Deep Learning and Infrared Spectroscopy: Representation Learning with a β-Variational Autoencoder

Infrared (IR) spectra contain detailed and extensive information about the chemical composition and bonding environment in a sample. However, this information is difficult to extract from complex heterogeneous systems because of overlapping absorptions due to different generative factors. We impleme...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:The journal of physical chemistry letters Ročník 13; číslo 25; s. 5787
Hlavní autoři: Grossutti, Michael, D'Amico, Joseph, Quintal, Jonathan, MacFarlane, Hugh, Quirk, Amanda, Dutcher, John R
Médium: Journal Article
Jazyk:angličtina
Vydáno: 30.06.2022
ISSN:1948-7185, 1948-7185
On-line přístup:Zjistit podrobnosti o přístupu
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Infrared (IR) spectra contain detailed and extensive information about the chemical composition and bonding environment in a sample. However, this information is difficult to extract from complex heterogeneous systems because of overlapping absorptions due to different generative factors. We implement a deep learning approach to study the complex spectroscopic changes that occur in cross-linked polyethylene (PEX-a) pipe by training a β-variational autoencoder (β-VAE) on a database of PEX-a pipe spectra. We show that the β-VAE outperforms principal component analysis (PCA) and learns interpretable and independent representations of the generative factors of variance in the spectra. We apply the β-VAE encoder to a hyperspectrum of a crack in the wall of a pipe to evaluate the spatial distribution of these learned representations. This study shows how deep learning architectures like β-VAE can enhance the analysis of spectroscopic data of complex heterogeneous systems.Infrared (IR) spectra contain detailed and extensive information about the chemical composition and bonding environment in a sample. However, this information is difficult to extract from complex heterogeneous systems because of overlapping absorptions due to different generative factors. We implement a deep learning approach to study the complex spectroscopic changes that occur in cross-linked polyethylene (PEX-a) pipe by training a β-variational autoencoder (β-VAE) on a database of PEX-a pipe spectra. We show that the β-VAE outperforms principal component analysis (PCA) and learns interpretable and independent representations of the generative factors of variance in the spectra. We apply the β-VAE encoder to a hyperspectrum of a crack in the wall of a pipe to evaluate the spatial distribution of these learned representations. This study shows how deep learning architectures like β-VAE can enhance the analysis of spectroscopic data of complex heterogeneous systems.
AbstractList Infrared (IR) spectra contain detailed and extensive information about the chemical composition and bonding environment in a sample. However, this information is difficult to extract from complex heterogeneous systems because of overlapping absorptions due to different generative factors. We implement a deep learning approach to study the complex spectroscopic changes that occur in cross-linked polyethylene (PEX-a) pipe by training a β-variational autoencoder (β-VAE) on a database of PEX-a pipe spectra. We show that the β-VAE outperforms principal component analysis (PCA) and learns interpretable and independent representations of the generative factors of variance in the spectra. We apply the β-VAE encoder to a hyperspectrum of a crack in the wall of a pipe to evaluate the spatial distribution of these learned representations. This study shows how deep learning architectures like β-VAE can enhance the analysis of spectroscopic data of complex heterogeneous systems.Infrared (IR) spectra contain detailed and extensive information about the chemical composition and bonding environment in a sample. However, this information is difficult to extract from complex heterogeneous systems because of overlapping absorptions due to different generative factors. We implement a deep learning approach to study the complex spectroscopic changes that occur in cross-linked polyethylene (PEX-a) pipe by training a β-variational autoencoder (β-VAE) on a database of PEX-a pipe spectra. We show that the β-VAE outperforms principal component analysis (PCA) and learns interpretable and independent representations of the generative factors of variance in the spectra. We apply the β-VAE encoder to a hyperspectrum of a crack in the wall of a pipe to evaluate the spatial distribution of these learned representations. This study shows how deep learning architectures like β-VAE can enhance the analysis of spectroscopic data of complex heterogeneous systems.
