Hydrogen uptake prediction in porous carbon materials explained by decision tree machine learning Algorithms: From experimental data to interpretable predictions

Widespread adoption of hydrogen fuel is constrained by the cost and safety limits of high-pressure and cryogenic storage. Adsorption-based storage in Porous Carbon Materials (PCMs) is a promising alternative, yet its potential is unrealized due to the research time and cost of discovery. A Machine L...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:International journal of hydrogen energy Jg. 197; S. 152704
Hauptverfasser: Sunkara, Hemanth, Bhat A S, Shravani, R, Namitha, Acharya, Sushmitha, Shekar, Selva Kumar, Sainath, Krishnamurthy, Siddiqui, Shabnam
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 05.01.2026
Schlagworte:
ISSN:0360-3199
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Widespread adoption of hydrogen fuel is constrained by the cost and safety limits of high-pressure and cryogenic storage. Adsorption-based storage in Porous Carbon Materials (PCMs) is a promising alternative, yet its potential is unrealized due to the research time and cost of discovery. A Machine Learning (ML) approach was developed using five Decision Tree-based models on a 2,101datapoint PCM dataset to rapidly address the demands of this gap. CatBoost delivered the best performance (R2 = 0.9983, RMSE = 0.094, and MAE = 0.053), outperforming the Stacking Ensemble model (improving R2 by 0.1 %, RMSE by 13 %, and MAE by 15 %). Further, SHAP analysis confirmed pressure, temperature, SBET, and pore volumes as the key predictors, aligning with adsorption theory. This ML strategy serves as an efficient pre-screening tool for accelerating PCM discovery and reducing research cost and time for safe and cost-effective hydrogen storage with higher interpretability compared to previously developed tools. [Display omitted] •Five Decision Tree ML models were used to predict H2 uptake in PCMs.•Gradient Boosting models showed stronger regression and residual performance.•CatBoost gave the best results with R2 of 0.9983 and RMSE of 0.094.•SHAP analysis found SBET as the most influential morphological property.•A Stacking ensemble outperformed its individual constituent models.
AbstractList Widespread adoption of hydrogen fuel is constrained by the cost and safety limits of high-pressure and cryogenic storage. Adsorption-based storage in Porous Carbon Materials (PCMs) is a promising alternative, yet its potential is unrealized due to the research time and cost of discovery. A Machine Learning (ML) approach was developed using five Decision Tree-based models on a 2,101datapoint PCM dataset to rapidly address the demands of this gap. CatBoost delivered the best performance (R2 = 0.9983, RMSE = 0.094, and MAE = 0.053), outperforming the Stacking Ensemble model (improving R2 by 0.1 %, RMSE by 13 %, and MAE by 15 %). Further, SHAP analysis confirmed pressure, temperature, SBET, and pore volumes as the key predictors, aligning with adsorption theory. This ML strategy serves as an efficient pre-screening tool for accelerating PCM discovery and reducing research cost and time for safe and cost-effective hydrogen storage with higher interpretability compared to previously developed tools. [Display omitted] •Five Decision Tree ML models were used to predict H2 uptake in PCMs.•Gradient Boosting models showed stronger regression and residual performance.•CatBoost gave the best results with R2 of 0.9983 and RMSE of 0.094.•SHAP analysis found SBET as the most influential morphological property.•A Stacking ensemble outperformed its individual constituent models.
ArticleNumber 152704
Author Sunkara, Hemanth
R, Namitha
Acharya, Sushmitha
Siddiqui, Shabnam
Sainath, Krishnamurthy
Bhat A S, Shravani
Shekar, Selva Kumar
Author_xml – sequence: 1
  givenname: Hemanth
  orcidid: 0009-0004-4000-437X
  surname: Sunkara
  fullname: Sunkara, Hemanth
  email: hemanthsunkara.ch24@bmsce.ac.in
  organization: Department of Chemical Engineering, B.M.S. College of Engineering, Bengaluru, Karnataka, India, 560019
– sequence: 2
  givenname: Shravani
  orcidid: 0009-0003-5388-2449
  surname: Bhat A S
  fullname: Bhat A S, Shravani
  email: shravanibhat.ch24@bmsce.ac.in
  organization: Department of Chemical Engineering, B.M.S. College of Engineering, Bengaluru, Karnataka, India, 560019
– sequence: 3
  givenname: Namitha
  orcidid: 0009-0006-4591-8028
  surname: R
  fullname: R, Namitha
  email: namithar.ch24@bmsce.ac.in
  organization: Department of Chemical Engineering, B.M.S. College of Engineering, Bengaluru, Karnataka, India, 560019
– sequence: 4
  givenname: Sushmitha
  orcidid: 0009-0007-4352-6802
  surname: Acharya
  fullname: Acharya, Sushmitha
  email: sushmitha.ch22@bmsce.ac.in
  organization: Department of Chemical Engineering, B.M.S. College of Engineering, Bengaluru, Karnataka, India, 560019
– sequence: 5
  givenname: Selva Kumar
  orcidid: 0000-0002-3342-7161
  surname: Shekar
  fullname: Shekar, Selva Kumar
  email: selva.cse@bmsce.ac.in
  organization: Department of Computer Science and Engineering, B.M.S. College of Engineering, Bengaluru, Karnataka, India, 560019
– sequence: 6
  givenname: Krishnamurthy
  orcidid: 0000-0003-3910-9401
  surname: Sainath
  fullname: Sainath, Krishnamurthy
  email: sainath.che@bmsce.ac.in
  organization: Department of Chemical Engineering, B.M.S. College of Engineering, Bengaluru, Karnataka, India, 560019
– sequence: 7
  givenname: Shabnam
  orcidid: 0000-0002-2559-6088
  surname: Siddiqui
  fullname: Siddiqui, Shabnam
  email: shabnamsiddiqui.che@bmsce.ac.in
  organization: Department of Chemical Engineering, B.M.S. College of Engineering, Bengaluru, Karnataka, India, 560019
BookMark eNqFUEtOwzAQ9aJItMAVkC_QYiex47CiqihFqsQG1pbjTFqHxI5sF9HjcFNcFSR2rGY0M-8zb4Ym1llA6JaSBSWU33UL0-2PDVhYZCRjC8qykhQTNCU5J_OcVtUlmoXQEULTvJqir82x8W4HFh_GqN4Bjx4ao6NxFhuLR-fdIWCtfJ0Gg4rgjeoDhs-xV8ZCg-sjbkCbcAJED5CO9D5tcA_KW2N3eNnvnDdxP4R7vPZuOIETzQA2qh43KiocXRJL3Ek8qrr_6yJco4s2ScLNT71Cb-vH19Vmvn15el4tt3NNSx7ntGSC0dRmRIiaClXpnDUiF1oppkRelSyrKq4FVHnNoKB10fJCZGWrOWPA8yvEz7zauxA8tHJMJpU_SkrkKVzZyd9w5SlceQ43AR_OQEjuPgx4GbQBq9MHHnSUjTP_UXwDri-OlA
Cites_doi 10.1016/j.ijhydene.2011.05.181
10.1016/j.jallcom.2025.180709
10.1016/j.neucom.2020.07.061
10.3390/nano11071830
10.1039/C7EE02616A
10.1016/j.ijhydene.2019.07.023
10.1002/jps.2600741006
10.1039/c0ee00347f
10.1186/s12859-016-1236-x
10.1016/j.ijhydene.2020.03.004
10.1007/s10462-023-10591-4
10.1016/j.ijhydene.2008.11.010
10.1098/rsta.2010.0113
10.3390/en18112930
10.1038/35104634
10.1016/j.ceja.2021.100172
10.1016/j.ijhydene.2025.03.028
10.1016/j.carbon.2009.01.001
10.1016/j.ijhydene.2025.06.112
10.1016/j.carbon.2015.12.032
10.1016/j.artint.2021.103502
10.1038/nmeth.3854
10.1021/acssuschemeng.5b00351
10.1039/D4LF00215F
10.3390/app15020672
10.1023/A:1022627411411
10.1007/s10462-011-9272-4
10.1109/TCBB.2021.3089417
10.1038/s41467-017-01633-x
10.1186/s40537-020-00369-8
10.1002/wene.390
10.1002/9781118445112.stat08235
10.1007/s10994-006-6226-1
10.1177/00131644221117193
10.3390/en18153958
10.3389/frai.2023.1272506
10.1023/A:1010933404324
10.1038/s41586-018-0337-2
10.3390/en16207174
10.1016/j.est.2024.112914
10.1007/s10462-020-09896-5
10.1016/j.ijhydene.2024.12.131
10.3390/technologies9030052
10.1111/cts.70056
10.1039/c3ta10583k
10.1016/j.ijhydene.2014.05.134
10.1039/C9TA06308K
10.1016/j.acags.2024.100178
10.1016/j.carbon.2021.04.036
10.1038/s41598-020-73268-w
10.1016/j.ijhydene.2025.03.247
10.1371/journal.pbio.1002128
10.3390/axioms14060464
10.1016/j.ijhydene.2025.05.002
10.1016/j.ijhydene.2020.04.037
10.3390/app8040646
10.3389/fenvs.2021.689985
10.1016/j.scitotenv.2021.146708
10.1021/ja067149g
10.1016/j.ijhydene.2024.11.375
10.1016/j.ijhydene.2024.02.337
10.1016/j.jclepro.2021.129714
10.1016/j.carbon.2009.04.021
10.1038/s41529-024-00508-z
10.1016/j.micromeso.2006.12.033
10.1016/j.ijhydene.2024.03.223
10.1371/journal.pone.0224365
10.1016/j.asoc.2022.109924
10.1214/21-AIHP1240
10.1002/widm.1424
10.1016/j.ijhydene.2024.12.121
10.1016/j.cej.2019.122367
10.21037/atm.2016.03.36
10.1016/j.seppur.2023.123807
ContentType Journal Article
Copyright 2025 Hydrogen Energy Publications LLC
Copyright_xml – notice: 2025 Hydrogen Energy Publications LLC
DBID AAYXX
CITATION
DOI 10.1016/j.ijhydene.2025.152704
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
ExternalDocumentID 10_1016_j_ijhydene_2025_152704
S0360319925057076
GroupedDBID --K
--M
.~1
0R~
1B1
1~.
