A new formulation for symbolic regression to identify physico-chemical laws from experimental data
•Automated identification of physical laws from noisy experimental data demonstrated.•Symbolic regression problem is formulated using directed acyclic graphs.•Demonstration of physical knowledge generated from the robotically collected data. A modification to the mixed-integer nonlinear programming...
Uloženo v:
| Vydáno v: | Chemical engineering journal (Lausanne, Switzerland : 1996) Ročník 387; s. 123412 |
|---|---|
| Hlavní autoři: | , , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Elsevier B.V
01.05.2020
|
| Témata: | |
| ISSN: | 1385-8947, 1873-3212 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | •Automated identification of physical laws from noisy experimental data demonstrated.•Symbolic regression problem is formulated using directed acyclic graphs.•Demonstration of physical knowledge generated from the robotically collected data.
A modification to the mixed-integer nonlinear programming (MINLP) formulation for symbolic regression was proposed with the aim of identification of physical models from noisy experimental data. In the proposed formulation, a binary tree in which equations are represented as directed, acyclic graphs, is fully constructed for a pre-defined number of layers. The introduced modification results in the reduction in the number of required binary variables and removal of redundancy due to possible symmetry of the tree formulation. The formulation was tested using numerical models and was found to be more efficient than the previous literature example with respect to the numbers of predictor variables and training data points. The globally optimal search was extended to identify physical models and to cope with noise in the experimental data predictor variable. The methodology was proven to be successful in identifying the correct physical models describing the relationship between shear stress and shear rate for both Newtonian and non-Newtonian fluids, and simple kinetic laws of chemical reactions. Future work will focus on addressing the limitations of the present formulation and solver to enable extension of target problems to larger, more complex physical models. |
|---|---|
| AbstractList | •Automated identification of physical laws from noisy experimental data demonstrated.•Symbolic regression problem is formulated using directed acyclic graphs.•Demonstration of physical knowledge generated from the robotically collected data.
A modification to the mixed-integer nonlinear programming (MINLP) formulation for symbolic regression was proposed with the aim of identification of physical models from noisy experimental data. In the proposed formulation, a binary tree in which equations are represented as directed, acyclic graphs, is fully constructed for a pre-defined number of layers. The introduced modification results in the reduction in the number of required binary variables and removal of redundancy due to possible symmetry of the tree formulation. The formulation was tested using numerical models and was found to be more efficient than the previous literature example with respect to the numbers of predictor variables and training data points. The globally optimal search was extended to identify physical models and to cope with noise in the experimental data predictor variable. The methodology was proven to be successful in identifying the correct physical models describing the relationship between shear stress and shear rate for both Newtonian and non-Newtonian fluids, and simple kinetic laws of chemical reactions. Future work will focus on addressing the limitations of the present formulation and solver to enable extension of target problems to larger, more complex physical models. |
| ArticleNumber | 123412 |
| Author | Vassiliadis, Vassilios S. Neumann, Pascal Russo, Danilo Cao, Liwei Lapkin, Alexei A. |
