Multiscale Spectral-Spatial Unmixing Network With Boltzmann-Inspired Adaptive Temperature

Hyperspectral unmixing aims to decompose mixed pixels into endmembers with corresponding abundances. However, while several existing convolutional autoencoder methods usually use fixed convolutional kernels, making it difficult to capture the global context. In addition, due to the huge solution spa...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE journal of selected topics in applied earth observations and remote sensing Vol. 18; pp. 20085 - 20097
Main Authors:	Wang, Zhixiang, Xu, Jindong, Wei, Guangyi, Wang, Jie, Yan, Yu
Format:	Journal Article
Language:	English
Published:	Piscataway IEEE 2025 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:	Autoencoders Boltzmann distribution Constraints convolutional autoencoder (AE) Convolutional codes Decoding Distance Energy distribution Euclidean geometry Feature extraction Hyperspectral imaging hyperspectral unmixing (HU) Image reconstruction Kernel multiscale spectral–spatial attention Particle energy Pixels Representation learning Solution space Sparsity Spectral bands Temperature distribution Temperature effects temperature matrix
ISSN:	1939-1404, 2151-1535
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	Hyperspectral unmixing aims to decompose mixed pixels into endmembers with corresponding abundances. However, while several existing convolutional autoencoder methods usually use fixed convolutional kernels, making it difficult to capture the global context. In addition, due to the huge solution space of unmixing, existing methods usually adopt a consistent sparsity constraint and lack adaptivity. To overcome the above-mentioned limitations, we propose a multiscale spectral-spatial unmixing network with Boltzmann-inspired adaptive temperature. First, the spectral attention block and spatial attention block are designed to capture the dependence between spectral bands and enhance spatial feature extraction, respectively. These are integrated into multiscale spectral-spatial attention blocks with varying convolution kernels, which enable the network to focus on local and global image structures at the same time. Moreover, inspired by the Boltzmann distribution, we introduce a temperature matrix T in the softmax activation to regulate the output sparsity, similar to the effect of temperature on the particle energy distribution. The Euclidean distance and cosine distance between adjacent pixels are used to construct the similarity matrix to capture the spectral difference caused by the amplitude change, and then the T matrix is constructed. The softmax layer is divided by the resulting T matrix, so as to impose sparsity constraints of varying strengths on different areas. Evaluations on simulated and real datasets demonstrate the proposed approach's superiority over state-of-the-art methods.
AbstractList	Hyperspectral unmixing aims to decompose mixed pixels into endmembers with corresponding abundances. However, while several existing convolutional autoencoder methods usually use fixed convolutional kernels, making it difficult to capture the global context. In addition, due to the huge solution space of unmixing, existing methods usually adopt a consistent sparsity constraint and lack adaptivity. To overcome the above-mentioned limitations, we propose a multiscale spectral–spatial unmixing network with Boltzmann-inspired adaptive temperature. First, the spectral attention block and spatial attention block are designed to capture the dependence between spectral bands and enhance spatial feature extraction, respectively. These are integrated into multiscale spectral–spatial attention blocks with varying convolution kernels, which enable the network to focus on local and global image structures at the same time. Moreover, inspired by the Boltzmann distribution, we introduce a temperature matrix T in the softmax activation to regulate the output sparsity, similar to the effect of temperature on the particle energy distribution. The Euclidean distance and cosine distance between adjacent pixels are used to construct the similarity matrix to capture the spectral difference caused by the amplitude change, and then the T matrix is constructed. The softmax layer is divided by the resulting T matrix, so as to impose sparsity constraints of varying strengths on different areas. Evaluations on simulated and real datasets demonstrate the proposed approach’s superiority over state-of-the-art methods.