1~5
4.4
457
4G.
5GY
5VS
7-5
71M
8P~
9JN
AABNK
AABXZ
AAEDT
AAEDW
AAHCO
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AARJD
AARLI
AATTM
AAXKI
AAXUO
AAYWO
ABFNM
ABJNI
ABMAC
ACDAQ
ACGFS
ACLOT
ACRLP
ACVFH
ADBBV
ADCNI
ADECG
ADEZE
AEBSH
AEIPS
AEKER
AENEX
AEUPX
AEZYN
AFJKZ
AFPUW
AFRZQ
AFTJW
AFZHZ
AGHFR
AGUBO
AGYEJ
AHHHB
AHIDL
AIEXJ
AIGII
AIIUN
AIKHN
AITUG
AJSZI
AKBMS
AKRWK
AKYEP
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
ANKPU
APXCP
AXJTR
BELTK
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFKBS
EFLBG
EO8
EO9
EP2
EP3
F5P
FDB
FIRID
FLBIZ
FNPLU
FYGXN
G-Q
GBLVA
HZ~
IHE
J1W
JARJE
KOM
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
RNS
ROL
RPZ
SCC
SDF
SDG
SES
SEW
SPC
SPCBC
SSK
SSM
SSR
SSZ
T5K
TN5
XPP
ZMT
~G-
~HD
29J
9DU
AAQXK
AAYXX
ABWVN
ABXDB
ACNNM
ACRPL
ADMUD
ADNMO
AGQPQ
ASPBG
AVWKF
AZFZN
CITATION
EJD
FEDTE
FGOYB
G-2
HVGLF
LY6
M41
R2-
SAC
SCB
T9H
WUQ
ID FETCH-LOGICAL-c176t-1758511762088b18a9c35d838caa5a839752996c8e93b5e41b4f64827fc655e63
ISSN 0360-3199
IngestDate Thu Nov 27 01:06:28 EST 2025
Sat Nov 29 17:04:25 EST 2025
IsPeerReviewed true
IsScholarly true
Keywords SHAP
Adsorption
Porous carbon materials
Decision trees
Hydrogen
Machine learning
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c176t-1758511762088b18a9c35d838caa5a839752996c8e93b5e41b4f64827fc655e63
ORCID 0009-0004-4000-437X
0009-0003-5388-2449
0009-0007-4352-6802
0009-0006-4591-8028
0000-0003-3910-9401
0000-0002-2559-6088
0000-0002-3342-7161
ParticipantIDs crossref_primary_10_1016_j_ijhydene_2025_152704
elsevier_sciencedirect_doi_10_1016_j_ijhydene_2025_152704
PublicationCentury 2000
PublicationDate 2026-01-05
PublicationDateYYYYMMDD 2026-01-05
PublicationDate_xml – month: 01
  year: 2026
  text: 2026-01-05
  day: 05
PublicationDecade 2020
PublicationTitle International journal of hydrogen energy
PublicationYear 2026
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Cawley, Talbot (bib82) 2010; 11
Wang, Shahbeik, Moradi, Rafiee, Shafizadeh, Khoshnevisan (bib32) 2024; 97
Bergstra, Bengio (bib80) 2012; 13
Knight, Gillespie, Prosniewski, Stalla, Dohnke, Rash (bib7) 2020; 45
Cao, Liu, Wang, Yang, Zheng (bib21) 2025; 135
Banerjee, Ji, Xia, Ouyang, Del Rose, Hlova (bib33) 2025
Cortes, Vapnik (bib29) 1995; 20
Bentéjac, Csörgő, Martínez-Muñoz (bib62) 2021; 54
Dhami, Pasricha, Kaur, Sidhu (bib97) 2022
Angelov, Soares, Jiang, Arnold, Atkinson (bib31) 2021; 11
Khurana, Samulowitz, Turaga (bib76) 2018
Restrepo (bib2) 2021; 9
Sethia, Sayari (bib41) 2016; 99
Kotsiantis (bib50) 2013; 39
Fu, Mojiri, Wang, Zhao (bib15) 2025; 18
Li, Yan, Li, Qiu, Zhang (bib16) 2025; 35
Chen, Singh, Webley (bib44) 2007; 102
Scornet (bib58) 2023; 59
Denis DJ. Model selection in regression: statistical and scientific perspectives. Wiley StatsRef: Statistics Reference Online. p. 1-7.
Xia, Yang, Zhu (bib20) 2013; 1
Minami, Lennert-Cody (bib88) 2024
Kumar, Venkatasubramanian, Scheidegger, Friedler (bib98) 2020
Shi, Li, Li (bib59) 2018
Butler, Davies, Cartwright, Isayev, Walsh (bib96) 2018; 559
Zivic, Malisic, Grujovic, Stojanovic, Ivanovic (bib51) 2025; 48
Ponce‐Bobadilla, Schmitt, Maier, Mensing, Stodtmann (bib68) 2024; 17
Uddin, Lee, Rizvi, Hamada (bib75) 2018; 8
Cao, Bian, Chen, Zhang, Fu (bib24) 2025; 145
Geurts, Ernst, Wehenkel (bib55) 2006; 63
Hancock, Khoshgoftaar (bib63) 2020; 7
Ranjbaran, Recupero, Roy, Schneider (bib70) 2025; 15
Rahimi, Abbaspour-Fard, Rohani (bib27) 2021; 329
Li, Xiao, Dong, Zheng, Liu (bib49) 2019; 44
Mahmoud, Rowlandson, Fermin, Ting, Nayak (bib10) 2025
Friedman (bib56) 2001
Ghosh, Cabrera (bib57) 2021; 19
Tahmassebi, Smith (bib105) 2021
Huang, Marques-Silva (bib99) 2023
Weissgerber, Milic, Winham, Garovic (bib90) 2015; 13
Hwang, Kim, Seo, Jeong, Kim, Lim (bib12) 2021; 11
Jacobsen, Zscherpel, Perner (bib30) 1999
Murari, Rossi, Spolladore, Lungaroni, Gaudio, Gelfusa (bib93) 2023; 56
Antonini, Tanzola, Asiain, Ferracutti, Castro, Bjerg (bib69) 2024; 23
Kohavi (bib86) 1995
Zhou, Jiao (bib65) 2023; 83
Ahsan, Mahmud, Saha, Gupta, Siddique (bib73) 2021; 9
Wang, Huang, Tang, Miao, Wang (bib13) 2009; 34
Zhang (bib101) 2016; 4
Maulana Kusdhany, Lyth (bib25) 2021; 179
Chen, Liang, Kang, Fan, Fan, Zhou (bib19) 2025; 18
Giacomazzi, Troiani, Di Nardo, Calchetti, Cecere, Messina (bib6) 2023; 16
Yahia, Wjihi (bib8) 2020; 10
Lundberg, Lee (bib67) 2017; 30
Thanh, Dai, Rahimi (bib34) 2025; 1028
Bleviss (bib1) 2021; 10
Xiao, Dong, Long, Zheng, Lei, Zhang (bib38) 2014; 39
Elizabeth (bib84) 2010; 25
Aas, Jullum, Løland (bib94) 2021; 298
Prokhorenkova, Gusev, Vorobev, Dorogush, Gulin (bib52) 2018; 31
Gosiewska, Biecek (bib78) 2020
Jia, Sun, Zhang, Luo, Zhou, Lu (bib22) 2025; 119
Yamde, Lade, Bindwal, Tiwari, Birmod (bib23) 2025; 98
Blankenship, Balahmar, Mokaya (bib37) 2017; 8
Habib, Amin, Aljeddani (bib103) 2025; 14
Elyasi, Saha, Hameed, Mahon, Juodkazis, Salim (bib18) 2024; 62
Blankenship, Mokaya (bib40) 2017; 10
Breiman (bib54) 2001; 45
Weigang, Fierro, Zlotea, Aylon, Izquierdo, Latroche (bib9) 2011; 36
Tashie-Lewis, Nnabuife (bib17) 2021; 8
Zhang, Si, Hsieh (bib61) 2017
Vabalas, Gowen, Poliakoff, Casson (bib85) 2019; 14
Kang, Lee, Lee (bib39) 2009; 47
Raychaudhuri, Kumar, Bhanu (bib28) 2017
Bi, Bennett (bib104) 2003
John Lu (bib83) 2010
Wang, Gao, Hu, Chen (bib45) 2009; 47
Li, Jamieson, DeSalvo, Rostamizadeh, Talwalkar (bib81) 2018; 18
Ke, Meng, Finley, Wang, Chen, Ma (bib60) 2017; 30
Cao, Stojkovic, Obradovic (bib74) 2016; 17
Nambiar, S, S (bib91) 2023; 6
Elyasi, Hameed, Mahon, Juodkazis, Keshavarz, Iglauer (bib36) 2025; 119
De Amorim, Cavalcanti, Cruz (bib72) 2023; 133
Chen, Guestrin (bib53) 2016
Ribeiro, Umezaki, Chiquetto, Santos, Machado, Miranda (bib3) 2021; 781
Yang, Xia, Mokaya (bib11) 2007; 129
Züttel, Remhof, Borgschulte, Friedrichs (bib5) 2010; 368
Gholijani Farahani, Zarrabi, Ghazanfari (bib64) 2025
Yang, Shami (bib79) 2020; 415
Altman, Krzywinski (bib102) 2016; 13
Balahmar, Mokaya (bib42) 2019; 7
Sangchoom, Mokaya (bib46) 2015; 3
Wang, Lu (bib66) 2024; 8
Heaton (bib87) 2018; vol. 19
Li, Dong, Wang, Gong (bib4) 2024; 96
Mukaka (bib89) 2012; 24
Lundberg, Lee (bib71) 2017
Jeng, Martin (bib100) 1985; 74
Davoodi, Vo Thanh, Wood, Mehrad, Al-Shargabi, Rukavishnikov (bib26) 2023; 316
Zheng, Casari (bib77) 2018
Schlapbach, Züttel (bib95) 2001; 414
Attia, Jung, Park, Cho, Oh (bib47) 2020; 45
Sevilla, Fuertes, Mokaya (bib43) 2011; 4
Bhaskar, Muduli, Kale (bib35) 2025; 98
Osman, Nasr, Eltaweil, Hosny, Farghali, Al-Fatesh (bib14) 2024; 67
Attia, Jung, Park, Jang, Lee, Oh (bib48) 2020; 379
Bhaskar (10.1016/j.ijhydene.2025.152704_bib35) 2025; 98
Khurana (10.1016/j.ijhydene.2025.152704_bib76) 2018
Altman (10.1016/j.ijhydene.2025.152704_bib102) 2016; 13
Zhou (10.1016/j.ijhydene.2025.152704_bib65) 2023; 83
Bentéjac (10.1016/j.ijhydene.2025.152704_bib62) 2021; 54
Aas (10.1016/j.ijhydene.2025.152704_bib94) 2021; 298
Wang (10.1016/j.ijhydene.2025.152704_bib45) 2009; 47
Xia (10.1016/j.ijhydene.2025.152704_bib20) 2013; 1
Tashie-Lewis (10.1016/j.ijhydene.2025.152704_bib17) 2021; 8
Zhang (10.1016/j.ijhydene.2025.152704_bib101) 2016; 4
10.1016/j.ijhydene.2025.152704_bib92
Kohavi (10.1016/j.ijhydene.2025.152704_bib86) 1995
Rahimi (10.1016/j.ijhydene.2025.152704_bib27) 2021; 329
Gosiewska (10.1016/j.ijhydene.2025.152704_bib78) 2020
Li (10.1016/j.ijhydene.2025.152704_bib4) 2024; 96
Schlapbach (10.1016/j.ijhydene.2025.152704_bib95) 2001; 414
Hancock (10.1016/j.ijhydene.2025.152704_bib63) 2020; 7
Thanh (10.1016/j.ijhydene.2025.152704_bib34) 2025; 1028
Cawley (10.1016/j.ijhydene.2025.152704_bib82) 2010; 11
Blankenship (10.1016/j.ijhydene.2025.152704_bib37) 2017; 8
Zheng (10.1016/j.ijhydene.2025.152704_bib77) 2018
Bi (10.1016/j.ijhydene.2025.152704_bib104) 2003
Wang (10.1016/j.ijhydene.2025.152704_bib13) 2009; 34
Weissgerber (10.1016/j.ijhydene.2025.152704_bib90) 2015; 13
Elizabeth (10.1016/j.ijhydene.2025.152704_bib84) 2010; 25
Chen (10.1016/j.ijhydene.2025.152704_bib19) 2025; 18
Habib (10.1016/j.ijhydene.2025.152704_bib103) 2025; 14
Li (10.1016/j.ijhydene.2025.152704_bib16) 2025; 35
Kotsiantis (10.1016/j.ijhydene.2025.152704_bib50) 2013; 39
Wang (10.1016/j.ijhydene.2025.152704_bib32) 2024; 97
Osman (10.1016/j.ijhydene.2025.152704_bib14) 2024; 67
Banerjee (10.1016/j.ijhydene.2025.152704_bib33) 2025
Attia (10.1016/j.ijhydene.2025.152704_bib48) 2020; 379
Davoodi (10.1016/j.ijhydene.2025.152704_bib26) 2023; 316
Yamde (10.1016/j.ijhydene.2025.152704_bib23) 2025; 98
Bergstra (10.1016/j.ijhydene.2025.152704_bib80) 2012; 13
Breiman (10.1016/j.ijhydene.2025.152704_bib54) 2001; 45
Shi (10.1016/j.ijhydene.2025.152704_bib59) 2018
Ahsan (10.1016/j.ijhydene.2025.152704_bib73) 2021; 9
Bleviss (10.1016/j.ijhydene.2025.152704_bib1) 2021; 10
