing model (LMM) [4] and the nonlinear mixing model [5], [6].”
MethodZhang, G., Cerra, D., & Müller, R. (2019) · Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing · doi:10.1109/whispers.2019.8920894 · Cited by 8
“In addition, spectral unmixing methods have been widely used to analyze elementary materials in hyperspectral images, and they allow multiple materials to be present in one pixel [1].”
BackgroundMethodInfluentialFast Spectral Unmixing based on Dykstra's Alternating ProjectionPreprint
Wei, Q., Bioucas‐Dias, J. M., Nicolas Dobigeon, B., & Tourneret, J. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1505.01740 · Cited by 6
“tection [8]. In this context, several models have been proposed in the literature to properly describe the physical process underlying the observed measurements. Under some generally mild assumptions [9], these measurements are supposed to result from linear combinations of the elementary spectra, according Part of th…”
ResultInfluentialSelf-citationWang, T., & Lin, H. (2017) · Wiley eBooks · doi:10.1002/9781118786352.wbieg0927 · Cited by 6
GLUP: Yet another algorithm for blind unmixing of hyperspectral data
Ammanouil, R., Ferrari, A., Richard, C., & Mary, D. L. (2014) · Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing · doi:10.1109/whispers.2014.8077546 · Cited by 5
“See [3–7] for extensions to nonlinear mixing models.”
Self-citationAugmented GBM Nonlinear Model to Address Spectral Variability for Hyperspectral Unmixing
Meng, L., Liu, D., Wang, L., Benediktsson, J. A., Yue, X., & Pan, Y. (2023) · Remote Sensing · doi:10.3390/rs15123205 · Cited by 6
“GBM can effectively handle the assumptions in bilinear mixing models (BMM) [18,19] and is considered to be a generalization of LMM and FM [8,20].”
BackgroundXiang, C., Xiao, H., He, F.-S., Dai, Z., Huang, W., Zhu, B., & Liu, S. (2024) · Ore and Energy Resource Geology · doi:10.1016/j.oreoa.2024.100072 · Cited by 5
Non‐linear unmixing of hyperspectral images using multiple‐kernel self‐organising maps
Rashwan, S., Nicolas Dobigeon, B., Sheta, W. M., & Hassan, H. M. (2019) · IET Image Processing · doi:10.1049/iet-ipr.2018.5094 · Cited by 5
Decomposition of mixed pixels in MODIS data using Bernstein basis functions
Qin, Y., Guo, F., Ren, Y., Wang, X., Gu, J., Ma, J., Zou, L., & Shen, X. (2019) · Journal of Applied Remote Sensing · doi:10.1117/1.jrs.13.046509 · Cited by 5
“mixed pixels is generally based on a linear spectral mixture model (LSMM) or a nonlinear spectral mixture model (NLSMM).(11) Although the NLSMM is more applicable when the multiple scattering among distinct endmembers is not negligible,(12) such as in intimate mineral mixtures and vegetation canopies,(13) the LSMM is…”
MethodSpatial-Spectral Nonlinear Hyperspectral Unmixing Under Complex Noise
Li, C., Li, J., Sui, C., Song, R., & Chen, X. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3143852 · Cited by 6
Computational macroscopic lifetime imaging and concentration unmixing of autofluorescence
Ochoa, M., Smith, J. T., Gao, S., & Intes, X. (2022) · Journal of Biophotonics · doi:10.1002/jbio.202200133 · Cited by 9
Investigating the influence of hyperspectral data compression on spectral unmixing
Kuester, J., Anastasiadis, J., Middelmann, W., & Heizmann, M. (2022) · Image and signal processing for remote sensing. Conference · doi:10.1117/12.2636129 · Cited by 7
“To perform spectral unmixing, an inverse problem has to be solved, which is often achieved using a mixing model.(27) A straightforward mixing model that yields valid results for macroscopic scale mixtures is the linear mixing model (LMM):(28,29)”
MethodShadow-Aware Nonlinear Spectral Unmixing With Spatial Regularization
Zhang, G., Scheunders, P., & Cerra, D. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3289570 · Cited by 6
“an image element at subpixel level [1], [2], [3].”
