A pre-training enhanced deep learning framework for robust sparse unmixing in chemical imaging

Chemical imaging techniques, such as hyperspectral and Raman imaging, provide spatially resolved spectral insights for non-destructive analysis of complex mixtures. However, accurately decomposing mixed pixel spectra into constituent components remains challenging due to spectral overlaps and variab...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Analytica chimica acta Ročník 1374; s. 344524
Hlavní autori: Wang, Yue, Liu, Anqi, Tan, Lin, Sun, Jinyu, Zhang, Hailiang, Xie, Ting, Zhang, Zhimin, Lu, Hongmei
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Netherlands Elsevier B.V 08.11.2025
Predmet:
ISSN:0003-2670, 1873-4324, 1873-4324
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Chemical imaging techniques, such as hyperspectral and Raman imaging, provide spatially resolved spectral insights for non-destructive analysis of complex mixtures. However, accurately decomposing mixed pixel spectra into constituent components remains challenging due to spectral overlaps and variability. While deep learning models have shown promise in jointly estimating endmember spectra and abundances, the increased complexity and parameters make them highly sensitive to initialization, often resulting in unstable performance. Therefore, developing accurate and robust unmixing algorithms is critical for reliable chemical imaging analysis. We propose a versatile pre-training framework to enhance sparse unmixing (P4SU) for chemical imaging. P4SU leverages simulated spectra generated from spectral libraries to pre-train deep learning models, followed by fine-tuning on target chemical imaging data. To accommodate a range of mixing scenarios, we equip the framework with both linear and nonlinear decoder options. Evaluated across three chemically diverse datasets—pigment mixtures, sugar solutions, and pharmaceutical tablets—P4SU demonstrates superior accuracy and stability compared to conventional methods (e.g., SUnSAL, CLSUnSAL) and non-pre-trained models. Significantly, pre-trained models reduce the root mean square error (RMSE) by 15–32 % compared to non-pre-trained ones and lower the standard deviation of results by 90–98 % on the pigment dataset. The method's robustness to spectral variability and noise demonstrates its potential for rapid, reliable chemical analysis in quality control and material identification. Implemented as an open-source Python toolkit (available at https://github.com/Ryan21wy/P4SU), P4SU offers a practical solution to streamline analytical workflows in chemical imaging analysis. [Display omitted] •A pretraining framework tailored for sparse unmixing (P4SU) was proposed for robust and accurate chemical imaging unmixing.•Leveraging simulated spectra, P4SU overcomes deep learning models' sensitivity to initial parameter settings.•Combined with linear and nonlinear decoders, pretrained models exhibit improvements across diverse unmixing scenarios.•P4SU provides a versatile, open-source solution for rapid chemical analysis in quality control and heritage conservation.
AbstractList Chemical imaging techniques, such as hyperspectral and Raman imaging, provide spatially resolved spectral insights for non-destructive analysis of complex mixtures. However, accurately decomposing mixed pixel spectra into constituent components remains challenging due to spectral overlaps and variability. While deep learning models have shown promise in jointly estimating endmember spectra and abundances, the increased complexity and parameters make them highly sensitive to initialization, often resulting in unstable performance. Therefore, developing accurate and robust unmixing algorithms is critical for reliable chemical imaging analysis. We propose a versatile pre-training framework to enhance sparse unmixing (P4SU) for chemical imaging. P4SU leverages simulated spectra generated from spectral libraries to pre-train deep learning models, followed by fine-tuning on target chemical imaging data. To accommodate a range of mixing scenarios, we equip the framework with both linear and nonlinear decoder options. Evaluated across three chemically diverse datasets—pigment mixtures, sugar solutions, and pharmaceutical tablets—P4SU demonstrates superior accuracy and stability compared to conventional methods (e.g., SUnSAL, CLSUnSAL) and non-pre-trained models. Significantly, pre-trained models reduce the root mean square error (RMSE) by 15–32 % compared to non-pre-trained ones and lower the standard deviation of results by 90–98 % on the pigment dataset. The method's robustness to spectral variability and noise demonstrates its potential for rapid, reliable chemical analysis in quality control and material identification. Implemented as an open-source Python toolkit (available at https://github.com/Ryan21wy/P4SU), P4SU offers a practical solution to streamline analytical workflows in chemical imaging analysis. [Display omitted] •A pretraining framework tailored for sparse unmixing (P4SU) was proposed for robust and accurate chemical imaging unmixing.•Leveraging simulated spectra, P4SU overcomes deep learning models' sensitivity to initial parameter settings.•Combined with linear and nonlinear decoders, pretrained models exhibit improvements across diverse unmixing scenarios.•P4SU provides a versatile, open-source solution for rapid chemical analysis in quality control and heritage conservation.
Chemical imaging techniques, such as hyperspectral and Raman imaging, provide spatially resolved spectral insights for non-destructive analysis of complex mixtures. However, accurately decomposing mixed pixel spectra into constituent components remains challenging due to spectral overlaps and variability. While deep learning models have shown promise in jointly estimating endmember spectra and abundances, the increased complexity and parameters make them highly sensitive to initialization, often resulting in unstable performance. Therefore, developing accurate and robust unmixing algorithms is critical for reliable chemical imaging analysis. We propose a versatile pre-training framework to enhance sparse unmixing (P4SU) for chemical imaging. P4SU leverages simulated spectra generated from spectral libraries to pre-train deep learning models, followed by fine-tuning on target chemical imaging data. To accommodate a range of mixing scenarios, we equip the framework with both linear and nonlinear decoder options. Evaluated across three chemically diverse datasets-pigment mixtures, sugar solutions, and pharmaceutical tablets-P4SU demonstrates superior accuracy and stability compared to conventional methods (e.g., SUnSAL, CLSUnSAL) and non-pre-trained models. Significantly, pre-trained models reduce the root mean square error (RMSE) by 15-32 % compared to non-pre-trained ones and lower the standard deviation of results by 90-98 % on the pigment dataset. The method's robustness to spectral variability and noise demonstrates its potential for rapid, reliable chemical analysis in quality control and material identification. Implemented as an open-source Python toolkit (available at https://github.com/Ryan21wy/P4SU), P4SU offers a practical solution to streamline analytical workflows in chemical imaging analysis.