Author	Wei, Guangyi Wang, Zhixiang Xu, Jindong Yan, Yu Wang, Jie
Author_xml	– sequence: 1 givenname: Zhixiang orcidid: 0009-0008-6044-5622 surname: Wang fullname: Wang, Zhixiang email: wangzhixiang@s.ytu.edu.cn organization: School of Computer and Control Engineering, YanTai University, Yantai, China – sequence: 2 givenname: Jindong orcidid: 0000-0001-6688-5014 surname: Xu fullname: Xu, Jindong email: xujindong@ytu.edu.cn organization: School of Computer and Control Engineering, YanTai University, Yantai, China – sequence: 3 givenname: Guangyi orcidid: 0009-0001-6307-8273 surname: Wei fullname: Wei, Guangyi email: weiguangyi@s.ytu.edu.cn organization: School of Computer and Control Engineering, YanTai University, Yantai, China – sequence: 4 givenname: Jie surname: Wang fullname: Wang, Jie email: wangjie103120@163.com organization: School of Computer and Control Engineering, YanTai University, Yantai, China – sequence: 5 givenname: Yu orcidid: 0009-0006-4410-4444 surname: Yan fullname: Yan, Yu email: 100781134@s.ytu.edu.cn organization: School of Computer and Control Engineering, YanTai University, Yantai, China
BookMark	eNpFkctu2zAQRYkiAeo8vqBZCOhaLt8Sl27Qh4MkBWoHQVfEmBwldGVRpei2yddHiYJ2NcDg3jMDnCNy0MUOCXnH6Jwxaj5crNaL76s5p1zNhTKSKfWGzDhTrGRKqAMyY0aYkkkq35KjYdhSqnllxIz8uNq3OQwOWixWPbqcoC1XPeQAbXHT7cLf0N0V15j_xPSzuA35vvgY2_y4g64rl93Qh4S-WHjoc_iNxRp3PSbI-4Qn5LCBdsDT13lMbj5_Wp9_LS-_fVmeLy5LJzTLJdSVr2jFwSgP6B3faKC1VF5grVXDvKiE5syDkOjRmNpIjpVDw2qHUjbimCwnro-wtX0KO0gPNkKwL4uY7iykHFyLdtNo12ipUTIpNeO1UEpRqKpab5Qwm5H1fmL1Kf7a45DtNu5TN75vBZcvj1A5psSUcikOQ8Lm31VG7bMPO_mwzz7sq4-xdTa1AiL-b4z5kVqLJ4WtiPU
CODEN	IJSTHZ
Cites_doi	10.1109/JSTARS.2024.3450856 10.1109/TNNLS.2023.3300903 10.1109/TGRS.2018.2890633 10.1109/TCSVT.2024.3418610 10.1109/TGRS.2024.3353259 10.1080/10408347.2022.2073433 10.1109/JSTARS.2022.3175257 10.1016/j.ophoto.2024.100062 10.1016/j.ins.2013.03.014 10.1109/IGARSS46834.2022.9883117 10.1016/j.asoc.2018.05.012 10.1016/j.inffus.2024.102417 10.1109/ICWAPR48189.2019.8946465 10.1109/TGRS.2005.844293 10.1016/0166-1280(88)80133-7 10.1016/j.jag.2024.103864 10.1109/TGRS.2023.3321839 10.1109/IGARSS.2019.8898427 10.1109/WHISPERS.2015.8075378 10.1002/int.22108 10.1109/JSTARS.2012.2192472 10.1109/TGRS.2021.3069845 10.1016/j.inffus.2024.102419 10.1109/TGRS.2021.3064958 10.1016/j.jag.2024.103850 10.1080/01431161.2020.1854893 10.1109/TGRS.2019.2916296 10.3389/fpls.2022.810546 10.1016/j.neunet.2021.01.001 10.1109/CVPR42600.2020.01155 10.1109/TGRS.2024.3505292 10.1109/TIP.2014.2363423 10.1109/36.911111 10.1016/j.rse.2022.113448 10.1109/TCSVT.2025.3586282 10.1109/TGRS.2024.3393931 10.1109/IGARSS.2019.8900297 10.1109/TGRS.2021.3121799 10.1109/TGRS.2018.2868690 10.1016/j.jag.2022.102981 10.1109/TGRS.2024.3434427 10.2307/143141
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
DBID	97E ESBDL RIA RIE AAYXX CITATION 7UA 8FD C1K F1W FR3 H8D H96 KR7 L.G L7M DOA
DOI	10.1109/JSTARS.2025.3594155
DatabaseName	IEEE Xplore (IEEE) IEEE Xplore Open Access Journals IEEE All-Society Periodicals Package (ASPP) Online IEEE Xplore Digital Library CrossRef Water Resources Abstracts Technology Research Database Environmental Sciences and Pollution Management ASFA: Aquatic Sciences and Fisheries Abstracts Engineering Research Database Aerospace Database Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources Civil Engineering Abstracts Aquatic Science & Fisheries Abstracts (ASFA) Professional Advanced Technologies Database with Aerospace DOAJ Directory of Open Access Journals