Author MacFarlane, Hugh
Quintal, Jonathan
D'Amico, Joseph
Grossutti, Michael
Quirk, Amanda
Dutcher, John R
Author_xml – sequence: 1
  givenname: Michael
  surname: Grossutti
  fullname: Grossutti, Michael
– sequence: 2
  givenname: Joseph
  surname: D'Amico
  fullname: D'Amico, Joseph
– sequence: 3
  givenname: Jonathan
  surname: Quintal
  fullname: Quintal, Jonathan
– sequence: 4
  givenname: Hugh
  surname: MacFarlane
  fullname: MacFarlane, Hugh
– sequence: 5
  givenname: Amanda
  surname: Quirk
  fullname: Quirk, Amanda
– sequence: 6
  givenname: John R
  surname: Dutcher
  fullname: Dutcher, John R
BookMark eNpNjM1KAzEURoNUsK0-gZss3UxNMpOZxF2pf4WCoMVtuUnu6JQxGZMM4mv5ID6ToIKuvgOH883IxAePhJxytuBM8HOwabEfbI85L4RlvBTqgEy5rlTRcCUn__iIzFLaM1ZrppopMZeIA90gRN_5Jwre0bVvI0R09GFAm2NINgzvF_Qeh4gJfYbcBf-XvHX5mQL9_CgeIXbfEnq6HHNAb4PDeEwOW-gTnvzunGyvr7ar22Jzd7NeLTcFCCly4bgzlREGTStbpYWsnaudZG1To1WMWWhKqUFZNNxqLQCEUU4640pXmkbMydnP7RDD64gp7166ZLHvwWMY007UjRYVY6wSX2DqYEY
CitedBy_id crossref_primary_10_1038_s41467_024_49381_z
crossref_primary_10_1063_5_0271206
crossref_primary_10_1016_j_chemolab_2023_105029
crossref_primary_10_1016_j_diamond_2025_112352
crossref_primary_10_1039_D3EW00043E
crossref_primary_10_1016_j_trac_2024_117612
crossref_primary_10_3390_s22249764
crossref_primary_10_1021_acssensors_4c03260
crossref_primary_10_1016_j_fmre_2025_09_014
crossref_primary_10_1016_j_progpolymsci_2024_101828
crossref_primary_10_1016_j_matdes_2025_114788
crossref_primary_10_1038_s43588_023_00550_y
crossref_primary_10_1016_j_artmed_2024_103053
ContentType Journal Article
DBID 7X8
DOI 10.1021/acs.jpclett.2c01328
DatabaseName MEDLINE - Academic
DatabaseTitle MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic
Database_xml – sequence: 1
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod no_fulltext_linktorsrc
Discipline Chemistry
EISSN 1948-7185
GroupedDBID 53G
55A
5VS
7X8
7~N
AABXI
ABBLG
ABJNI
ABLBI
ABMVS
ABQRX
ABUCX
ACGFO
ACGFS
ACS
ADHLV
AEESW
AENEX
AFEFF
AHGAQ
ALMA_UNASSIGNED_HOLDINGS
AQSVZ
BAANH
CUPRZ
DU5
EBS
ED~
GGK
GNL
IH9
JG~
P2P
RNS
ROL
UI2
VF5
VG9
W1F
XKZ
ID FETCH-LOGICAL-a252t-d1db4b2bebf5f89256dd6d50f76ec800ca7359a8ceb1c992aa2b8d5dbd3d3b72
IEDL.DBID 7X8
ISICitedReferencesCount 19
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000821927200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1948-7185
IngestDate Fri Jul 11 11:01:47 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 25
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a252t-d1db4b2bebf5f89256dd6d50f76ec800ca7359a8ceb1c992aa2b8d5dbd3d3b72
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
PQID 2679240004
PQPubID 23479
ParticipantIDs proquest_miscellaneous_2679240004
PublicationCentury 2000
PublicationDate 20220630
PublicationDateYYYYMMDD 2022-06-30
PublicationDate_xml – month: 06
  year: 2022
  text: 20220630
  day: 30
PublicationDecade 2020
PublicationTitle The journal of physical chemistry letters
PublicationYear 2022
SSID ssj0069087
Score 2.4674432
Snippet Infrared (IR) spectra contain detailed and extensive information about the chemical composition and bonding environment in a sample. However, this information...
SourceID proquest
SourceType Aggregation Database
StartPage 5787
Title Deep Learning and Infrared Spectroscopy: Representation Learning with a β-Variational Autoencoder
URI https://www.proquest.com/docview/2679240004
Volume 13
WOSCitedRecordID wos000821927200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV27TsMwFLWAIsHCG_GWkVjdpk5c2yyoKlSwVAhVqFvlVxAMSWhSJH6LD-Gb8A0OHViQ2BPFvrGv7-P4HIQugGmSU6YIN1qRhHK_53QkiGJMMREJzVRSi03w0UhMJvI-FNzKAKtsfGLtqG1uoEbeoT0uAe8YJVfFKwHVKOiuBgmNZdSK_UcB0sUnP10En_jVAnk-TxfE-2DWsA7RbkeZsv1S-D9TVW1qoOEgfnnj-ogZbv53cFtoIwSXuP-9GrbRkst20Nqg0XTbRfrauQIHTtUnrDKL77J0BiB0DEr0FXBb5sX7JX6oEbLhYlK2eAXqtljhzw_y6LPsUEnE_XmVAyOmdbM9NB7ejAe3JKgsEEUZrYjtWp1oqp1OWSqkD4FAZIpFKe8548NJo3jMpBLGe3UjJVWKamGZ1Ta2seZ0H61keeYOENYxSJe4mFrJktgomXCTCAOGYc665BCdN9ab-nlDZ0JlLp-X04X9jv7wzDFap3AJoUbtnaBW6jeqO0Wr5q16Lmdn9Rr4AifWvsI
linkProvider ProQuest
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=Deep+Learning+and+Infrared+Spectroscopy%3A+Representation+Learning+with+a+%CE%B2-Variational+Autoencoder&rft.jtitle=The+journal+of+physical+chemistry+letters&rft.au=Grossutti%2C+Michael&rft.au=D%27Amico%2C+Joseph&rft.au=Quintal%2C+Jonathan&rft.au=MacFarlane%2C+Hugh&rft.date=2022-06-30&rft.issn=1948-7185&rft.eissn=1948-7185&rft.volume=13&rft.issue=25&rft.spage=5787&rft_id=info:doi/10.1021%2Facs.jpclett.2c01328&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1948-7185&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1948-7185&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1948-7185&client=summon