Giacomazzi (10.1016/j.ijhydene.2025.152704_bib6) 2023; 16
Dhami (10.1016/j.ijhydene.2025.152704_bib97) 2022
Heaton (10.1016/j.ijhydene.2025.152704_bib87) 2018; vol. 19
Restrepo (10.1016/j.ijhydene.2025.152704_bib2) 2021; 9
Li (10.1016/j.ijhydene.2025.152704_bib81) 2018; 18
Gholijani Farahani (10.1016/j.ijhydene.2025.152704_bib64) 2025
Mahmoud (10.1016/j.ijhydene.2025.152704_bib10) 2025
Mukaka (10.1016/j.ijhydene.2025.152704_bib89) 2012; 24
Züttel (10.1016/j.ijhydene.2025.152704_bib5) 2010; 368
Vabalas (10.1016/j.ijhydene.2025.152704_bib85) 2019; 14
Huang (10.1016/j.ijhydene.2025.152704_bib99) 2023
Blankenship (10.1016/j.ijhydene.2025.152704_bib40) 2017; 10
Cortes (10.1016/j.ijhydene.2025.152704_bib29) 1995; 20
Ke (10.1016/j.ijhydene.2025.152704_bib60) 2017; 30
Elyasi (10.1016/j.ijhydene.2025.152704_bib18) 2024; 62
Maulana Kusdhany (10.1016/j.ijhydene.2025.152704_bib25) 2021; 179
Prokhorenkova (10.1016/j.ijhydene.2025.152704_bib52) 2018; 31
Murari (10.1016/j.ijhydene.2025.152704_bib93) 2023; 56
Cao (10.1016/j.ijhydene.2025.152704_bib24) 2025; 145
Lundberg (10.1016/j.ijhydene.2025.152704_bib71) 2017
Yang (10.1016/j.ijhydene.2025.152704_bib79) 2020; 415
Ponce‐Bobadilla (10.1016/j.ijhydene.2025.152704_bib68) 2024; 17
Raychaudhuri (10.1016/j.ijhydene.2025.152704_bib28) 2017
Xiao (10.1016/j.ijhydene.2025.152704_bib38) 2014; 39
Li (10.1016/j.ijhydene.2025.152704_bib49) 2019; 44
Wang (10.1016/j.ijhydene.2025.152704_bib66) 2024; 8
Attia (10.1016/j.ijhydene.2025.152704_bib47) 2020; 45
Minami (10.1016/j.ijhydene.2025.152704_bib88) 2024
Scornet (10.1016/j.ijhydene.2025.152704_bib58) 2023; 59
Ghosh (10.1016/j.ijhydene.2025.152704_bib57) 2021; 19
De Amorim (10.1016/j.ijhydene.2025.152704_bib72) 2023; 133
Ranjbaran (10.1016/j.ijhydene.2025.152704_bib70) 2025; 15
Chen (10.1016/j.ijhydene.2025.152704_bib53) 2016
Yang (10.1016/j.ijhydene.2025.152704_bib11) 2007; 129
Nambiar (10.1016/j.ijhydene.2025.152704_bib91) 2023; 6
Uddin (10.1016/j.ijhydene.2025.152704_bib75) 2018; 8
Friedman (10.1016/j.ijhydene.2025.152704_bib56) 2001
Kang (10.1016/j.ijhydene.2025.152704_bib39) 2009; 47
Zivic (10.1016/j.ijhydene.2025.152704_bib51) 2025; 48
Sethia (10.1016/j.ijhydene.2025.152704_bib41) 2016; 99
Sevilla (10.1016/j.ijhydene.2025.152704_bib43) 2011; 4
Ribeiro (10.1016/j.ijhydene.2025.152704_bib3) 2021; 781
Angelov (10.1016/j.ijhydene.2025.152704_bib31) 2021; 11
Cao (10.1016/j.ijhydene.2025.152704_bib21) 2025; 135
Jacobsen (10.1016/j.ijhydene.2025.152704_bib30) 1999
Tahmassebi (10.1016/j.ijhydene.2025.152704_bib105) 2021
Jia (10.1016/j.ijhydene.2025.152704_bib22) 2025; 119
Balahmar (10.1016/j.ijhydene.2025.152704_bib42) 2019; 7
John Lu (10.1016/j.ijhydene.2025.152704_bib83)
Fu (10.1016/j.ijhydene.2025.152704_bib15) 2025; 18
Hwang (10.1016/j.ijhydene.2025.152704_bib12) 2021; 11
Kumar (10.1016/j.ijhydene.2025.152704_bib98) 2020
Elyasi (10.1016/j.ijhydene.2025.152704_bib36) 2025; 119
Sangchoom (10.1016/j.ijhydene.2025.152704_bib46) 2015; 3
Weigang (10.1016/j.ijhydene.2025.152704_bib9) 2011; 36
Zhang (10.1016/j.ijhydene.2025.152704_bib61) 2017
Jeng (10.1016/j.ijhydene.2025.152704_bib100) 1985; 74
Yahia (10.1016/j.ijhydene.2025.152704_bib8) 2020; 10
Cao (10.1016/j.ijhydene.2025.152704_bib74) 2016; 17
Antonini (10.1016/j.ijhydene.2025.152704_bib69) 2024; 23
Butler (10.1016/j.ijhydene.2025.152704_bib96) 2018; 559
Knight (10.1016/j.ijhydene.2025.152704_bib7) 2020; 45
Geurts (10.1016/j.ijhydene.2025.152704_bib55) 2006; 63
Lundberg (10.1016/j.ijhydene.2025.152704_bib67) 2017; 30
Chen (10.1016/j.ijhydene.2025.152704_bib44) 2007; 102
References_xml – volume: 19
  start-page: 2817
  year: 2021
  end-page: 2828
  ident: bib57
  article-title: Enriched random forest for high dimensional genomic data
  publication-title: IEEE ACM Trans Comput Biol Bioinf
– start-page: 165
  year: 2022
  end-page: 174
  ident: bib97
  article-title: A review of machine learning applications in materials science
– volume: 67
  start-page: 1270
  year: 2024
  end-page: 1294
  ident: bib14
  article-title: Advances in hydrogen storage materials: harnessing innovative technology, from machine learning to computational chemistry, for energy storage solutions
  publication-title: Int J Hydrogen Energy
– volume: 135
  start-page: 525
  year: 2025
  end-page: 536
  ident: bib21
  article-title: Prediction of hydrogen storage in IL/COF composites based on high-throughput computational screening and machine learning
  publication-title: Int J Hydrogen Energy
– volume: 8
  year: 2021
  ident: bib17
  article-title: Hydrogen production, distribution, storage and power conversion in a hydrogen economy - a technology review
  publication-title: Chem Eng J Adv
– volume: 83
  start-page: 831
  year: 2023
  end-page: 854
  ident: bib65
  article-title: Exploration of the stacking ensemble machine learning algorithm for cheating detection in large-scale assessment
  publication-title: Educ Psychol Meas
– volume: 129
  start-page: 1673
  year: 2007
  end-page: 1679
  ident: bib11
  article-title: Enhanced hydrogen storage capacity of high surface area zeolite-like carbon materials
  publication-title: J Am Chem Soc
– volume: 99
  start-page: 289
  year: 2016
  end-page: 294
  ident: bib41
  article-title: Activated carbon with optimum pore size distribution for hydrogen storage
  publication-title: Carbon
– volume: 44
  start-page: 23210
  year: 2019
  end-page: 23215
  ident: bib49
  article-title: Polyacrylonitrile-based highly porous carbon materials for exceptional hydrogen storage
  publication-title: Int J Hydrogen Energy
– volume: 179
  start-page: 190
  year: 2021
  end-page: 201
  ident: bib25
  article-title: New insights into hydrogen uptake on porous carbon materials via explainable machine learning
  publication-title: Carbon
– start-page: 1189
  year: 2001
  end-page: 1232
  ident: bib56
  article-title: Greedy function approximation: a gradient boosting machine
  publication-title: Ann Stat
– volume: 8
  start-page: 87
  year: 2024
  ident: bib66
  article-title: A novel stacking ensemble learner for predicting residual strength of corroded pipelines
  publication-title: npj Mater Degrad
– volume: 13
  year: 2015
  ident: bib90
  article-title: Beyond bar and line graphs: time for a new data presentation paradigm
  publication-title: PLoS Biol
– volume: 45
  start-page: 15541
  year: 2020
  end-page: 15552
  ident: bib7
  article-title: Determination of the enthalpy of adsorption of hydrogen in activated carbon at room temperature
  publication-title: Int J Hydrogen Energy
– volume: 54
  start-page: 1937
  year: 2021
  end-page: 1967
  ident: bib62
  article-title: A comparative analysis of gradient boosting algorithms
  publication-title: Artif Intell Rev
– volume: 329
  year: 2021
  ident: bib27
  article-title: Machine learning approaches to rediscovery and optimization of hydrogen storage on porous bio-derived carbon
  publication-title: J Clean Prod
– volume: 47
  start-page: 2259
  year: 2009
  end-page: 2268
  ident: bib45
  article-title: High performance of nanoporous carbon in cryogenic hydrogen storage and electrochemical capacitance
  publication-title: Carbon
– volume: 414
  start-page: 353
  year: 2001
  end-page: 358
  ident: bib95
  article-title: Hydrogen-storage materials for Mobile applications
  publication-title: Nature
– volume: 7
  start-page: 94
  year: 2020
  ident: bib63
  article-title: CatBoost for big data: an interdisciplinary review
  publication-title: Journal of big data
– volume: 10
  year: 2021
  ident: bib1
  article-title: Transportation is critical to reducing greenhouse gas emissions in the United States
  publication-title: WIREs Energy and Environment
– volume: 368
  start-page: 3329
  year: 2010
  end-page: 3342
  ident: bib5
  article-title: Hydrogen: the future energy carrier
  publication-title: Philos Trans R Soc A Math Phys Eng Sci
– start-page: 43
  year: 2003
  end-page: 50
  ident: bib104
  article-title: Regression error characteristic curves
  publication-title: Proceedings of the 20th international conference on machine learning
– volume: 4
  start-page: 195
  year: 2016
  ident: bib101
  article-title: Residuals and regression diagnostics: focusing on logistic regression
  publication-title: Ann Transl Med
– volume: 35
  year: 2025
  ident: bib16
  article-title: Porous carbon materials: from traditional synthesis, machine learning-assisted design, to their applications in advanced energy storage and conversion
  publication-title: Adv Funct Mater
– year: 2025
  ident: bib33
  article-title: Machine learning driven search of hydrogen storage materials
  publication-title: arXiv preprint arXiv:250304027