DatabaseTitle	CrossRef Aerospace Database Civil Engineering Abstracts Aquatic Science & Fisheries Abstracts (ASFA) Professional Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources Technology Research Database ASFA: Aquatic Sciences and Fisheries Abstracts Engineering Research Database Advanced Technologies Database with Aerospace Water Resources Abstracts Environmental Sciences and Pollution Management
DatabaseTitleList	Aerospace Database
Database_xml	– sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: RIE name: IEEE Xplore Digital Library url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Geology
EISSN	2151-1535
EndPage	20097
ExternalDocumentID	oai_doaj_org_article_bf6cf646e4144612835550a7786b539b 10_1109_JSTARS_2025_3594155 11106218
Genre	orig-research
GrantInformation_xml	– fundername: Basic Research Key Project of Yantai Science and Technology Innovation Development Plan grantid: 2024JCYJ037 – fundername: National Natural Science Foundation of China grantid: 62072391; 62066013 funderid: 10.13039/501100001809
GroupedDBID	0R~ 29I 4.4 5GY 5VS 6IK 97E AAFWJ AAJGR AASAJ AAWTH ABAZT ABVLG ACIWK AENEX AETIX AFPKN AFRAH AGSQL ALMA_UNASSIGNED_HOLDINGS BEFXN BFFAM BGNUA BKEBE BPEOZ DU5 EBS EJD ESBDL GROUPED_DOAJ HZ~ IFIPE IPLJI JAVBF M43 O9- OCL OK1 RIA RIE RNS AAYXX CITATION 7UA 8FD C1K F1W FR3 H8D H96 KR7 L.G L7M
ID	FETCH-LOGICAL-c361t-a87d7072a95daedc2b6a0845d3e865f1d373621da34ede998942e7ce918ce44f3
IEDL.DBID	RIE
ISICitedReferencesCount	0
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001554469500008&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1939-1404
IngestDate	Fri Oct 03 12:46:35 EDT 2025 Sat Nov 29 13:42:12 EST 2025 Sat Nov 29 07:39:40 EST 2025 Wed Aug 27 07:36:31 EDT 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Language	English
License	https://creativecommons.org/licenses/by/4.0/legalcode
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c361t-a87d7072a95daedc2b6a0845d3e865f1d373621da34ede998942e7ce918ce44f3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0009-0006-4410-4444 0000-0001-6688-5014 0009-0008-6044-5622 0009-0001-6307-8273
OpenAccessLink	https://ieeexplore.ieee.org/document/11106218
PQID	3247362104
PQPubID	75722
PageCount	13
ParticipantIDs	crossref_primary_10_1109_JSTARS_2025_3594155 proquest_journals_3247362104 ieee_primary_11106218 doaj_primary_oai_doaj_org_article_bf6cf646e4144612835550a7786b539b
PublicationCentury	2000
PublicationDate	20250000 2025-00-00 20250101 2025-01-01
PublicationDateYYYYMMDD	2025-01-01
PublicationDate_xml	– year: 2025 text: 20250000
PublicationDecade	2020
PublicationPlace	Piscataway
PublicationPlace_xml	– name: Piscataway
PublicationTitle	IEEE journal of selected topics in applied earth observations and remote sensing
PublicationTitleAbbrev	JSTARS
PublicationYear	2025
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref13 ref12 ref34 ref15 ref37 ref14 ref36 ref30 ref11 ref33 ref10 ref32 ref2 Hernandez (ref31) 2017; 2 ref1 ref17 ref39 ref16 ref38 ref19 ref18 Otsu (ref35) 1975; 11 ref24 ref45 ref26 ref25 ref20 ref42 ref41 ref22 ref44 ref21 Liu (ref23) 2025 ref43 ref28 ref27 ref29 ref8 ref7 ref9 ref4 ref3 ref6 ref5 ref40