Chemical imaging techniques, such as hyperspectral and Raman imaging, provide spatially resolved spectral insights for non-destructive analysis of complex mixtures. However, accurately decomposing mixed pixel spectra into constituent components remains challenging due to spectral overlaps and variability. While deep learning models have shown promise in jointly estimating endmember spectra and abundances, the increased complexity and parameters make them highly sensitive to initialization, often resulting in unstable performance. Therefore, developing accurate and robust unmixing algorithms is critical for reliable chemical imaging analysis.BACKGROUNDChemical imaging techniques, such as hyperspectral and Raman imaging, provide spatially resolved spectral insights for non-destructive analysis of complex mixtures. However, accurately decomposing mixed pixel spectra into constituent components remains challenging due to spectral overlaps and variability. While deep learning models have shown promise in jointly estimating endmember spectra and abundances, the increased complexity and parameters make them highly sensitive to initialization, often resulting in unstable performance. Therefore, developing accurate and robust unmixing algorithms is critical for reliable chemical imaging analysis.We propose a versatile pre-training framework to enhance sparse unmixing (P4SU) for chemical imaging. P4SU leverages simulated spectra generated from spectral libraries to pre-train deep learning models, followed by fine-tuning on target chemical imaging data. To accommodate a range of mixing scenarios, we equip the framework with both linear and nonlinear decoder options. Evaluated across three chemically diverse datasets-pigment mixtures, sugar solutions, and pharmaceutical tablets-P4SU demonstrates superior accuracy and stability compared to conventional methods (e.g., SUnSAL, CLSUnSAL) and non-pre-trained models. Significantly, pre-trained models reduce the root mean square error (RMSE) by 15-32 % compared to non-pre-trained ones and lower the standard deviation of results by 90-98 % on the pigment dataset.RESULTSWe propose a versatile pre-training framework to enhance sparse unmixing (P4SU) for chemical imaging. P4SU leverages simulated spectra generated from spectral libraries to pre-train deep learning models, followed by fine-tuning on target chemical imaging data. To accommodate a range of mixing scenarios, we equip the framework with both linear and nonlinear decoder options. Evaluated across three chemically diverse datasets-pigment mixtures, sugar solutions, and pharmaceutical tablets-P4SU demonstrates superior accuracy and stability compared to conventional methods (e.g., SUnSAL, CLSUnSAL) and non-pre-trained models. Significantly, pre-trained models reduce the root mean square error (RMSE) by 15-32 % compared to non-pre-trained ones and lower the standard deviation of results by 90-98 % on the pigment dataset.The method's robustness to spectral variability and noise demonstrates its potential for rapid, reliable chemical analysis in quality control and material identification. Implemented as an open-source Python toolkit (available at https://github.com/Ryan21wy/P4SU), P4SU offers a practical solution to streamline analytical workflows in chemical imaging analysis.SIGNIFICANCEThe method's robustness to spectral variability and noise demonstrates its potential for rapid, reliable chemical analysis in quality control and material identification. Implemented as an open-source Python toolkit (available at https://github.com/Ryan21wy/P4SU), P4SU offers a practical solution to streamline analytical workflows in chemical imaging analysis.
ArticleNumber 344524
Author Xie, Ting
Wang, Yue
Sun, Jinyu
Zhang, Zhimin
Lu, Hongmei
Zhang, Hailiang
Tan, Lin
Liu, Anqi
Author_xml – sequence: 1
  givenname: Yue
  surname: Wang
  fullname: Wang, Yue
– sequence: 2
  givenname: Anqi
  surname: Liu
  fullname: Liu, Anqi
– sequence: 3
  givenname: Lin
  surname: Tan
  fullname: Tan, Lin
– sequence: 4
  givenname: Jinyu
  surname: Sun
  fullname: Sun, Jinyu
– sequence: 5
  givenname: Hailiang
  surname: Zhang
  fullname: Zhang, Hailiang
– sequence: 6
  givenname: Ting
  surname: Xie
  fullname: Xie, Ting
– sequence: 7
  givenname: Zhimin
  orcidid: 0000-0002-4167-4234
  surname: Zhang
  fullname: Zhang, Zhimin
  email: zmzhang@csu.edu.cn
– sequence: 8
  givenname: Hongmei
  surname: Lu
  fullname: Lu, Hongmei
  email: hongmeilu@csu.edu.cn
BackLink https://www.ncbi.nlm.nih.gov/pubmed/40983411$$D View this record in MEDLINE/PubMed
BookMark eNp9kLtOxDAQRS0Egl3gA2iQS5osfiZGVAjxkpBooMXyOmPwkjjBTnj8PQ4LlFTWjM615p452gxdAIQOKFlQQsvj1cJYs2CEyQUXQjKxgWZUVbwQnIlNNCOE8IKVFdlB85RWeWSUiG20I8iJ4oLSGXo8w32EYojGBx-eMIRnEyzUuAbocQMmfq9dNC28d_EFuy7i2C3HNODUm5gAj6H1HxPkA7bP0HprGuxb85R3e2jLmSbB_s-7ix4uL-7Pr4vbu6ub87PbwnJSDYXKVztWLiVfKuWEKmswlnJVWUmFs5V0TLkaJD-RpeCkdLIiAqACk3s4xfkuOlr_28fudYQ06NYnC01jAnRj0pzJqW9ZTujhDzouW6h1H_Ot8VP_OskAXQM2dilFcH8IJXryrlc6e9eTd732njOn6wzkkm8eok7WwyTSR7CDrjv_T_oL3BeJeQ
Cites_doi 10.1126/science.228.4704.1147
10.1021/acs.analchem.0c04071
10.1109/TGRS.2017.2683719
10.1016/j.trac.2017.07.004
10.1021/acs.analchem.4c02426
10.1021/acs.analchem.0c03241
10.1109/TSP.2012.2222390
10.1038/s41467-023-39279-7
10.1080/01431160802558659
10.1016/j.culher.2018.01.003
10.1016/0169-7439(87)80084-9
10.1002/jrs.4054
10.1109/TGRS.2013.2240001
10.1073/pnas.2407439121
10.1021/ac4005265
10.1109/TGRS.2022.3230378
10.1016/j.chroma.2022.463768
10.1021/acs.analchem.3c05772
10.1109/JSTARS.2020.2977399
10.1109/JSTARS.2012.2194696
10.1109/JSTARS.2022.3175257
10.1109/TGRS.2011.2144605
10.1109/TGRS.2010.2098413
10.1109/TGRS.2018.2797200
10.1109/TIP.2015.2468177
10.1039/b922045c
10.1109/TIP.2012.2187668
10.1016/S0165-9936(04)00101-3
10.1029/JB086iB04p03039
10.1038/ncomms14843
10.1007/BF02163027
10.1021/cr300147r
10.1021/acs.analchem.2c03853
10.1021/acs.accounts.6b00048
10.1039/C8AN02212G
10.1146/annurev-anchem-062011-143152
10.1109/TGRS.2015.2453915
10.1177/0003702820952440
10.1016/j.jpba.2008.08.014
10.1021/acs.analchem.4c02720
10.1117/1.JRS.13.026509
10.1117/1.JBO.19.1.010901
10.1016/j.aca.2015.09.030
ContentType Journal Article
Copyright 2025 Elsevier B.V.
Copyright © 2025 Elsevier B.V. All rights reserved.
Copyright_xml – notice: 2025 Elsevier B.V.
– notice: Copyright © 2025 Elsevier B.V. All rights reserved.
DBID AAYXX
CITATION
NPM
7X8
DOI 10.1016/j.aca.2025.344524
DatabaseName CrossRef
PubMed
MEDLINE - Academic
DatabaseTitle CrossRef
PubMed
MEDLINE - Academic
DatabaseTitleList
PubMed
MEDLINE - Academic
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Chemistry
EISSN 1873-4324
ExternalDocumentID 40983411
10_1016_j_aca_2025_344524
S0003267025009183
Genre Journal Article
GroupedDBID ---
--K
--M
-~X
.~1
0R~
1B1
1RT
1~.
1~5
23M
4.4
457
4G.