– volume: vol. 19
  start-page: 305
  year: 2018
  end-page: 307
  ident: bib87
  publication-title: Ian goodfellow, yoshua bengio, and aaron courville: deep learning
– volume: 98
  start-page: 1212
  year: 2025
  end-page: 1225
  ident: bib35
  article-title: Prediction of hydrogen storage in metal hydrides and complex hydrides: a supervised machine learning approach
  publication-title: Int J Hydrogen Energy
– volume: 133
  year: 2023
  ident: bib72
  article-title: The choice of scaling technique matters for classification performance
  publication-title: Appl Soft Comput
– volume: 16
  start-page: 7174
  year: 2023
  ident: bib6
  article-title: Hydrogen combustion: features and barriers to its exploitation in the energy transition
  publication-title: Energies
– volume: 1028
  year: 2025
  ident: bib34
  article-title: Data-driven explainable machine learning approaches for predicting hydrogen adsorption in porous crystalline materials
  publication-title: J Alloys Compd
– start-page: 785
  year: 2016
  end-page: 794
  ident: bib53
  article-title: XGBoost: a scalable tree boosting system
  publication-title: Journal
– volume: 316
  year: 2023
  ident: bib26
  article-title: Machine-learning models to predict hydrogen uptake of porous carbon materials from influential variables
  publication-title: Separation and Purification Technology
– volume: 62
  start-page: 272
  year: 2024
  end-page: 306
  ident: bib18
  article-title: Emerging trends in biomass-derived porous carbon materials for hydrogen storage
  publication-title: Int J Hydrogen Energy
– volume: 34
  start-page: 1084
  year: 2009
  end-page: 1096
  ident: bib13
  article-title: Numerical study of the effect of hydrogen addition on methane–air mixtures combustion
  publication-title: Int J Hydrogen Energy
– volume: 74
  start-page: 1053
  year: 1985
  end-page: 1057
  ident: bib100
  article-title: Residuals in multiple regression analysis
  publication-title: J Pharmaceut Sci
– start-page: 144
  year: 1999
  end-page: 158
  ident: bib30
  article-title: A comparison between neural networks and decision trees
  publication-title: Machine learning and data mining in pattern recognition
– volume: 10
  start-page: 2552
  year: 2017
  end-page: 2562
  ident: bib40
  article-title: Cigarette butt-derived carbons have ultra-high surface area and unprecedented hydrogen storage capacity
  publication-title: Energy Environ Sci
– volume: 20
  start-page: 273
  year: 1995
  end-page: 297
  ident: bib29
  article-title: Support-vector networks
  publication-title: Mach Learn
– volume: 30
  year: 2017
  ident: bib60
  article-title: Lightgbm: a highly efficient gradient boosting decision tree
  publication-title: Adv Neural Inf Process Syst
– volume: 11
  start-page: 2079
  year: 2010
  end-page: 2107
  ident: bib82
  article-title: On over-fitting in model selection and subsequent selection bias in performance evaluation
  publication-title: J Mach Learn Res
– volume: 56
  start-page: 2825
  year: 2023
  end-page: 2859
  ident: bib93
  article-title: A practical utility-based but objective approach to model selection for regression in scientific applications
  publication-title: Artif Intell Rev
– volume: 18
  start-page: 1
  year: 2018
  end-page: 52
  ident: bib81
  article-title: Hyperband: a novel bandit-based approach to hyperparameter optimization
  publication-title: J Mach Learn Res
– year: 2018
  ident: bib59
  article-title: Gradient boosting with piece-wise linear regression trees
  publication-title: arXiv preprint arXiv:180205640
– volume: 23
  year: 2024
  ident: bib69
  article-title: Machine learning model interpretability using SHAP values: application to igneous rock classification task
  publication-title: Applied Computing and Geosciences
– year: 2020
  ident: bib78
  article-title: Lifting interpretability-performance trade-off via automated feature engineering
  publication-title: arXiv preprint arXiv:200204267
– volume: 781
  year: 2021
  ident: bib3
  article-title: Impact of different transportation planning scenarios on air pollutants, greenhouse gases and heat emission abatement
  publication-title: Sci Total Environ
– start-page: 5491
  year: 2020
  end-page: 5500
  ident: bib98
  article-title: Problems with shapley-value-based explanations as feature importance measures
  publication-title: International conference on machine learning
– year: 2018
  ident: bib76
  article-title: Feature engineering for predictive modeling using reinforcement learning
  publication-title: Proceedings of the AAAI conference on artificial intelligence
– volume: 59
  year: 2023
  ident: bib58
  article-title: Trees, forests, and impurity-based variable importance in regression
  publication-title: Annales de l'Institut Henri Poincaré, Probabilités et Statistiques
– volume: 47
  start-page: 1171
  year: 2009
  end-page: 1180
  ident: bib39
  article-title: Hydrogen adsorption on nitrogen-doped carbon xerogels
  publication-title: Carbon
– volume: 36
  start-page: 11746
  year: 2011
  end-page: 11751
  ident: bib9
  article-title: Optimization of activated carbons for hydrogen storage
  publication-title: Int J Hydrogen Energy
– volume: 10
  year: 2020
  ident: bib8
  article-title: Study of the hydrogen physisorption on adsorbents based on activated carbon by means of statistical physics formalism: modeling analysis and thermodynamics investigation
  publication-title: Sci Rep
– volume: 15
  start-page: 672
  year: 2025
  ident: bib70
  article-title: C-SHAP: a hybrid method for fast and efficient interpretability
  publication-title: Applied Sciences
– volume: 8
  start-page: 646
  year: 2018
  ident: bib75
  article-title: Proposing enhanced feature engineering and a selection model for machine learning processes
  publication-title: Applied Sciences
– volume: 31
  year: 2018
  ident: bib52
  article-title: CatBoost: unbiased boosting with categorical features
  publication-title: Adv Neural Inf Process Syst
– volume: 4
  start-page: 1400
  year: 2011
  end-page: 1410
  ident: bib43
  article-title: High density hydrogen storage in superactivated carbons from hydrothermally carbonized renewable organic materials
  publication-title: Energy Environ Sci
– volume: 379
  year: 2020
  ident: bib48
  article-title: Flexible nanoporous activated carbon cloth for achieving high H2, CH4, and CO2 storage capacities and selective CO2/CH4 separation
  publication-title: Chem Eng J
– volume: 45
  start-page: 32797
  year: 2020
  end-page: 32807
  ident: bib47
  article-title: Facile synthesis of hybrid porous composites and its porous carbon for enhanced H2 and CH4 storage
  publication-title: Int J Hydrogen Energy
– volume: 119
  start-page: 45
  year: 2025
  end-page: 55
  ident: bib22
  article-title: Machine learning descriptor-assisted exploration of metal-modified graphene hydrogen storage materials
  publication-title: Int J Hydrogen Energy
– volume: 11
  year: 2021
  ident: bib31
  article-title: Explainable artificial intelligence: an analytical review
  publication-title: WIREs Data Mining and Knowledge Discovery
– volume: 7
  start-page: 17466
  year: 2019
  end-page: 17479
  ident: bib42
  article-title: Pre-mixed precursors for modulating the porosity of carbons for enhanced hydrogen storage: towards predicting the activation behaviour of carbonaceous matter
  publication-title: J Mater Chem A
– volume: 24
  start-page: 69
  year: 2012
  end-page: 71
  ident: bib89
  article-title: A guide to appropriate use of correlation coefficient in medical research
  publication-title: Malawi Med J
– volume: 17
  year: 2024
  ident: bib68
  article-title: Practical guide to SHAP analysis: explaining supervised machine learning model predictions in drug development
  publication-title: Clinical and translational science
– volume: 45
  start-page: 5
  year: 2001
  end-page: 32
  ident: bib54
  article-title: Random forests
  publication-title: Mach Learn
– year: 2021
  ident: bib105
  article-title: SlickML: Slick machine learning in python. 0.2.0 ed
– year: 2024
  ident: bib88
  article-title: Regression tree and clustering for distributions, and homogeneous structure of population characteristics
  publication-title: J Agric Biol Environ Stat
– volume: 97
  year: 2024
  ident: bib32
  article-title: Predictive modeling for hydrogen storage in functionalized carbonaceous nanomaterials using machine learning
  publication-title: J Energy Storage
– reference: Denis DJ. Model selection in regression: statistical and scientific perspectives. Wiley StatsRef: Statistics Reference Online. p. 1-7.