References_xml	– ident: ref16 doi: 10.1109/JSTARS.2024.3450856 – ident: ref21 doi: 10.1109/TNNLS.2023.3300903 – ident: ref12 doi: 10.1109/TGRS.2018.2890633 – ident: ref3 doi: 10.1109/TCSVT.2024.3418610 – ident: ref18 doi: 10.1109/TGRS.2024.3353259 – ident: ref4 doi: 10.1080/10408347.2022.2073433 – ident: ref25 doi: 10.1109/JSTARS.2022.3175257 – ident: ref7 doi: 10.1016/j.ophoto.2024.100062 – ident: ref37 doi: 10.1016/j.ins.2013.03.014 – ident: ref45 doi: 10.1109/IGARSS46834.2022.9883117 – ident: ref38 doi: 10.1016/j.asoc.2018.05.012 – ident: ref8 doi: 10.1016/j.inffus.2024.102417 – ident: ref13 doi: 10.1109/ICWAPR48189.2019.8946465 – ident: ref41 doi: 10.1109/TGRS.2005.844293 – ident: ref30 doi: 10.1016/0166-1280(88)80133-7 – volume: 11 start-page: 23 issue: 285/296 year: 1975 ident: ref35 article-title: A threshold selection method from gray-level histograms publication-title: Automatica – ident: ref36 doi: 10.1016/j.jag.2024.103864 – ident: ref20 doi: 10.1109/TGRS.2023.3321839 – ident: ref26 doi: 10.1109/IGARSS.2019.8898427 – ident: ref10 doi: 10.1109/WHISPERS.2015.8075378 – ident: ref40 doi: 10.1002/int.22108 – ident: ref27 doi: 10.1109/JSTARS.2012.2192472 – ident: ref43 doi: 10.1109/TGRS.2021.3069845 – ident: ref6 doi: 10.1016/j.inffus.2024.102419 – ident: ref15 doi: 10.1109/TGRS.2021.3064958 – ident: ref1 doi: 10.1016/j.jag.2024.103850 – ident: ref9 doi: 10.1080/01431161.2020.1854893 – ident: ref28 doi: 10.1109/TGRS.2019.2916296 – year: 2025 ident: ref23 article-title: Dual classification head self-training network for cross-scene hyperspectral image classification – ident: ref32 doi: 10.3389/fpls.2022.810546 – ident: ref33 doi: 10.1016/j.neunet.2021.01.001 – volume: 2 start-page: 2017 year: 2017 ident: ref31 article-title: Standard Maxwell-Boltzmann distribution: Definition and properties publication-title: ForsChem Res. Rep. – ident: ref34 doi: 10.1109/CVPR42600.2020.01155 – ident: ref17 doi: 10.1109/TGRS.2024.3505292 – ident: ref29 doi: 10.1109/TIP.2014.2363423 – ident: ref42 doi: 10.1109/36.911111 – ident: ref2 doi: 10.1016/j.rse.2022.113448 – ident: ref24 doi: 10.1109/TCSVT.2025.3586282 – ident: ref5 doi: 10.1109/TGRS.2024.3393931 – ident: ref14 doi: 10.1109/IGARSS.2019.8900297 – ident: ref44 doi: 10.1109/TGRS.2021.3121799 – ident: ref11 doi: 10.1109/TGRS.2018.2868690 – ident: ref19 doi: 10.1016/j.jag.2022.102981 – ident: ref22 doi: 10.1109/TGRS.2024.3434427 – ident: ref39 doi: 10.2307/143141
SSID	ssj0062793
Score	2.3751976
Snippet	Hyperspectral unmixing aims to decompose mixed pixels into endmembers with corresponding abundances. However, while several existing convolutional autoencoder...
SourceID	doaj proquest crossref ieee
SourceType	Open Website Aggregation Database Index Database Publisher
StartPage	20085
SubjectTerms	Autoencoders Boltzmann distribution Constraints convolutional autoencoder (AE) Convolutional codes Decoding Distance Energy distribution Euclidean geometry Feature extraction Hyperspectral imaging hyperspectral unmixing (HU) Image reconstruction Kernel multiscale spectral–spatial attention Particle energy Pixels Representation learning Solution space Sparsity Spectral bands Temperature distribution Temperature effects temperature matrix