5GY
5VS
6J9
7-5
71M
8P~
9JM
9JN
AABNK
AAEDT
AAEDW
AAHBH
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AARLI
AATTM
AAXKI
AAXUO
AAYWO
ABFNM
ABFRF
ABFYP
ABGSF
ABJNI
ABLST
ABMAC
ABUDA
ACBEA
ACCUC
ACDAQ
ACGFO
ACGFS
ACIWK
ACLOT
ACNCT
ACPRK
ACRLP
ACVFH
ADBBV
ADCNI
ADECG
ADEZE
ADUVX
AEBSH
AEFWE
AEHWI
AEIPS
AEKER
AENEX
AEUPX
AFJKZ
AFPUW
AFRAH
AFTJW
AFXIZ
AFZHZ
AGHFR
AGUBO
AGYEJ
AHEUO
AIEXJ
AIGII
AIIUN
AIKHN
AITUG
AJSZI
AKBMS
AKIFW
AKRWK
AKYEP
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
ANKPU
APXCP
AXJTR
BKOJK
BLECG
BLXMC
CS3
EBS
EFJIC
EFKBS
EFLBG
EO8
EO9
EP2
EP3
F5P
FDB
FIRID
FLBIZ
FNPLU
FYGXN
G-Q
GBLVA
IHE
J1W
K-O
KCYFY
KOM
M36
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
RNS
ROL
RPZ
SCC
SCH
SDF
SDG
SDP
SES
SEW
SPC
SPCBC
SSJ
SSK
SSU
SSZ
T5K
TN5
TWZ
UPT
WH7
YK3
ZMT
~02
~G-
~HD
.GJ
3O-
53G
9DU
AAQXK
AAYJJ
AAYXX
ABDPE
ABEFU
ABWVN
ABXDB
ACKIV
ACNNM
ACRPL
ADMUD
ADNMO
AGQPQ
AGRDE
AHHHB
AI.
AJQLL
ASPBG
AVWKF
AZFZN
CITATION
EJD
FA8
FEDTE
FGOYB
HMU
HVGLF
HZ~
H~9
MVM
NHB
R2-
SCB
T9H
UQL
VH1
WUQ
XOL
XPP
ZCG
ZXP
ZY4
NPM
7X8
ID FETCH-LOGICAL-c307t-8187f26b53b88f486deac1387c514fc75f28fde539564306f5704ee7ea983f833
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001582653800003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0003-2670
1873-4324
IngestDate Tue Sep 23 22:59:09 EDT 2025
Wed Sep 24 03:10:55 EDT 2025
Sat Nov 29 06:52:15 EST 2025
Sun Oct 19 01:49:16 EDT 2025
IsPeerReviewed true
IsScholarly true
Keywords Deep learning
Pre-training
Sparse unmixing
Raman imaging
Hyperspectral imaging
Language English
License Copyright © 2025 Elsevier B.V. All rights reserved.
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c307t-8187f26b53b88f486deac1387c514fc75f28fde539564306f5704ee7ea983f833
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0000-0002-4167-4234
PMID 40983411
PQID 3253411663
PQPubID 23479
ParticipantIDs proquest_miscellaneous_3253411663
pubmed_primary_40983411
crossref_primary_10_1016_j_aca_2025_344524
elsevier_sciencedirect_doi_10_1016_j_aca_2025_344524
PublicationCentury 2000
PublicationDate 2025-11-08
PublicationDateYYYYMMDD 2025-11-08
PublicationDate_xml – month: 11
  year: 2025
  text: 2025-11-08
  day: 08
PublicationDecade 2020
PublicationPlace Netherlands
PublicationPlace_xml – name: Netherlands
PublicationTitle Analytica chimica acta
PublicationTitleAlternate Anal Chim Acta
PublicationYear 2025
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References Yuan, Zhang, Wang (bib24) 2020; 13
Févotte, Dobigeon (bib38) 2015; 24
Abramczyk, Brozek-Pluska (bib7) 2013; 113
Kokaly, Clark, Swayze, Livo, Hoefen, Pearson, Wise, Benzel, Lowers, Driscoll, Klein (bib52) 2017
Golub, Reinsch (bib13) 1970; 14
Lee, Seung (bib19) 2000
Khoshsokhan, Rajabi, Zayyani (bib23) 2019; 13
Zhang, Chen, Liang (bib53) 2010; 135
Fan, Hu, Miller, Li (bib29) 2009; 30
Rasti, Koirala (bib49) 2022; 19
Fan, Yu, Lu, Chen, Hu, Zhang, Su, Zhang (bib40) 2023; 1690
Ghosh, Stuke, Todorović, Jørgensen, Schmidt, Vehtari, Rinke (bib44) 2019; 6
Gendrin, Roggo, Collet (bib4) 2008; 48
Broadwater, Banerjee (bib36) 2009
Rasti, Zouaoui, Mairal, Chanussot (bib10) 2024; 62
Lu, Fei (bib8) 2014; 19
Yang, Ji, Lu, Zhang (bib39) 2021; 93
Chandrasekhar (bib34) 2013
Rocha de Oliveira, de Juan (bib18) 2020; 92
Altmann, Halimi, Dobigeon, Tourneret (bib30) 2012; 21
Hapke (bib32) 1981; 86
Bioucas-Dias, Plaza, Dobigeon, Parente, Du, Gader, Chanussot (bib11) 2012; 5
Zhang, Yang, Xie, Wang, Zhang, Lu (bib43) 2024; 96
Georgiev, Fernández-Galiana, Vilms Pedersen, Papadopoulos, Xie, Stevens, Barahona (bib48) 2024; 121
Kong, Zheng, Li, Li, Chen (bib50) 2023; 20
Chen, Richard, Honeine (bib37) 2013; 61
Grabowski, Masarczyk, Głomb, Mendys (bib6) 2018; 31
Zhang, Li, Li, Deng, Plaza (bib28) 2018; 56
Fremout, Saverwyns (bib55) 2012; 43
Stewart, Priore, Nelson, Treado (bib2) 2012; 5
Piqueras, Duponchel, Offroy, Jamme, Tauler, de Juan (bib14) 2013; 85
Qian, Jia, Zhou, Robles-Kelly (bib20) 2011; 49
Carruthers, Clark, Clarke, Faulds, Graham (bib54) 2020; 75
Feng, Li, Wang, Du, Jia, Plaza (bib9) 2022; 15
Fan, Ming, Zeng, Zhang, Lu (bib45) 2019; 144
Yang, Ji, Xu, Li, Wang, Sun, Fan, Zhang, Lu, Zhang (bib42) 2023; 14
Broadwater, Chellappa, Banerjee, Burlina (bib35) 2007
Iordache, Bioucas-Dias, Plaza (bib27) 2014; 52
Kubelka, Munk (bib33) 1931; 12
Heylen, Scheunders (bib31) 2016; 54
Wold, Esbensen, Geladi (bib12) 1987; 2
Kallepitis, Bergholt, Mazo, Leonardo, Skaalure, Maynard, Stevens (bib16) 2017; 8
Guo, Fan, Yu, Lu, Zhang (bib41) 2024; 96
Bioucas-Dias, Figueiredo (bib25) 2010
Zhao, Wang, Chen, Rahardja (bib51) 2022; 60
Iordache, Bioucas-Dias, Plaza (bib26) 2011; 49
Fan, Wang, Yu, Lv, Zhang, Yang, Wen, Lu, Zhang (bib46) 2023; 95
Olmos, Benítez, Marro, Loza-Alvarez, Piña, Tauler, de Juan (bib15) 2017; 94
Amigo, Babamoradi, Elcoroaristizabal (bib3) 2015; 896
Liu, Duan, Cai, Shao (bib47) 2024; 96
Cucci, Delaney, Picollo (bib5) 2016; 49