– volume: 145
  start-page: 401
  year: 2025
  end-page: 411
  ident: bib24
  article-title: Predicting hydrogen storage in metal-organic frameworks using a novel hybrid machine learning model
  publication-title: Int J Hydrogen Energy
– volume: 119
  start-page: 260
  year: 2025
  end-page: 270
  ident: bib36
  article-title: Analysis of pistachio shell-derived activated porous carbon materials for hydrogen adsorption
  publication-title: Int J Hydrogen Energy
– volume: 18
  start-page: 3958
  year: 2025
  ident: bib15
  article-title: Hydrogen energy storage via carbon-based materials: from traditional sorbents to emerging architecture engineering and AI-Driven optimization
  publication-title: Energies
– volume: 63
  start-page: 3
  year: 2006
  end-page: 42
  ident: bib55
  article-title: Extremely randomized trees
  publication-title: Mach Learn
– volume: 9
  year: 2021
  ident: bib2
  article-title: Nitrogen dioxide, greenhouse gas emissions and transportation in urban areas: lessons from the Covid-19 pandemic
  publication-title: Front Environ Sci
– year: 2018
  ident: bib77
  article-title: Feature engineering for machine learning: principles and techniques for data scientists
– volume: 3
  start-page: 1658
  year: 2015
  end-page: 1667
  ident: bib46
  article-title: Valorization of lignin waste: carbons from hydrothermal carbonization of renewable lignin as superior sorbents for CO2 and hydrogen storage
  publication-title: ACS Sustainable Chem Eng
– volume: 6
  year: 2023
  ident: bib91
  article-title: Model-agnostic explainable artificial intelligence tools for severity prediction and symptom analysis on Indian COVID-19 data
  publication-title: Frontiers in Artificial Intelligence
– volume: 1
  year: 2013
  ident: bib20
  article-title: Porous carbon-based materials for hydrogen storage: advancement and challenges
  publication-title: J Mater Chem A
– volume: 13
  start-page: 281
  year: 2012
  end-page: 305
  ident: bib80
  article-title: Random search for hyper-parameter optimization
  publication-title: J Mach Learn Res
– year: 2017
  ident: bib71
  article-title: Consistent feature attribution for tree ensembles
  publication-title: arXiv preprint arXiv:170606060
– start-page: 1137
  year: 1995
  end-page: 1145
  ident: bib86
  article-title: A study of cross-validation and bootstrap for accuracy estimation and model selection
– volume: 102
  start-page: 159
  year: 2007
  end-page: 170
  ident: bib44
  article-title: Synthesis, characterization and hydrogen storage properties of microporous carbons templated by cation exchanged forms of zeolite Y with propylene and butylene as carbon precursors
  publication-title: Microporous Mesoporous Mater
– volume: 39
  start-page: 11661
  year: 2014
  end-page: 11667
  ident: bib38
  article-title: Melaleuca bark based porous carbons for hydrogen storage
  publication-title: Int J Hydrogen Energy
– volume: 559
  start-page: 547
  year: 2018
  end-page: 555
  ident: bib96
  article-title: Machine learning for molecular and materials science
  publication-title: Nature
– volume: 415
  start-page: 295
  year: 2020
  end-page: 316
  ident: bib79
  article-title: On hyperparameter optimization of machine learning algorithms: theory and practice
  publication-title: Neurocomputing
– volume: 14
  year: 2019
  ident: bib85
  article-title: Machine learning algorithm validation with a limited sample size
  publication-title: PLoS One
– year: 2017
  ident: bib61
  article-title: GPU-Acceleration for large-scale tree boosting
  publication-title: arXiv preprint arXiv:170608359
– volume: 30
  year: 2017
  ident: bib67
  article-title: A unified approach to interpreting model predictions
  publication-title: Adv Neural Inf Process Syst
– year: 2010
  ident: bib83
  article-title: The elements of statistical learning: data mining, inference, and prediction
– year: 2025
  ident: bib10
  article-title: Porous carbons: a class of nanomaterials for efficient adsorption-based hydrogen storage
  publication-title: RSC Applied Interfaces
– volume: 17
  start-page: 359
  year: 2016
  ident: bib74
  article-title: A robust data scaling algorithm to improve classification accuracies in biomedical data
  publication-title: BMC Bioinf
– year: 2023
  ident: bib99
  article-title: The inadequacy of shapley values for explainability
  publication-title: arXiv preprint arXiv:230208160
– volume: 298
  year: 2021
  ident: bib94
  article-title: Explaining individual predictions when features are dependent: more accurate approximations to shapley values
  publication-title: Artif Intell
– start-page: 13
  year: 2017
  end-page: 21
  ident: bib28
  article-title: A comparative study and performance analysis of classification techniques: support vector machine, neural networks and decision trees
  publication-title: Advances in computing and data sciences
– volume: 8
  start-page: 1545
  year: 2017
  ident: bib37
  article-title: Oxygen-rich microporous carbons with exceptional hydrogen storage capacity
  publication-title: Nat Commun
– volume: 11
  year: 2021
  ident: bib12
  article-title: The enhanced hydrogen storage capacity of carbon fibers: the effect of hollow porous structure and surface modification
  publication-title: Nanomaterials
– volume: 39
  start-page: 261
  year: 2013
  end-page: 283
  ident: bib50
  article-title: Decision trees: a recent overview
  publication-title: Artif Intell Rev
– volume: 96
  start-page: 680
  year: 2024
  end-page: 691
  ident: bib4
  article-title: Study on the influence factors of gravimetric hydrogen storage density of type III cryo-compressed hydrogen storage vessel
  publication-title: Int J Hydrogen Energy
– volume: 14
  start-page: 464
  year: 2025
  ident: bib103
  article-title: Influence analysis in the lognormal regression model with fitted and quantile residuals
  publication-title: Axioms
– year: 2025
  ident: bib64
  article-title: A report on CatBoost: unbiased boosting with categorical features
– volume: 9
  start-page: 52
  year: 2021
  ident: bib73
  article-title: Effect of data scaling methods on machine learning algorithms and model performance
  publication-title: Technologies
– volume: 13
  start-page: 385
  year: 2016
  end-page: 386
  ident: bib102
  article-title: Regression diagnostics
  publication-title: Nat Methods
– volume: 25
  start-page: 1
  year: 2010
  end-page: 21
  ident: bib84
  article-title: Matching methods for causal inference: a review and a look forward
  publication-title: Stat Sci
– volume: 98
  start-page: 1131
  year: 2025
  end-page: 1154
  ident: bib23
  article-title: Machine learning approaches for the prediction of hydrogen uptake in metal-organic-frameworks: a comprehensive review
  publication-title: Int J Hydrogen Energy
– volume: 48
  year: 2025
  ident: bib51
  article-title: Materials informatics: a review of AI and machine learning tools, platforms, data repositories, and applications to architectured porous materials
  publication-title: Mater Today Commun
– volume: 18
  start-page: 2930
  year: 2025
  ident: bib19
  article-title: Review of hydrogen storage in solid-state materials
  publication-title: Energies
– volume: 36
  start-page: 11746
  year: 2011
  ident: 10.1016/j.ijhydene.2025.152704_bib9
  article-title: Optimization of activated carbons for hydrogen storage
  publication-title: Int J Hydrogen Energy
  doi: 10.1016/j.ijhydene.2011.05.181
– volume: 1028
  year: 2025
  ident: 10.1016/j.ijhydene.2025.152704_bib34
  article-title: Data-driven explainable machine learning approaches for predicting hydrogen adsorption in porous crystalline materials
  publication-title: J Alloys Compd
  doi: 10.1016/j.jallcom.2025.180709
– volume: 415
  start-page: 295
  year: 2020
  ident: 10.1016/j.ijhydene.2025.152704_bib79
  article-title: On hyperparameter optimization of machine learning algorithms: theory and practice
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2020.07.061
– volume: 11
  year: 2021
  ident: 10.1016/j.ijhydene.2025.152704_bib12
  article-title: The enhanced hydrogen storage capacity of carbon fibers: the effect of hollow porous structure and surface modification
  publication-title: Nanomaterials
  doi: 10.3390/nano11071830
– volume: 10
  start-page: 2552
  year: 2017
  ident: 10.1016/j.ijhydene.2025.152704_bib40
  article-title: Cigarette butt-derived carbons have ultra-high surface area and unprecedented hydrogen storage capacity
  publication-title: Energy Environ Sci
  doi: 10.1039/C7EE02616A
– volume: 44
  start-page: 23210
  year: 2019