BackgroundInfluentialMultilayer structured NMF for spectral unmixing of hyperspectral images
Rajabi, R., & Ghassemian, H. (2014) · Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing · doi:10.1109/whispers.2014.8077521 · Cited by 5
“Spectral unmixing problem can be solved under linear or nonlinear frameworks [9].”
BackgroundRand, R. S., Resmini, R. G., & Allen, D. W. (2017) · Journal of Applied Remote Sensing · doi:10.1117/1.jrs.11.016005 · Cited by 5
“17 , 26, 27, and 28 and references cited therein.”
BackgroundLinear-Quadratic NMF-Based Urban Hyperspectral Data Unmixing With Some Known Endmembers
Benhalouche, F. Z., Karoui, M. S., & Deville, Y. (2018) · Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing · doi:10.1109/whispers.2018.8747241 · Cited by 5
Scattering Transform Framework for Unmixing of Hyperspectral Data
Zeng, Y., Ritz, C. H., Zhao, J., & Lan, J. (2019) · Remote Sensing · doi:10.3390/rs11232868 · Cited by 5
“However, because the linear model does not exactly match the real scenarios, it cannot obtain appropriate unmixing results in most cases [2,19,20].”
BackgroundImproved Deconvolution of Mineral Reflectance Spectra
Rialland, R., Soussen, C., Marion, R., & Carrère, V. (2021) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2021.3110008 · Cited by 5
Geodesic simplex based multiobjective endmember extraction for nonlinear hyperspectral mixtures
Jiang, X., Gong, M., Zhan, T., & Li, H. (2021) · Information Sciences · doi:10.1016/j.ins.2021.07.009 · Cited by 5
GAUSS: Guided encoder - decoder Architecture for hyperspectral Unmixing with Spatial Smoothness
Wickramathilaka, H. M. K. D., Fernando, D., Jayasundara, D., Wickramasinghe, D., Ranasinghe, Y., Godaliyadda, R. I., Ekanayake, M. P. B., Herath, V. R., Ramanayake, L., Senarath, N., et al. (2023) · European Journal of Remote Sensing · doi:10.1080/22797254.2023.2277213 · Cited by 6
“Over the evolution of HU techniques, numerous unmixing algorithms have been proposed for both linear and non-linear mixing models (Dobigeon et al., 2013; Gu et al., 2021; Halimi et al., 2011; Heylen et al., 2014; Zhao & Zhao, 2019) under signal processing (SP) and deep learning (DL) domains (Wang…”
Method
Metadata
- Authors
- Dobigeon, N., Tourneret, J.-Y., Richard, C., Bermudez, J. C. M., McLaughlin, S., & Hero, A. O.
- Affiliations
- Institut National Polytechnique de Toulouse (FR)
- Université de Toulouse (FR)
- Universidade Federal de Santa Catarina (BR)
- Heriot-Watt University (GB)
- University of Michigan (US)
- Venue
- IEEE Signal Processing Magazine
- Published
- 2014-01
- Volume
- 31
- Issue
- 1
- Pages
- 82-94
- ISSN
- 1053-5888 (ISSN-L)
- OpenAlex
- W2005818237
- Cited by
- 420
- References
- 57
- Citations by year
- 2026: 11 · 2025: 23 · 2024: 32 · 2023: 38 · 2022: 36 · 2021: 34 · 2020: 45 · 2019: 31 · 2018: 36 · 2017: 39 · 2016: 45 · 2015: 29 · 2014: 20
- FWCI
- 61.72
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Signal Processing Magazine (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- HAL (submittedVersion, other-oa)
- arXiv (Cornell University)
- Funders
- Agence Nationale de la Recherche (ANR-12-BS03-0003)
- Engineering and Physical Sciences Research Council (EP/J015180/1)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Remote-Sensing Image Classification
- Physical Sciences › Chemistry › Analytical Chemistry › Spectroscopy and Chemometric Analyses
- Physical Sciences › Earth and Planetary Sciences › Geochemistry and Petrology › Geochemistry and Geologic Mapping
- Keywords
- nonlinear unmixing, hyperspectral unmixing, linear mixing model, multiple scattering, end-member mixing model, endmember extraction
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
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.