Juan, Tauler, Dyson, Marcolli, Rault, Maeder (bib17) 2004; 23
Khoshsokhan, Rajabi, Zayyani (bib21) 2019; 12
Goetz, Vane, Solomon, Rock (bib1) 1985; 228
He, Zhang, Zhang (bib22) 2017; 55
Guo (10.1016/j.aca.2025.344524_bib41) 2024; 96
Févotte (10.1016/j.aca.2025.344524_bib38) 2015; 24
Zhang (10.1016/j.aca.2025.344524_bib43) 2024; 96
Fremout (10.1016/j.aca.2025.344524_bib55) 2012; 43
Khoshsokhan (10.1016/j.aca.2025.344524_bib21) 2019; 12
Hapke (10.1016/j.aca.2025.344524_bib32) 1981; 86
Golub (10.1016/j.aca.2025.344524_bib13) 1970; 14
Iordache (10.1016/j.aca.2025.344524_bib27) 2014; 52
Ghosh (10.1016/j.aca.2025.344524_bib44) 2019; 6
Fan (10.1016/j.aca.2025.344524_bib45) 2019; 144
Lu (10.1016/j.aca.2025.344524_bib8) 2014; 19
Olmos (10.1016/j.aca.2025.344524_bib15) 2017; 94
Chen (10.1016/j.aca.2025.344524_bib37) 2013; 61
Goetz (10.1016/j.aca.2025.344524_bib1) 1985; 228
Rocha de Oliveira (10.1016/j.aca.2025.344524_bib18) 2020; 92
He (10.1016/j.aca.2025.344524_bib22) 2017; 55
Stewart (10.1016/j.aca.2025.344524_bib2) 2012; 5
Yang (10.1016/j.aca.2025.344524_bib42) 2023; 14
Zhao (10.1016/j.aca.2025.344524_bib51) 2022; 60
Kallepitis (10.1016/j.aca.2025.344524_bib16) 2017; 8
Kokaly (10.1016/j.aca.2025.344524_bib52) 2017
Broadwater (10.1016/j.aca.2025.344524_bib36) 2009
Georgiev (10.1016/j.aca.2025.344524_bib48) 2024; 121
Carruthers (10.1016/j.aca.2025.344524_bib54) 2020; 75
Wold (10.1016/j.aca.2025.344524_bib12) 1987; 2
Chandrasekhar (10.1016/j.aca.2025.344524_bib34) 2013
Piqueras (10.1016/j.aca.2025.344524_bib14) 2013; 85
Grabowski (10.1016/j.aca.2025.344524_bib6) 2018; 31
Fan (10.1016/j.aca.2025.344524_bib46) 2023; 95
Kubelka (10.1016/j.aca.2025.344524_bib33) 1931; 12
Yang (10.1016/j.aca.2025.344524_bib39) 2021; 93
Bioucas-Dias (10.1016/j.aca.2025.344524_bib25) 2010
Cucci (10.1016/j.aca.2025.344524_bib5) 2016; 49
Zhang (10.1016/j.aca.2025.344524_bib28) 2018; 56
Rasti (10.1016/j.aca.2025.344524_bib10) 2024; 62
Zhang (10.1016/j.aca.2025.344524_bib53) 2010; 135
Altmann (10.1016/j.aca.2025.344524_bib30) 2012; 21
Yuan (10.1016/j.aca.2025.344524_bib24) 2020; 13
Kong (10.1016/j.aca.2025.344524_bib50) 2023; 20
Gendrin (10.1016/j.aca.2025.344524_bib4) 2008; 48
Liu (10.1016/j.aca.2025.344524_bib47) 2024; 96
Qian (10.1016/j.aca.2025.344524_bib20) 2011; 49
Amigo (10.1016/j.aca.2025.344524_bib3) 2015; 896
Rasti (10.1016/j.aca.2025.344524_bib49) 2022; 19
Abramczyk (10.1016/j.aca.2025.344524_bib7) 2013; 113
Bioucas-Dias (10.1016/j.aca.2025.344524_bib11) 2012; 5
Feng (10.1016/j.aca.2025.344524_bib9) 2022; 15
Khoshsokhan (10.1016/j.aca.2025.344524_bib23) 2019; 13
Lee (10.1016/j.aca.2025.344524_bib19) 2000
Juan (10.1016/j.aca.2025.344524_bib17) 2004; 23
Broadwater (10.1016/j.aca.2025.344524_bib35) 2007
Fan (10.1016/j.aca.2025.344524_bib40) 2023; 1690
Heylen (10.1016/j.aca.2025.344524_bib31) 2016; 54
Iordache (10.1016/j.aca.2025.344524_bib26) 2011; 49
Fan (10.1016/j.aca.2025.344524_bib29) 2009; 30
References_xml – start-page: 1
  year: 2010
  end-page: 4
  ident: bib25
  article-title: Alternating direction algorithms for constrained sparse regression: application to hyperspectral unmixing
  publication-title: 2010 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing
– volume: 75
  start-page: 178
  year: 2020
  end-page: 188
  ident: bib54
  article-title: Comparison of Raman and near-infrared chemical mapping for the analysis of pharmaceutical tablets
  publication-title: Appl. Spectrosc.
– volume: 2
  start-page: 37
  year: 1987
  end-page: 52
  ident: bib12
  article-title: Principal component analysis
  publication-title: Chemometr. Intell. Lab. Syst.
– volume: 96
  start-page: 5878
  year: 2024
  end-page: 5886
  ident: bib41
  article-title: GCMSFormer: a fully automatic method for the resolution of overlapping peaks in gas chromatography–mass spectrometry
  publication-title: Anal. Chem.
– volume: 43
  start-page: 1536
  year: 2012
  end-page: 1544
  ident: bib55
  article-title: Identification of synthetic organic pigments: the role of a comprehensive digital Raman spectral library
  publication-title: J. Raman Spectrosc.
– volume: 228
  start-page: 1147
  year: 1985
  end-page: 1153
  ident: bib1
  article-title: Imaging spectrometry for earth remote sensing
  publication-title: Science
– volume: 23
  start-page: 70
  year: 2004
  end-page: 79
  ident: bib17
  article-title: Spectroscopic imaging and chemometrics: a powerful combination for global and local sample analysis
  publication-title: Trends Anal. Chem.
– volume: 60
  start-page: 1
  year: 2022
  end-page: 15
  ident: bib51
  article-title: Hyperspectral unmixing for additive nonlinear models with a 3-D-CNN autoencoder network
  publication-title: IEEE Trans. Geosci. Rem. Sens.
– volume: 49
  start-page: 2014
  year: 2011
  end-page: 2039
  ident: bib26
  article-title: Sparse unmixing of hyperspectral data
  publication-title: IEEE Trans. Geosci. Rem. Sens.