SummonAdditionalLinks	– databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LT9wwELYqRCUuiLYgtt0iHzjWECd2HB-XCmgltKrK-2Q5fggkCIhdEPTXd8bO8hAHLlwjS46_mcx849jfELLuQm098ABW2AoKFCAETHsXmYJcL710Mqa7MEd7ajxuTk70n2etvvBMWJYHzsBttrF2sRZ1EFi5cJQHA1JtUfaslZVuMfoWSs-KqRyD61IluV1gJ5qhgEyvN8QLvQkOP_q7D5VhKTcqqTGhvshJSbq_77XyKkCnrLOzRBZ7ukhH-TU_kQ-h-0w-7qZ2vA9fyGm6PzsBnAPFTvK4bcGwyzB4FT3sLs_vITPRcT7qTY_Pp2d06-pi-u_Sdh373eFf9uDpyNtrjHr0IACJziLLy-RwZ_vg5y_WN0tgrqr5lNlGeVWo0mrpbfCubGtbNEL6KjS1jNxXCnIV97YSwQeNuutlUC5o3rggRKxWyFx31YVVQgPYyLfeeR6j0Dw2AoYCMynL6LQt-YD8mMFlrrMmhkm1RKFNRtcguqZHd0C2ENLHoShonR6AmU1vZvOWmQdkGQ3yNB_MBstpBmQ4s5Dpv76JAZKYFluIr-8x9zeygOvJGy9DMje9uQ3fyby7AwPfrCXH-w_Tytfj priority: 102 providerName: Directory of Open Access Journals
Title	Multiscale Spectral-Spatial Unmixing Network With Boltzmann-Inspired Adaptive Temperature
URI	https://ieeexplore.ieee.org/document/11106218 https://www.proquest.com/docview/3247362104 https://doaj.org/article/bf6cf646e4144612835550a7786b539b
Volume	18
WOSCitedRecordID	wos001554469500008&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: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2151-1535 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0062793 issn: 1939-1404 databaseCode: DOA dateStart: 20200101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVIEE databaseName: IEEE Xplore Digital Library customDbUrl: eissn: 2151-1535 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0062793 issn: 1939-1404 databaseCode: RIE dateStart: 20080101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Nb9QwELVoBRIXPovYUiofOOI2TvwRH7eIAhJaIWihnCzHHotKNFu12wr49cw4XhBCHLhFUaI4fmO_GdvzhrFnEUxI6AeIJnQYoKBDIFyKWVjkep101Lnkwnx8axeL_uTEvavJ6iUXBgDK4TPYo8uyl5-W8YqWyvZxXDYGOWmDbVhrpmSt9bRrWlsUdtEhcYI0Y6rEkGzcPtr4_P0HDAZbvddpRxz6Bw0Vtf5aXuWvObkQzeHd_2ziPXanepR8PpnAfXYDxgfs1qtSsff7Q_a5pNheIhTAqdg8rWwIKkSMhsePx7PTb0hefDGdBuefTldf-MHy6-rHWRhH8WakjXhIfJ7COU2M_AjQz550mLfY8eHLoxevRa2nIGJn5EqE3ibb2DY4nQKk2A4mNL3SqYPe6CxTZ5HOZAqdggSOpNlbsBGc7CMolbtHbHNcjvCYcUAY05BikjkrJ3Ov8FF0Xto2RxdaOWPP193rzyfZDF_Cjcb5CQ1PaPiKxowdEAS_HiXN63ID-9bXIeSHbGI2yoCiGFaSUByGV4EE8AbduWHGtgiP39-rUMzYzhpRXwfopUc_svxso7b_8doTdpuaOC237LDN1cUVPGU34zVidrFbYvfdYoE_AZsX16s
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Nb9QwEB1BAcGFzyIWCuTAEbexYzvxcYsorVhWCLZQTpZjj0Ulmq3aLQJ-PWPHC0KIA7coShTHb-x5Y3veADzzqF0gHsBq11CAQoSAmeAja8nXq6C8ijkX5sOsnc-7oyPztiSr51wYRMyHz3A7Xea9_LD0F2mpbIfGZa3JJ12GK0pKUY_pWuuJV4s2a-wSJTEsqcYUkSFemx2y8um79xQOCrXdKJO86B-OKOv1lwIrf83K2dXs3frPRt6Gm4VTVtPRCO7AJRzuwrVXuWbv93vwKSfZnhMYWKVy82ltg6VSxGR61eFwcvyN3Fc1H8-DVx-PV5-r3eWX1Y8TNwzsYEhb8RiqaXCnaWqsFkhMe1Ri3oTDvZeLF_usVFRgvtF8xVzXhrZuhTMqOAxe9NrVnVShwU6ryEPTkkPjwTUSA5okzi6w9Wh451HK2NyHjWE54AOokIAMffCBxygNjx0BgkRfhIjeOMEn8HzdvfZ0FM6wOeCojR3RsAkNW9CYwG6C4NejSfU636C-tWUQ2T5qH7XUKFMUy5NUHAVYLkng9aox_QQ2Ex6_v1egmMDWGlFbhui5JSaZf7aWD__x2lO4vr94M7Ozg_nrR3AjNXdcfNmCjdXZBT6Gq_4r4Xf2JNvhT-Lo2f0
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=Multiscale+Spectral%E2%80%93Spatial+Unmixing+Network+With+Boltzmann-Inspired+Adaptive+Temperature&rft.jtitle=IEEE+journal+of+selected+topics+in+applied+earth+observations+and+remote+sensing&rft.au=Wang%2C+Zhixiang&rft.au=Xu%2C+Jindong&rft.au=Wei%2C+Guangyi&rft.au=Wang%2C+Jie&rft.date=2025&rft.issn=1939-1404&rft.eissn=2151-1535&rft.volume=18&rft.spage=20085&rft.epage=20097&rft_id=info:doi/10.1109%2FJSTARS.2025.3594155&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_JSTARS_2025_3594155
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1939-1404&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1939-1404&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1939-1404&client=summon