  ident: 10.1016/j.ijhydene.2025.152704_bib49
  article-title: Polyacrylonitrile-based highly porous carbon materials for exceptional hydrogen storage
  publication-title: Int J Hydrogen Energy
  doi: 10.1016/j.ijhydene.2019.07.023
– volume: 74
  start-page: 1053
  year: 1985
  ident: 10.1016/j.ijhydene.2025.152704_bib100
  article-title: Residuals in multiple regression analysis
  publication-title: J Pharmaceut Sci
  doi: 10.1002/jps.2600741006
– volume: 4
  start-page: 1400
  year: 2011
  ident: 10.1016/j.ijhydene.2025.152704_bib43
  article-title: High density hydrogen storage in superactivated carbons from hydrothermally carbonized renewable organic materials
  publication-title: Energy Environ Sci
  doi: 10.1039/c0ee00347f
– volume: 17
  start-page: 359
  year: 2016
  ident: 10.1016/j.ijhydene.2025.152704_bib74
  article-title: A robust data scaling algorithm to improve classification accuracies in biomedical data
  publication-title: BMC Bioinf
  doi: 10.1186/s12859-016-1236-x
– volume: 45
  start-page: 32797
  year: 2020
  ident: 10.1016/j.ijhydene.2025.152704_bib47
  article-title: Facile synthesis of hybrid porous composites and its porous carbon for enhanced H2 and CH4 storage
  publication-title: Int J Hydrogen Energy
  doi: 10.1016/j.ijhydene.2020.03.004
– volume: 56
  start-page: 2825
  year: 2023
  ident: 10.1016/j.ijhydene.2025.152704_bib93
  article-title: A practical utility-based but objective approach to model selection for regression in scientific applications
  publication-title: Artif Intell Rev
  doi: 10.1007/s10462-023-10591-4
– volume: 34
  start-page: 1084
  year: 2009
  ident: 10.1016/j.ijhydene.2025.152704_bib13
  article-title: Numerical study of the effect of hydrogen addition on methane–air mixtures combustion
  publication-title: Int J Hydrogen Energy
  doi: 10.1016/j.ijhydene.2008.11.010
– volume: 368
  start-page: 3329
  year: 2010
  ident: 10.1016/j.ijhydene.2025.152704_bib5
  article-title: Hydrogen: the future energy carrier
  publication-title: Philos Trans R Soc A Math Phys Eng Sci
  doi: 10.1098/rsta.2010.0113
– volume: 18
  start-page: 2930
  year: 2025
  ident: 10.1016/j.ijhydene.2025.152704_bib19
  article-title: Review of hydrogen storage in solid-state materials
  publication-title: Energies
  doi: 10.3390/en18112930
– volume: 30
  year: 2017
  ident: 10.1016/j.ijhydene.2025.152704_bib67
  article-title: A unified approach to interpreting model predictions
  publication-title: Adv Neural Inf Process Syst
– volume: 48
  year: 2025
  ident: 10.1016/j.ijhydene.2025.152704_bib51
  article-title: Materials informatics: a review of AI and machine learning tools, platforms, data repositories, and applications to architectured porous materials
  publication-title: Mater Today Commun
– volume: 25
  start-page: 1
  year: 2010
  ident: 10.1016/j.ijhydene.2025.152704_bib84
  article-title: Matching methods for causal inference: a review and a look forward
  publication-title: Stat Sci
– volume: 414
  start-page: 353
  year: 2001
  ident: 10.1016/j.ijhydene.2025.152704_bib95
  article-title: Hydrogen-storage materials for Mobile applications
  publication-title: Nature
  doi: 10.1038/35104634
– volume: 18
  start-page: 1
  year: 2018
  ident: 10.1016/j.ijhydene.2025.152704_bib81
  article-title: Hyperband: a novel bandit-based approach to hyperparameter optimization
  publication-title: J Mach Learn Res
– year: 2017
  ident: 10.1016/j.ijhydene.2025.152704_bib71
  article-title: Consistent feature attribution for tree ensembles
  publication-title: arXiv preprint arXiv:170606060
– volume: 8
  year: 2021
  ident: 10.1016/j.ijhydene.2025.152704_bib17
  article-title: Hydrogen production, distribution, storage and power conversion in a hydrogen economy - a technology review
  publication-title: Chem Eng J Adv
  doi: 10.1016/j.ceja.2021.100172
– volume: 119
  start-page: 260
  year: 2025
  ident: 10.1016/j.ijhydene.2025.152704_bib36
  article-title: Analysis of pistachio shell-derived activated porous carbon materials for hydrogen adsorption
  publication-title: Int J Hydrogen Energy
  doi: 10.1016/j.ijhydene.2025.03.028
– volume: 47
  start-page: 1171
  year: 2009
  ident: 10.1016/j.ijhydene.2025.152704_bib39
  article-title: Hydrogen adsorption on nitrogen-doped carbon xerogels
  publication-title: Carbon
  doi: 10.1016/j.carbon.2009.01.001
– volume: 145
  start-page: 401
  year: 2025
  ident: 10.1016/j.ijhydene.2025.152704_bib24
  article-title: Predicting hydrogen storage in metal-organic frameworks using a novel hybrid machine learning model
  publication-title: Int J Hydrogen Energy
  doi: 10.1016/j.ijhydene.2025.06.112
– volume: 99
  start-page: 289
  year: 2016
  ident: 10.1016/j.ijhydene.2025.152704_bib41
  article-title: Activated carbon with optimum pore size distribution for hydrogen storage
  publication-title: Carbon
  doi: 10.1016/j.carbon.2015.12.032
– volume: 11
  start-page: 2079
  year: 2010
  ident: 10.1016/j.ijhydene.2025.152704_bib82
  article-title: On over-fitting in model selection and subsequent selection bias in performance evaluation
  publication-title: J Mach Learn Res
– volume: 298
  year: 2021
  ident: 10.1016/j.ijhydene.2025.152704_bib94
  article-title: Explaining individual predictions when features are dependent: more accurate approximations to shapley values
  publication-title: Artif Intell
  doi: 10.1016/j.artint.2021.103502
– volume: 31
  year: 2018
  ident: 10.1016/j.ijhydene.2025.152704_bib52
  article-title: CatBoost: unbiased boosting with categorical features
  publication-title: Adv Neural Inf Process Syst
– year: 2023
  ident: 10.1016/j.ijhydene.2025.152704_bib99
  article-title: The inadequacy of shapley values for explainability
  publication-title: arXiv preprint arXiv:230208160
– volume: 13
  start-page: 385
  year: 2016
  ident: 10.1016/j.ijhydene.2025.152704_bib102
  article-title: Regression diagnostics
  publication-title: Nat Methods
  doi: 10.1038/nmeth.3854
– volume: 3
  start-page: 1658
  year: 2015
  ident: 10.1016/j.ijhydene.2025.152704_bib46
  article-title: Valorization of lignin waste: carbons from hydrothermal carbonization of renewable lignin as superior sorbents for CO2 and hydrogen storage
  publication-title: ACS Sustainable Chem Eng
  doi: 10.1021/acssuschemeng.5b00351
– year: 2021
  ident: 10.1016/j.ijhydene.2025.152704_bib105
– start-page: 165
  year: 2022
  ident: 10.1016/j.ijhydene.2025.152704_bib97
– year: 2025
  ident: 10.1016/j.ijhydene.2025.152704_bib10
  article-title: Porous carbons: a class of nanomaterials for efficient adsorption-based hydrogen storage
  publication-title: RSC Applied Interfaces
  doi: 10.1039/D4LF00215F
– volume: 15
  start-page: 672
  year: 2025
  ident: 10.1016/j.ijhydene.2025.152704_bib70
  article-title: C-SHAP: a hybrid method for fast and efficient interpretability
  publication-title: Applied Sciences
  doi: 10.3390/app15020672
– volume: 20
  start-page: 273
  year: 1995
  ident: 10.1016/j.ijhydene.2025.152704_bib29
  article-title: Support-vector networks
  publication-title: Mach Learn
  doi: 10.1023/A:1022627411411
– volume: 39
  start-page: 261
  year: 2013
  ident: 10.1016/j.ijhydene.2025.152704_bib50
  article-title: Decision trees: a recent overview
  publication-title: Artif Intell Rev
  doi: 10.1007/s10462-011-9272-4
– volume: 19
  start-page: 2817
  year: 2021
  ident: 10.1016/j.ijhydene.2025.152704_bib57
  article-title: Enriched random forest for high dimensional genomic data
  publication-title: IEEE ACM Trans Comput Biol Bioinf
  doi: 10.1109/TCBB.2021.3089417
– volume: 35
  year: 2025
  ident: 10.1016/j.ijhydene.2025.152704_bib16
  article-title: Porous carbon materials: from traditional synthesis, machine learning-assisted design, to their applications in advanced energy storage and conversion
  publication-title: Adv Funct Mater
– volume: 8
  start-page: 1545
  year: 2017
  ident: 10.1016/j.ijhydene.2025.152704_bib37
  article-title: Oxygen-rich microporous carbons with exceptional hydrogen storage capacity
  publication-title: Nat Commun
  doi: 10.1038/s41467-017-01633-x
– year: 2020
  ident: 10.1016/j.ijhydene.2025.152704_bib78
  article-title: Lifting interpretability-performance trade-off via automated feature engineering
  publication-title: arXiv preprint arXiv:200204267
– volume: 7
  start-page: 94
  year: 2020
  ident: 10.1016/j.ijhydene.2025.152704_bib63
  article-title: CatBoost for big data: an interdisciplinary review
  publication-title: Journal of big data
  doi: 10.1186/s40537-020-00369-8
– start-page: 5491
  year: 2020