– year: 2017
  ident: bib52
  article-title: USGS Spectral Library Version 7
– volume: 49
  start-page: 4282
  year: 2011
  end-page: 4297
  ident: bib20
  article-title: Hyperspectral unmixing via L1/2 sparsity-constrained nonnegative matrix factorization
  publication-title: IEEE Trans. Geosci. Rem. Sens.
– volume: 93
  start-page: 2200
  year: 2021
  end-page: 2206
  ident: bib39
  article-title: Prediction of liquid chromatographic retention time with graph neural networks to assist in small molecule identification
  publication-title: Anal. Chem.
– volume: 96
  start-page: 20354
  year: 2024
  end-page: 20361
  ident: bib47
  article-title: Unmixing autoencoder for image reconstruction from hyperspectral data
  publication-title: Anal. Chem.
– volume: 896
  start-page: 34
  year: 2015
  end-page: 51
  ident: bib3
  article-title: Hyperspectral image analysis. A tutorial
  publication-title: Anal. Chim. Acta
– volume: 85
  start-page: 6303
  year: 2013
  end-page: 6311
  ident: bib14
  article-title: Chemometric strategies to unmix information and increase the spatial description of hyperspectral images: a single-cell case study
  publication-title: Anal. Chem.
– volume: 113
  start-page: 5766
  year: 2013
  end-page: 5781
  ident: bib7
  article-title: Raman imaging in biochemical and biomedical applications. diagnosis and treatment of breast cancer
  publication-title: Chem. Rev.
– volume: 96
  start-page: 16599
  year: 2024
  end-page: 16608
  ident: bib43
  article-title: MSBERT: embedding tandem mass spectra into chemically rational space by mask learning and contrastive learning
  publication-title: Anal. Chem.
– volume: 30
  start-page: 2951
  year: 2009
  end-page: 2962
  ident: bib29
  article-title: Comparative study between a new nonlinear model and common linear model for analysing laboratory simulated‐forest hyperspectral data
  publication-title: Int. J. Rem. Sens.
– volume: 1690
  year: 2023
  ident: bib40
  article-title: Deep learning-based method for automatic resolution of gas chromatography-mass spectrometry data from complex samples
  publication-title: J. Chromatogr. A
– volume: 135
  start-page: 1138
  year: 2010
  ident: bib53
  article-title: Baseline correction using adaptive iteratively reweighted penalized least squares
  publication-title: Analyst
– volume: 8
  year: 2017
  ident: bib16
  article-title: Quantitative volumetric Raman imaging of three dimensional cell cultures
  publication-title: Nat. Commun.
– volume: 48
  start-page: 533
  year: 2008
  end-page: 553
  ident: bib4
  article-title: Pharmaceutical applications of vibrational chemical imaging and chemometrics: a review
  publication-title: J. Pharm. Biomed. Anal.
– volume: 61
  start-page: 480
  year: 2013
  end-page: 492
  ident: bib37
  article-title: Nonlinear unmixing of hyperspectral data based on a linear-mixture/nonlinear-fluctuation model
  publication-title: IEEE Trans. Signal Process.
– volume: 95
  start-page: 4863
  year: 2023
  end-page: 4870
  ident: bib46
  article-title: A universal and accurate method for easily identifying components in Raman spectroscopy based on deep learning
  publication-title: Anal. Chem.
– volume: 52
  start-page: 341
  year: 2014
  end-page: 354
  ident: bib27
  article-title: Collaborative sparse regression for hyperspectral unmixing
  publication-title: IEEE Trans. Geosci. Rem. Sens.
– volume: 19
  start-page: 1
  year: 2022
  end-page: 5
  ident: bib49
  article-title: SUnCNN: sparse unmixing using unsupervised convolutional neural network
  publication-title: IEEE Geosci. Remote. Sens. Lett.
– volume: 55
  start-page: 3909
  year: 2017
  end-page: 3921
  ident: bib22
  article-title: Total variation regularized reweighted sparse nonnegative matrix factorization for hyperspectral unmixing
  publication-title: IEEE Trans. Geosci. Rem. Sens.
– year: 2013
  ident: bib34
  article-title: Radiative transfer
  publication-title: Courier Corpor.
– volume: 19
  year: 2014
  ident: bib8
  article-title: Medical hyperspectral imaging: a review
  publication-title: J. Biomed. Opt.
– volume: 56
  start-page: 3265
  year: 2018
  end-page: 3276
  ident: bib28
  article-title: Spectral–spatial weighted sparse regression for hyperspectral image unmixing
  publication-title: IEEE Trans. Geosci. Rem. Sens.
– volume: 24
  start-page: 4810
  year: 2015
  end-page: 4819
  ident: bib38
  article-title: Nonlinear hyperspectral unmixing with robust nonnegative matrix factorization
  publication-title: IEEE Trans. Image Process.
– volume: 121
  year: 2024
  ident: bib48
  article-title: Hyperspectral unmixing for Raman spectroscopy via physics-constrained autoencoders
  publication-title: Proc. Natl. Acad. Sci.
– volume: 86
  start-page: 3039
  year: 1981
  end-page: 3054
  ident: bib32
  article-title: Bidirectional reflectance spectroscopy: 1. Theory
  publication-title: J. Geophys. Res. Solid Earth
– volume: 21
  start-page: 3017
  year: 2012
  end-page: 3025
  ident: bib30
  article-title: Supervised nonlinear spectral unmixing using a postnonlinear mixing model for hyperspectral imagery
  publication-title: IEEE Trans. Image Process.
– volume: 13
  year: 2019
  ident: bib23
  article-title: Clustered multitask non-negative matrix factorization for spectral unmixing of hyperspectral data
  publication-title: J. Appl. Remote Sens.
– volume: 31
  start-page: 1
  year: 2018
  end-page: 12
  ident: bib6
  article-title: Automatic pigment identification from hyperspectral data
  publication-title: J. Cult. Herit.
– volume: 15
  start-page: 4414
  year: 2022
  end-page: 4436
  ident: bib9
  article-title: Hyperspectral unmixing based on nonnegative matrix factorization: a comprehensive review
  publication-title: IEEE J. Sel. Top. Appl. Earth Obs. Rem. Sens.
– volume: 6
  year: 2019
  ident: bib44
  article-title: Deep learning spectroscopy: neural networks for molecular excitation spectra
  publication-title: Adv. Sci.
– volume: 20
  start-page: 1
  year: 2023
  end-page: 5
  ident: bib50
  article-title: Window transformer convolutional autoencoder for hyperspectral sparse unmixing
  publication-title: IEEE Geosci. Remote. Sens. Lett.
– volume: 5
  start-page: 354
  year: 2012
  end-page: 379
  ident: bib11
  article-title: Hyperspectral unmixing overview: geometrical, statistical, and sparse regression-based approaches
  publication-title: IEEE J. Sel. Top. Appl. Earth Obs. Rem. Sens.
– volume: 49
  start-page: 2070
  year: 2016
  end-page: 2079
  ident: bib5
  article-title: Reflectance hyperspectral imaging for investigation of works of art: old master paintings and illuminated manuscripts
  publication-title: Acc. Chem. Res.
– volume: 12
  start-page: 593
  year: 1931
  end-page: 601
  ident: bib33
  article-title: Ein beitrag zur optik der farbanstriche
  publication-title: Z. Tech. Phys.
– volume: 144
  start-page: 1789
  year: 2019
  end-page: 1798
  ident: bib45
  article-title: Deep learning-based component identification for the Raman spectra of mixtures
  publication-title: Analyst
– volume: 14
  start-page: 403
  year: 1970
  end-page: 420
  ident: bib13
  article-title: Singular value decomposition and least squares solutions
  publication-title: Numer. Math.
– volume: 14
  start-page: 3722
  year: 2023
  ident: bib42
  article-title: Ultra-fast and accurate electron ionization mass spectrum matching for compound identification with million-scale in-silico library
  publication-title: Nat. Commun.
– volume: 62
  start-page: 1
  year: 2024
  end-page: 31
  ident: bib10
  article-title: Image processing and machine learning for hyperspectral unmixing: an overview and the HySUPP python package
  publication-title: IEEE Trans. Geosci. Rem. Sens.
– volume: 12
  start-page: 1279
  year: 2019
  end-page: 1288
  ident: bib21
  article-title: Sparsity-Constrained distributed unmixing of hyperspectral data, IEEE J. Sel. Topics appl. Earth observ
  publication-title: Remote Sens.
– volume: 5
  start-page: 337
  year: 2012
  end-page: 360
  ident: bib2
  article-title: Raman imaging
  publication-title: Annu. Rev. Anal. Chem.
– start-page: 535
  year: 2000
  end-page: 541
  ident: bib19
  article-title: Algorithms for non-negative matrix factorization
  publication-title: Proceedings of the 14th International Conference on Neural Information Processing Systems
– volume: 13
  start-page: 998
  year: 2020
  end-page: 1010
  ident: bib24
  article-title: Improved collaborative non-negative matrix factorization and total variation for hyperspectral unmixing
  publication-title: IEEE J. Sel. Top. Appl. Earth Obs. Rem. Sens.
– volume: 92
  start-page: 15880
  year: 2020
  end-page: 15889
  ident: bib18
  article-title: Design of heterogeneity indices for blending quality assessment based on hyperspectral images and variographic analysis
  publication-title: Anal. Chem.
– volume: 94
  start-page: 130
  year: 2017
  end-page: 140
  ident: bib15
  article-title: Relevant aspects of unmixing/resolution analysis for the interpretation of biological vibrational hyperspectral images
  publication-title: Trends Anal. Chem.
– start-page: 4041
  year: 2007
  end-page: 4044
  ident: bib35
  article-title: Kernel fully constrained least squares abundance estimates
  publication-title: 2007 IEEE International Geoscience and Remote Sensing Symposium
– start-page: 1
  year: 2009
  end-page: 4
  ident: bib36
  article-title: A comparison of kernel functions for intimate mixture models
  publication-title: 2009 First Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing
– volume: 54
  start-page: 240
  year: 2016
  end-page: 251
  ident: bib31
  article-title: A multilinear mixing model for nonlinear spectral unmixing
  publication-title: IEEE Trans. Geosci. Rem. Sens.
– volume: 228
  start-page: 1147
  year: 1985
  ident: 10.1016/j.aca.2025.344524_bib1
  article-title: Imaging spectrometry for earth remote sensing
  publication-title: Science
  doi: 10.1126/science.228.4704.1147
– volume: 93
  start-page: 2200
  year: 2021
  ident: 10.1016/j.aca.2025.344524_bib39
  article-title: Prediction of liquid chromatographic retention time with graph neural networks to assist in small molecule identification
  publication-title: Anal. Chem.
  doi: 10.1021/acs.analchem.0c04071
– volume: 55
  start-page: 3909
  year: 2017
  ident: 10.1016/j.aca.2025.344524_bib22
  article-title: Total variation regularized reweighted sparse nonnegative matrix factorization for hyperspectral unmixing
  publication-title: IEEE Trans. Geosci. Rem. Sens.
  doi: 10.1109/TGRS.2017.2683719
– volume: 94
  start-page: 130
  year: 2017
  ident: 10.1016/j.aca.2025.344524_bib15
  article-title: Relevant aspects of unmixing/resolution analysis for the interpretation of biological vibrational hyperspectral images
  publication-title: Trends Anal. Chem.
  doi: 10.1016/j.trac.2017.07.004
– volume: 96
  start-page: 16599
  year: 2024
  ident: 10.1016/j.aca.2025.344524_bib43
  article-title: MSBERT: embedding tandem mass spectra into chemically rational space by mask learning and contrastive learning
  publication-title: Anal. Chem.
  doi: 10.1021/acs.analchem.4c02426
– volume: 92
  start-page: 15880
  year: 2020
  ident: 10.1016/j.aca.2025.344524_bib18
  article-title: Design of heterogeneity indices for blending quality assessment based on hyperspectral images and variographic analysis
  publication-title: Anal. Chem.
  doi: 10.1021/acs.analchem.0c03241
– year: 2017
  ident: 10.1016/j.aca.2025.344524_bib52
– volume: 61
  start-page: 480
  year: 2013
  ident: 10.1016/j.aca.2025.344524_bib37
  article-title: Nonlinear unmixing of hyperspectral data based on a linear-mixture/nonlinear-fluctuation model
  publication-title: IEEE Trans. Signal Process.
  doi: 10.1109/TSP.2012.2222390
– volume: 14
  start-page: 3722
  year: 2023
  ident: 10.1016/j.aca.2025.344524_bib42
  article-title: Ultra-fast and accurate electron ionization mass spectrum matching for compound identification with million-scale in-silico library
  publication-title: Nat. Commun.
  doi: 10.1038/s41467-023-39279-7
– start-page: 535
  year: 2000
  ident: 10.1016/j.aca.2025.344524_bib19
  article-title: Algorithms for non-negative matrix factorization
– volume: 30
  start-page: 2951
  year: 2009
  ident: 10.1016/j.aca.2025.344524_bib29
  article-title: Comparative study between a new nonlinear model and common linear model for analysing laboratory simulated‐forest hyperspectral data
  publication-title: Int. J. Rem. Sens.
  doi: 10.1080/01431160802558659
– volume: 31
  start-page: 1
  year: 2018
  ident: 10.1016/j.aca.2025.344524_bib6
  article-title: Automatic pigment identification from hyperspectral data
  publication-title: J. Cult. Herit.
  doi: 10.1016/j.culher.2018.01.003
– volume: 62
  start-page: 1
  year: 2024
  ident: 10.1016/j.aca.2025.344524_bib10
  article-title: Image processing and machine learning for hyperspectral unmixing: an overview and the HySUPP python package
  publication-title: IEEE Trans. Geosci. Rem. Sens.