  ident: 10.1016/j.ijhydene.2025.152704_bib98
  article-title: Problems with shapley-value-based explanations as feature importance measures
– volume: 10
  year: 2021
  ident: 10.1016/j.ijhydene.2025.152704_bib1
  article-title: Transportation is critical to reducing greenhouse gas emissions in the United States
  publication-title: WIREs Energy and Environment
  doi: 10.1002/wene.390
– ident: 10.1016/j.ijhydene.2025.152704_bib92
  doi: 10.1002/9781118445112.stat08235
– year: 2024
  ident: 10.1016/j.ijhydene.2025.152704_bib88
  article-title: Regression tree and clustering for distributions, and homogeneous structure of population characteristics
  publication-title: J Agric Biol Environ Stat
– volume: 63
  start-page: 3
  year: 2006
  ident: 10.1016/j.ijhydene.2025.152704_bib55
  article-title: Extremely randomized trees
  publication-title: Mach Learn
  doi: 10.1007/s10994-006-6226-1
– volume: 83
  start-page: 831
  year: 2023
  ident: 10.1016/j.ijhydene.2025.152704_bib65
  article-title: Exploration of the stacking ensemble machine learning algorithm for cheating detection in large-scale assessment
  publication-title: Educ Psychol Meas
  doi: 10.1177/00131644221117193
– start-page: 785
  year: 2016
  ident: 10.1016/j.ijhydene.2025.152704_bib53
  article-title: XGBoost: a scalable tree boosting system
  publication-title: Journal
– year: 2025
  ident: 10.1016/j.ijhydene.2025.152704_bib33
  article-title: Machine learning driven search of hydrogen storage materials
  publication-title: arXiv preprint arXiv:250304027
– volume: 18
  start-page: 3958
  year: 2025
  ident: 10.1016/j.ijhydene.2025.152704_bib15
  article-title: Hydrogen energy storage via carbon-based materials: from traditional sorbents to emerging architecture engineering and AI-Driven optimization
  publication-title: Energies
  doi: 10.3390/en18153958
– volume: 6
  year: 2023
  ident: 10.1016/j.ijhydene.2025.152704_bib91
  article-title: Model-agnostic explainable artificial intelligence tools for severity prediction and symptom analysis on Indian COVID-19 data
  publication-title: Frontiers in Artificial Intelligence
  doi: 10.3389/frai.2023.1272506
– volume: 45
  start-page: 5
  year: 2001
  ident: 10.1016/j.ijhydene.2025.152704_bib54
  article-title: Random forests
  publication-title: Mach Learn
  doi: 10.1023/A:1010933404324
– volume: 559
  start-page: 547
  year: 2018
  ident: 10.1016/j.ijhydene.2025.152704_bib96
  article-title: Machine learning for molecular and materials science
  publication-title: Nature
  doi: 10.1038/s41586-018-0337-2
– volume: 16
  start-page: 7174
  year: 2023
  ident: 10.1016/j.ijhydene.2025.152704_bib6
  article-title: Hydrogen combustion: features and barriers to its exploitation in the energy transition
  publication-title: Energies
  doi: 10.3390/en16207174
– volume: 97
  year: 2024
  ident: 10.1016/j.ijhydene.2025.152704_bib32
  article-title: Predictive modeling for hydrogen storage in functionalized carbonaceous nanomaterials using machine learning
  publication-title: J Energy Storage
  doi: 10.1016/j.est.2024.112914
– volume: 54
  start-page: 1937
  year: 2021
  ident: 10.1016/j.ijhydene.2025.152704_bib62
  article-title: A comparative analysis of gradient boosting algorithms
  publication-title: Artif Intell Rev
  doi: 10.1007/s10462-020-09896-5
– year: 2018
  ident: 10.1016/j.ijhydene.2025.152704_bib77
– volume: vol. 19
  start-page: 305
  year: 2018
  ident: 10.1016/j.ijhydene.2025.152704_bib87
– volume: 98
  start-page: 1131
  year: 2025
  ident: 10.1016/j.ijhydene.2025.152704_bib23
  article-title: Machine learning approaches for the prediction of hydrogen uptake in metal-organic-frameworks: a comprehensive review
  publication-title: Int J Hydrogen Energy
  doi: 10.1016/j.ijhydene.2024.12.131
– volume: 9
  start-page: 52
  year: 2021
  ident: 10.1016/j.ijhydene.2025.152704_bib73
  article-title: Effect of data scaling methods on machine learning algorithms and model performance
  publication-title: Technologies
  doi: 10.3390/technologies9030052
– volume: 17
  year: 2024
  ident: 10.1016/j.ijhydene.2025.152704_bib68
  article-title: Practical guide to SHAP analysis: explaining supervised machine learning model predictions in drug development
  publication-title: Clinical and translational science
  doi: 10.1111/cts.70056
– volume: 1
  year: 2013
  ident: 10.1016/j.ijhydene.2025.152704_bib20
  article-title: Porous carbon-based materials for hydrogen storage: advancement and challenges
  publication-title: J Mater Chem A
  doi: 10.1039/c3ta10583k
– volume: 39
  start-page: 11661
  year: 2014
  ident: 10.1016/j.ijhydene.2025.152704_bib38
  article-title: Melaleuca bark based porous carbons for hydrogen storage
  publication-title: Int J Hydrogen Energy
  doi: 10.1016/j.ijhydene.2014.05.134
– volume: 7
  start-page: 17466
  year: 2019
  ident: 10.1016/j.ijhydene.2025.152704_bib42
  article-title: Pre-mixed precursors for modulating the porosity of carbons for enhanced hydrogen storage: towards predicting the activation behaviour of carbonaceous matter
  publication-title: J Mater Chem A
  doi: 10.1039/C9TA06308K
– volume: 23
  year: 2024
  ident: 10.1016/j.ijhydene.2025.152704_bib69
  article-title: Machine learning model interpretability using SHAP values: application to igneous rock classification task
  publication-title: Applied Computing and Geosciences
  doi: 10.1016/j.acags.2024.100178
– volume: 179
  start-page: 190
  year: 2021
  ident: 10.1016/j.ijhydene.2025.152704_bib25
  article-title: New insights into hydrogen uptake on porous carbon materials via explainable machine learning
  publication-title: Carbon
  doi: 10.1016/j.carbon.2021.04.036
– volume: 10
  year: 2020
  ident: 10.1016/j.ijhydene.2025.152704_bib8
  article-title: Study of the hydrogen physisorption on adsorbents based on activated carbon by means of statistical physics formalism: modeling analysis and thermodynamics investigation
  publication-title: Sci Rep
  doi: 10.1038/s41598-020-73268-w
– volume: 119
  start-page: 45
  year: 2025
  ident: 10.1016/j.ijhydene.2025.152704_bib22
  article-title: Machine learning descriptor-assisted exploration of metal-modified graphene hydrogen storage materials
  publication-title: Int J Hydrogen Energy
  doi: 10.1016/j.ijhydene.2025.03.247
– volume: 13
  start-page: 281
  year: 2012
  ident: 10.1016/j.ijhydene.2025.152704_bib80
  article-title: Random search for hyper-parameter optimization
  publication-title: J Mach Learn Res
– volume: 13
  year: 2015
  ident: 10.1016/j.ijhydene.2025.152704_bib90
  article-title: Beyond bar and line graphs: time for a new data presentation paradigm
  publication-title: PLoS Biol
  doi: 10.1371/journal.pbio.1002128
– volume: 14
  start-page: 464
  year: 2025
  ident: 10.1016/j.ijhydene.2025.152704_bib103
  article-title: Influence analysis in the lognormal regression model with fitted and quantile residuals
  publication-title: Axioms
  doi: 10.3390/axioms14060464
– volume: 135
  start-page: 525
  year: 2025
  ident: 10.1016/j.ijhydene.2025.152704_bib21
  article-title: Prediction of hydrogen storage in IL/COF composites based on high-throughput computational screening and machine learning
  publication-title: Int J Hydrogen Energy
  doi: 10.1016/j.ijhydene.2025.05.002
– volume: 45
  start-page: 15541
  year: 2020
  ident: 10.1016/j.ijhydene.2025.152704_bib7
  article-title: Determination of the enthalpy of adsorption of hydrogen in activated carbon at room temperature
  publication-title: Int J Hydrogen Energy
  doi: 10.1016/j.ijhydene.2020.04.037
– volume: 8
  start-page: 646
  year: 2018
  ident: 10.1016/j.ijhydene.2025.152704_bib75
  article-title: Proposing enhanced feature engineering and a selection model for machine learning processes
  publication-title: Applied Sciences
  doi: 10.3390/app8040646
– start-page: 43
  year: 2003
  ident: 10.1016/j.ijhydene.2025.152704_bib104
  article-title: Regression error characteristic curves
– volume: 9
  year: 2021
  ident: 10.1016/j.ijhydene.2025.152704_bib2
  article-title: Nitrogen dioxide, greenhouse gas emissions and transportation in urban areas: lessons from the Covid-19 pandemic
  publication-title: Front Environ Sci
  doi: 10.3389/fenvs.2021.689985
– volume: 30
  year: 2017
  ident: 10.1016/j.ijhydene.2025.152704_bib60
  article-title: Lightgbm: a highly efficient gradient boosting decision tree
  publication-title: Adv Neural Inf Process Syst
– volume: 24
  start-page: 69
  year: 2012
  ident: 10.1016/j.ijhydene.2025.152704_bib89
  article-title: A guide to appropriate use of correlation coefficient in medical research