– volume: 2
  start-page: 37
  year: 1987
  ident: 10.1016/j.aca.2025.344524_bib12
  article-title: Principal component analysis
  publication-title: Chemometr. Intell. Lab. Syst.
  doi: 10.1016/0169-7439(87)80084-9
– volume: 43
  start-page: 1536
  year: 2012
  ident: 10.1016/j.aca.2025.344524_bib55
  article-title: Identification of synthetic organic pigments: the role of a comprehensive digital Raman spectral library
  publication-title: J. Raman Spectrosc.
  doi: 10.1002/jrs.4054
– volume: 52
  start-page: 341
  year: 2014
  ident: 10.1016/j.aca.2025.344524_bib27
  article-title: Collaborative sparse regression for hyperspectral unmixing
  publication-title: IEEE Trans. Geosci. Rem. Sens.
  doi: 10.1109/TGRS.2013.2240001
– start-page: 4041
  year: 2007
  ident: 10.1016/j.aca.2025.344524_bib35
  article-title: Kernel fully constrained least squares abundance estimates
– volume: 121
  year: 2024
  ident: 10.1016/j.aca.2025.344524_bib48
  article-title: Hyperspectral unmixing for Raman spectroscopy via physics-constrained autoencoders
  publication-title: Proc. Natl. Acad. Sci.
  doi: 10.1073/pnas.2407439121
– volume: 85
  start-page: 6303
  year: 2013
  ident: 10.1016/j.aca.2025.344524_bib14
  article-title: Chemometric strategies to unmix information and increase the spatial description of hyperspectral images: a single-cell case study
  publication-title: Anal. Chem.
  doi: 10.1021/ac4005265
– volume: 60
  start-page: 1
  year: 2022
  ident: 10.1016/j.aca.2025.344524_bib51
  article-title: Hyperspectral unmixing for additive nonlinear models with a 3-D-CNN autoencoder network
  publication-title: IEEE Trans. Geosci. Rem. Sens.
  doi: 10.1109/TGRS.2022.3230378
– volume: 1690
  year: 2023
  ident: 10.1016/j.aca.2025.344524_bib40
  article-title: Deep learning-based method for automatic resolution of gas chromatography-mass spectrometry data from complex samples
  publication-title: J. Chromatogr. A
  doi: 10.1016/j.chroma.2022.463768
– volume: 96
  start-page: 5878
  year: 2024
  ident: 10.1016/j.aca.2025.344524_bib41
  article-title: GCMSFormer: a fully automatic method for the resolution of overlapping peaks in gas chromatography–mass spectrometry
  publication-title: Anal. Chem.
  doi: 10.1021/acs.analchem.3c05772
– volume: 13
  start-page: 998
  year: 2020
  ident: 10.1016/j.aca.2025.344524_bib24
  article-title: Improved collaborative non-negative matrix factorization and total variation for hyperspectral unmixing
  publication-title: IEEE J. Sel. Top. Appl. Earth Obs. Rem. Sens.
  doi: 10.1109/JSTARS.2020.2977399
– volume: 5
  start-page: 354
  year: 2012
  ident: 10.1016/j.aca.2025.344524_bib11
  article-title: Hyperspectral unmixing overview: geometrical, statistical, and sparse regression-based approaches
  publication-title: IEEE J. Sel. Top. Appl. Earth Obs. Rem. Sens.
  doi: 10.1109/JSTARS.2012.2194696
– start-page: 1
  year: 2009
  ident: 10.1016/j.aca.2025.344524_bib36
  article-title: A comparison of kernel functions for intimate mixture models
– volume: 15
  start-page: 4414
  year: 2022
  ident: 10.1016/j.aca.2025.344524_bib9
  article-title: Hyperspectral unmixing based on nonnegative matrix factorization: a comprehensive review
  publication-title: IEEE J. Sel. Top. Appl. Earth Obs. Rem. Sens.
  doi: 10.1109/JSTARS.2022.3175257
– volume: 49
  start-page: 4282
  year: 2011
  ident: 10.1016/j.aca.2025.344524_bib20
  article-title: Hyperspectral unmixing via L1/2 sparsity-constrained nonnegative matrix factorization
  publication-title: IEEE Trans. Geosci. Rem. Sens.
  doi: 10.1109/TGRS.2011.2144605
– volume: 12
  start-page: 593
  year: 1931
  ident: 10.1016/j.aca.2025.344524_bib33
  article-title: Ein beitrag zur optik der farbanstriche
  publication-title: Z. Tech. Phys.
– volume: 6
  year: 2019
  ident: 10.1016/j.aca.2025.344524_bib44
  article-title: Deep learning spectroscopy: neural networks for molecular excitation spectra
  publication-title: Adv. Sci.
– volume: 49
  start-page: 2014
  year: 2011
  ident: 10.1016/j.aca.2025.344524_bib26
  article-title: Sparse unmixing of hyperspectral data
  publication-title: IEEE Trans. Geosci. Rem. Sens.
  doi: 10.1109/TGRS.2010.2098413
– volume: 56
  start-page: 3265
  year: 2018
  ident: 10.1016/j.aca.2025.344524_bib28
  article-title: Spectral–spatial weighted sparse regression for hyperspectral image unmixing
  publication-title: IEEE Trans. Geosci. Rem. Sens.
  doi: 10.1109/TGRS.2018.2797200
– volume: 24
  start-page: 4810
  year: 2015
  ident: 10.1016/j.aca.2025.344524_bib38
  article-title: Nonlinear hyperspectral unmixing with robust nonnegative matrix factorization
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2015.2468177
– volume: 135
  start-page: 1138
  year: 2010
  ident: 10.1016/j.aca.2025.344524_bib53
  article-title: Baseline correction using adaptive iteratively reweighted penalized least squares
  publication-title: Analyst
  doi: 10.1039/b922045c
– volume: 21
  start-page: 3017
  year: 2012
  ident: 10.1016/j.aca.2025.344524_bib30
  article-title: Supervised nonlinear spectral unmixing using a postnonlinear mixing model for hyperspectral imagery
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2012.2187668
– volume: 23
  start-page: 70
  year: 2004
  ident: 10.1016/j.aca.2025.344524_bib17
  article-title: Spectroscopic imaging and chemometrics: a powerful combination for global and local sample analysis
  publication-title: Trends Anal. Chem.
  doi: 10.1016/S0165-9936(04)00101-3
– volume: 20
  start-page: 1
  year: 2023
  ident: 10.1016/j.aca.2025.344524_bib50
  article-title: Window transformer convolutional autoencoder for hyperspectral sparse unmixing
  publication-title: IEEE Geosci. Remote. Sens. Lett.
– volume: 86
  start-page: 3039
  year: 1981
  ident: 10.1016/j.aca.2025.344524_bib32
  article-title: Bidirectional reflectance spectroscopy: 1. Theory
  publication-title: J. Geophys. Res. Solid Earth
  doi: 10.1029/JB086iB04p03039
– volume: 8
  year: 2017
  ident: 10.1016/j.aca.2025.344524_bib16
  article-title: Quantitative volumetric Raman imaging of three dimensional cell cultures
  publication-title: Nat. Commun.
  doi: 10.1038/ncomms14843
– year: 2013
  ident: 10.1016/j.aca.2025.344524_bib34
  article-title: Radiative transfer
  publication-title: Courier Corpor.
– volume: 14
  start-page: 403
  year: 1970
  ident: 10.1016/j.aca.2025.344524_bib13
  article-title: Singular value decomposition and least squares solutions
  publication-title: Numer. Math.
  doi: 10.1007/BF02163027
– volume: 113
  start-page: 5766
  year: 2013
  ident: 10.1016/j.aca.2025.344524_bib7
  article-title: Raman imaging in biochemical and biomedical applications. diagnosis and treatment of breast cancer
  publication-title: Chem. Rev.
  doi: 10.1021/cr300147r
– start-page: 1
  year: 2010
  ident: 10.1016/j.aca.2025.344524_bib25
  article-title: Alternating direction algorithms for constrained sparse regression: application to hyperspectral unmixing
– volume: 95
  start-page: 4863
  year: 2023
  ident: 10.1016/j.aca.2025.344524_bib46
  article-title: A universal and accurate method for easily identifying components in Raman spectroscopy based on deep learning
  publication-title: Anal. Chem.
  doi: 10.1021/acs.analchem.2c03853
– volume: 49
  start-page: 2070
  year: 2016
  ident: 10.1016/j.aca.2025.344524_bib5
  article-title: Reflectance hyperspectral imaging for investigation of works of art: old master paintings and illuminated manuscripts
  publication-title: Acc. Chem. Res.
  doi: 10.1021/acs.accounts.6b00048
– volume: 144
  start-page: 1789
  year: 2019
  ident: 10.1016/j.aca.2025.344524_bib45
  article-title: Deep learning-based component identification for the Raman spectra of mixtures
  publication-title: Analyst
  doi: 10.1039/C8AN02212G
– volume: 5
  start-page: 337
  year: 2012
  ident: 10.1016/j.aca.2025.344524_bib2
  article-title: Raman imaging
  publication-title: Annu. Rev. Anal. Chem.
  doi: 10.1146/annurev-anchem-062011-143152
– volume: 54
  start-page: 240
  year: 2016
  ident: 10.1016/j.aca.2025.344524_bib31
  article-title: A multilinear mixing model for nonlinear spectral unmixing
  publication-title: IEEE Trans. Geosci. Rem. Sens.
  doi: 10.1109/TGRS.2015.2453915
– volume: 75
  start-page: 178
  year: 2020
  ident: 10.1016/j.aca.2025.344524_bib54
  article-title: Comparison of Raman and near-infrared chemical mapping for the analysis of pharmaceutical tablets
  publication-title: Appl. Spectrosc.
  doi: 10.1177/0003702820952440
– volume: 48
  start-page: 533
  year: 2008
  ident: 10.1016/j.aca.2025.344524_bib4
  article-title: Pharmaceutical applications of vibrational chemical imaging and chemometrics: a review
  publication-title: J. Pharm. Biomed. Anal.
  doi: 10.1016/j.jpba.2008.08.014
– volume: 96
  start-page: 20354
  year: 2024
  ident: 10.1016/j.aca.2025.344524_bib47
  article-title: Unmixing autoencoder for image reconstruction from hyperspectral data
  publication-title: Anal. Chem.
  doi: 10.1021/acs.analchem.4c02720
– volume: 13
  year: 2019
  ident: 10.1016/j.aca.2025.344524_bib23
  article-title: Clustered multitask non-negative matrix factorization for spectral unmixing of hyperspectral data
  publication-title: J. Appl. Remote Sens.
  doi: 10.1117/1.JRS.13.026509
– volume: 19
  year: 2014
  ident: 10.1016/j.aca.2025.344524_bib8
  article-title: Medical hyperspectral imaging: a review
  publication-title: J. Biomed. Opt.
  doi: 10.1117/1.JBO.19.1.010901
– volume: 896
  start-page: 34
  year: 2015
  ident: 10.1016/j.aca.2025.344524_bib3
  article-title: Hyperspectral image analysis. A tutorial
  publication-title: Anal. Chim. Acta
  doi: 10.1016/j.aca.2015.09.030
– volume: 12
  start-page: 1279
  year: 2019
  ident: 10.1016/j.aca.2025.344524_bib21
  article-title: Sparsity-Constrained distributed unmixing of hyperspectral data, IEEE J. Sel. Topics appl. Earth observ
  publication-title: Remote Sens.
– volume: 19
  start-page: 1
  year: 2022
  ident: 10.1016/j.aca.2025.344524_bib49
  article-title: SUnCNN: sparse unmixing using unsupervised convolutional neural network
  publication-title: IEEE Geosci. Remote. Sens. Lett.
SSID ssj0002104
Score 2.4855664
Snippet Chemical imaging techniques, such as hyperspectral and Raman imaging, provide spatially resolved spectral insights for non-destructive analysis of complex...
SourceID proquest
pubmed
crossref
elsevier
SourceType Aggregation Database
Index Database
Publisher
StartPage 344524
SubjectTerms Deep learning
Hyperspectral imaging
Pre-training
Raman imaging
Sparse unmixing
Title A pre-training enhanced deep learning framework for robust sparse unmixing in chemical imaging
URI https://dx.doi.org/10.1016/j.aca.2025.344524
https://www.ncbi.nlm.nih.gov/pubmed/40983411
https://www.proquest.com/docview/3253411663
Volume 1374
WOSCitedRecordID wos001582653800003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1873-4324
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002104
  issn: 0003-2670
  databaseCode: AIEXJ
  dateStart: 19950110
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lj9MwELbYXSS4IN6Ux8pIiANVUBPbsXOsVl0BqsqlK5ULVmI7kJXW7TYNKv-ecRw35bFoOXCJKtdp0plP43kPQq9YQXM4qHU00oWOqMjiSIiURplivFSjIo4L3Q6b4LOZWCyyENGt23EC3Fqx3War_8pqWANmu9LZf2D37kdhAT4D0-EKbIfrtRg_dnX_URj9MDT2qw_ya2NWYUjEl2EZkrLaPMP1smjqzRCky7o2w8ZeVNuu1kWFhgLVRTvPaF-ZbRuaOF-4Kwl3u1xnjl7Md57oT80OO9Oq8UmUl1XvMbCda6APT_lykcp-b_Z9Eglri_P2xajgJHK9_vwp84e1IHsJp3vik1DK_IbfJLt3MpwDyly3qIS97ff-3EV79lGenk2ncj5ZzF-vLiM3YMwF4rtpKwfoKOEsAwF4NH4_WXzYHdtg-7YpCOE1Qwi8TQb85alXKTFXGSmtsjK_i-50VgYee3TcQzeMvY9unYThfg_Q5zHeRwkOKMEOJTigBO9QggEl2KMEe5TggBJcWRxQgjuUPERnp5P5ybuoG7URKRDymwjUNl4macFIIURJRarhQI6J4AoU6lJxViai1IYRMKcpWJkl4yNqDDd5JkgpCHmEDu3SmicIq1QonquRzouCJirNM6K1EolmwOuMxwP0JtBOrnxHFRlSDc8lEFo6QktP6AGigbqyUwm9qicBF3-77WXghATCuhhYbs2yqSVJGOhtMejZA_TYs2j3FnQEfwa-fHqNu5-h2z3wn6PDzboxL9BN9W1T1etjdMAX4rhD2A-bN5TV
linkProvider Elsevier
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+pre-training+enhanced+deep+learning+framework+for+robust+sparse+unmixing+in+chemical+imaging&rft.jtitle=Analytica+chimica+acta&rft.au=Wang%2C+Yue&rft.au=Liu%2C+Anqi&rft.au=Tan%2C+Lin&rft.au=Sun%2C+Jinyu&rft.date=2025-11-08&rft.issn=1873-4324&rft.eissn=1873-4324&rft.volume=1374&rft.spage=344524&rft_id=info:doi/10.1016%2Fj.aca.2025.344524&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0003-2670&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0003-2670&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0003-2670&client=summon