  publication-title: Malawi Med J
– volume: 781
  year: 2021
  ident: 10.1016/j.ijhydene.2025.152704_bib3
  article-title: Impact of different transportation planning scenarios on air pollutants, greenhouse gases and heat emission abatement
  publication-title: Sci Total Environ
  doi: 10.1016/j.scitotenv.2021.146708
– volume: 129
  start-page: 1673
  year: 2007
  ident: 10.1016/j.ijhydene.2025.152704_bib11
  article-title: Enhanced hydrogen storage capacity of high surface area zeolite-like carbon materials
  publication-title: J Am Chem Soc
  doi: 10.1021/ja067149g
– ident: 10.1016/j.ijhydene.2025.152704_bib83
– year: 2018
  ident: 10.1016/j.ijhydene.2025.152704_bib59
  article-title: Gradient boosting with piece-wise linear regression trees
  publication-title: arXiv preprint arXiv:180205640
– year: 2018
  ident: 10.1016/j.ijhydene.2025.152704_bib76
  article-title: Feature engineering for predictive modeling using reinforcement learning
– volume: 96
  start-page: 680
  year: 2024
  ident: 10.1016/j.ijhydene.2025.152704_bib4
  article-title: Study on the influence factors of gravimetric hydrogen storage density of type III cryo-compressed hydrogen storage vessel
  publication-title: Int J Hydrogen Energy
  doi: 10.1016/j.ijhydene.2024.11.375
– start-page: 144
  year: 1999
  ident: 10.1016/j.ijhydene.2025.152704_bib30
  article-title: A comparison between neural networks and decision trees
– volume: 62
  start-page: 272
  year: 2024
  ident: 10.1016/j.ijhydene.2025.152704_bib18
  article-title: Emerging trends in biomass-derived porous carbon materials for hydrogen storage
  publication-title: Int J Hydrogen Energy
  doi: 10.1016/j.ijhydene.2024.02.337
– volume: 329
  year: 2021
  ident: 10.1016/j.ijhydene.2025.152704_bib27
  article-title: Machine learning approaches to rediscovery and optimization of hydrogen storage on porous bio-derived carbon
  publication-title: J Clean Prod
  doi: 10.1016/j.jclepro.2021.129714
– volume: 47
  start-page: 2259
  year: 2009
  ident: 10.1016/j.ijhydene.2025.152704_bib45
  article-title: High performance of nanoporous carbon in cryogenic hydrogen storage and electrochemical capacitance
  publication-title: Carbon
  doi: 10.1016/j.carbon.2009.04.021
– volume: 8
  start-page: 87
  year: 2024
  ident: 10.1016/j.ijhydene.2025.152704_bib66
  article-title: A novel stacking ensemble learner for predicting residual strength of corroded pipelines
  publication-title: npj Mater Degrad
  doi: 10.1038/s41529-024-00508-z
– volume: 102
  start-page: 159
  year: 2007
  ident: 10.1016/j.ijhydene.2025.152704_bib44
  article-title: Synthesis, characterization and hydrogen storage properties of microporous carbons templated by cation exchanged forms of zeolite Y with propylene and butylene as carbon precursors
  publication-title: Microporous Mesoporous Mater
  doi: 10.1016/j.micromeso.2006.12.033
– volume: 67
  start-page: 1270
  year: 2024
  ident: 10.1016/j.ijhydene.2025.152704_bib14
  article-title: Advances in hydrogen storage materials: harnessing innovative technology, from machine learning to computational chemistry, for energy storage solutions
  publication-title: Int J Hydrogen Energy
  doi: 10.1016/j.ijhydene.2024.03.223
– volume: 14
  year: 2019
  ident: 10.1016/j.ijhydene.2025.152704_bib85
  article-title: Machine learning algorithm validation with a limited sample size
  publication-title: PLoS One
  doi: 10.1371/journal.pone.0224365
– start-page: 1137
  year: 1995
  ident: 10.1016/j.ijhydene.2025.152704_bib86
– year: 2017
  ident: 10.1016/j.ijhydene.2025.152704_bib61
  article-title: GPU-Acceleration for large-scale tree boosting
  publication-title: arXiv preprint arXiv:170608359
– volume: 133
  year: 2023
  ident: 10.1016/j.ijhydene.2025.152704_bib72
  article-title: The choice of scaling technique matters for classification performance
  publication-title: Appl Soft Comput
  doi: 10.1016/j.asoc.2022.109924
– start-page: 13
  year: 2017
  ident: 10.1016/j.ijhydene.2025.152704_bib28
  article-title: A comparative study and performance analysis of classification techniques: support vector machine, neural networks and decision trees
– volume: 59
  year: 2023
  ident: 10.1016/j.ijhydene.2025.152704_bib58
  article-title: Trees, forests, and impurity-based variable importance in regression
  publication-title: Annales de l'Institut Henri Poincaré, Probabilités et Statistiques
  doi: 10.1214/21-AIHP1240
– volume: 11
  year: 2021
  ident: 10.1016/j.ijhydene.2025.152704_bib31
  article-title: Explainable artificial intelligence: an analytical review
  publication-title: WIREs Data Mining and Knowledge Discovery
  doi: 10.1002/widm.1424
– volume: 98
  start-page: 1212
  year: 2025
  ident: 10.1016/j.ijhydene.2025.152704_bib35
  article-title: Prediction of hydrogen storage in metal hydrides and complex hydrides: a supervised machine learning approach
  publication-title: Int J Hydrogen Energy
  doi: 10.1016/j.ijhydene.2024.12.121
– volume: 379
  year: 2020
  ident: 10.1016/j.ijhydene.2025.152704_bib48
  article-title: Flexible nanoporous activated carbon cloth for achieving high H2, CH4, and CO2 storage capacities and selective CO2/CH4 separation
  publication-title: Chem Eng J
  doi: 10.1016/j.cej.2019.122367
– volume: 4
  start-page: 195
  year: 2016
  ident: 10.1016/j.ijhydene.2025.152704_bib101
  article-title: Residuals and regression diagnostics: focusing on logistic regression
  publication-title: Ann Transl Med
  doi: 10.21037/atm.2016.03.36
– year: 2025
  ident: 10.1016/j.ijhydene.2025.152704_bib64
– volume: 316
  year: 2023
  ident: 10.1016/j.ijhydene.2025.152704_bib26
  article-title: Machine-learning models to predict hydrogen uptake of porous carbon materials from influential variables
  publication-title: Separation and Purification Technology
  doi: 10.1016/j.seppur.2023.123807
– start-page: 1189
  year: 2001
  ident: 10.1016/j.ijhydene.2025.152704_bib56
  article-title: Greedy function approximation: a gradient boosting machine
  publication-title: Ann Stat
SSID ssj0017049
Score 2.490221
Snippet Widespread adoption of hydrogen fuel is constrained by the cost and safety limits of high-pressure and cryogenic storage. Adsorption-based storage in Porous...
SourceID crossref
elsevier
SourceType Index Database
Publisher
StartPage 152704
SubjectTerms Adsorption
Decision trees
Hydrogen
Machine learning
Porous carbon materials
SHAP
Title Hydrogen uptake prediction in porous carbon materials explained by decision tree machine learning Algorithms: From experimental data to interpretable predictions
URI https://dx.doi.org/10.1016/j.ijhydene.2025.152704
Volume 197
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: ScienceDirect (Freedom Collection)
  issn: 0360-3199
  databaseCode: AIEXJ
  dateStart: 19950101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.sciencedirect.com
  omitProxy: false
  ssIdentifier: ssj0017049
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb5wwELa2SQ_toepTSV-aQ28RaXkYTG_bKlHaQ1QpqbQ3ZIzJstmwK5ZE2Z-Tn5J_1hmMgW0jtVXVC0IgwGY-eT6Pv_Ew9o4jSLJcxk6O5NoJglQ7aayEI7iMvSwkF5E2xSai42MxmcTfRqNbmwtzNY_KUlxfx8v_amq8hsam1Nm_MHf3UryA52h0PKLZ8fhHhj9aZ9UC7-5dLmt5TnlQtBZjNY1It0n0qmSV4gWkq6ZJtNP_XCLjbPho1hbeIRk6CVxJb6ltgYmzvfH8bFEV9fSikdMdUoLKRqEAUp0Spy06QSOlZ_XtWA0Z8WZIcrCRxdT2Qzfpif3qVXkum-JI6DIvEBddPPvTVNY4zjVaxJNpJXGOUHTrScaTUBip80Njyjhby1abNO3vtUEQzwRBeB-Zs9k5vRTKZISRjzEFmLrR3siBf_EcJogx2y9m2D3s2D5-hlN1qMiUR_5pV-4Tejm9myhk9CEK77FtL-IxDqzb4y8Hk6_dUlbUzsFsYwZp6nd_7W6GNGA9p4_Zo3a6AmMDsydspMun7OFgE8tn7MYCDgzgoDc0FCUYwIEBHHSAgw5wkK7BAg4IcNACDizgoAfcRyC4wRBuQHCDegEbcBu0YvWcfT88OP185LSFPxzlRmHtuDSJdfHUQx-YukLGyueZ8IWSkkuk9BFHFhUqoWM_5Tpw0yAPaT_bXIWc69B_wbbKRal3GAhXeb70tB_yLPB1KmkhXYvMV0GucyV22Xv7s5Ol2d8lscLHWWLNk5B5EmOeXRZbmyQtSzXsM0Eo_ebZl__w7Cv2oEf-a7ZVV5f6DbuvrupiVb1tUfcDIHHGYg
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=Hydrogen+uptake+prediction+in+porous+carbon+materials+explained+by+decision+tree+machine+learning+Algorithms%3A+From+experimental+data+to+interpretable+predictions&rft.jtitle=International+journal+of+hydrogen+energy&rft.au=Sunkara%2C+Hemanth&rft.au=Bhat+A+S%2C+Shravani&rft.au=R%2C+Namitha&rft.au=Acharya%2C+Sushmitha&rft.date=2026-01-05&rft.pub=Elsevier+Ltd&rft.issn=0360-3199&rft.volume=197&rft_id=info:doi/10.1016%2Fj.ijhydene.2025.152704&rft.externalDocID=S0360319925057076
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0360-3199&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0360-3199&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0360-3199&client=summon