| Author_xml | – sequence: 1 givenname: Pascal surname: Neumann fullname: Neumann, Pascal organization: Aachener Verfahrenstchnik – Process Systems Engineering, RWTH Aachen University, Aachen, Germany – sequence: 2 givenname: Liwei surname: Cao fullname: Cao, Liwei organization: Department of Chemical Engineering and Biotechnology, University of Cambridge, Cambridge CB3 0AS, UK – sequence: 3 givenname: Danilo surname: Russo fullname: Russo, Danilo organization: Department of Chemical Engineering and Biotechnology, University of Cambridge, Cambridge CB3 0AS, UK – sequence: 4 givenname: Vassilios S. surname: Vassiliadis fullname: Vassiliadis, Vassilios S. organization: Department of Chemical Engineering and Biotechnology, University of Cambridge, Cambridge CB3 0AS, UK – sequence: 5 givenname: Alexei A. surname: Lapkin fullname: Lapkin, Alexei A. email: aal35@cam.ac.uk organization: Department of Chemical Engineering and Biotechnology, University of Cambridge, Cambridge CB3 0AS, UK |
| BookMark | eNp9kMtOwzAQRS1UJNrCB7DzDyTYcR6OWFUVL6kSG1hbzmRMHSVxZQdK_p6EsmLR1VyN5ox0z4osetcjIbecxZzx_K6JAZs4YbyMeSJSnlyQJZeFiETCk8WUhcwiWabFFVmF0DDG8pKXS1JtaI9HapzvPls9WNfPmYaxq1xrgXr88BjCvB8ctTX2gzUjPezHYMFFsMfOgm5pq4-BGu86it8H9LabDqd1rQd9TS6NbgPe_M01eX98eNs-R7vXp5ftZheBSNkQSZlXHApTZJAXwqRYyQwrU2ZSJEKDzqVEXqHMdVojYipYLdHkJXAja56AWJPi9Be8C8GjUWCH30qD17ZVnKlZlWrUpErNqtRJ1UTyf-RhaqD9eJa5PzE4Vfqy6FUAiz1gbT3CoGpnz9A_5yKGEw |
| CitedBy_id | crossref_primary_10_1021_jacs_3c04783 crossref_primary_10_1016_j_ces_2024_120391 crossref_primary_10_1007_s11831_023_09922_z crossref_primary_10_1002_cite_202100083 crossref_primary_10_1016_j_cma_2023_116096 crossref_primary_10_1016_j_compchemeng_2022_108083 crossref_primary_10_1007_s10661_022_10595_7 crossref_primary_10_1145_3735634 crossref_primary_10_1016_j_heliyon_2024_e32547 crossref_primary_10_1016_j_ces_2024_120606 crossref_primary_10_1016_j_ces_2024_119881 crossref_primary_10_1007_s11356_023_28608_4 crossref_primary_10_1007_s11433_023_2346_2 crossref_primary_10_1002_aic_17248 crossref_primary_10_3390_mi14071446 crossref_primary_10_3390_pr13071981 crossref_primary_10_1016_j_cep_2025_110350 crossref_primary_10_1016_j_ces_2023_119670 crossref_primary_10_1016_j_spc_2021_12_025 crossref_primary_10_1016_j_seppur_2024_129494 crossref_primary_10_1109_ACCESS_2020_2969997 crossref_primary_10_1016_j_compchemeng_2020_107051 crossref_primary_10_1016_j_compchemeng_2025_109281 crossref_primary_10_1007_s00707_025_04325_6 crossref_primary_10_1016_j_jmrt_2025_01_154 crossref_primary_10_1016_j_inffus_2022_11_030 crossref_primary_10_1109_TIM_2024_3449968 crossref_primary_10_1287_ijoc_2022_0050 crossref_primary_10_1002_aic_17695 crossref_primary_10_1016_j_actbio_2024_09_005 crossref_primary_10_1016_j_compchemeng_2022_108108 crossref_primary_10_1002_aic_17457 crossref_primary_10_1021_acs_iecr_5c00107 crossref_primary_10_3390_ijms26146748 |
| Cites_doi | 10.1021/ed074p1440 10.1080/10556788.2017.1350178 10.1038/nchem.1489 10.1007/s11081-018-9411-8 10.3762/bjoc.13.18 10.1126/sciadv.1602614 10.1002/aic.14418 10.1016/j.compchemeng.2017.02.010 10.2174/1874149501913010001 10.1037/a0027127 10.1021/acs.accounts.6b00261 10.1126/science.1165893 10.1007/s10898-014-0166-2 10.1016/j.compchemeng.2018.08.010 10.1111/j.1432-1033.1974.tb03267.x 10.1021/acscentsci.8b00357 10.1016/j.tet.2018.02.061 10.1016/j.coche.2015.07.001 10.1016/j.compchemeng.2014.11.010 10.1016/j.cep.2011.06.005 10.1080/10556780902753221 10.3389/fphys.2014.00021 10.1098/rspa.2017.0009 10.1021/acscentsci.7b00064 10.1103/PhysRevE.94.012214 10.1002/anie.201002590 10.1016/B978-0-444-63578-5.50113-4 10.1002/spe.4380181104 10.7717/peerj-cs.103 10.1073/pnas.0609476104 10.1039/C8SC04228D 10.2166/hydro.2008.015 10.1002/anie.201705721 10.1038/s41598-017-02303-0 10.1126/science.1207922 10.1080/10556788.2017.1335312 10.1021/ed081p870 10.1007/s12532-011-0026-8 10.1080/10556780903087124 10.1098/rspa.2016.0446 10.1039/C7FD00073A 10.1023/A:1021039126272 10.1073/pnas.1517384113 |
| ContentType | Journal Article |
| Copyright | 2019 Elsevier B.V. |
| Copyright_xml | – notice: 2019 Elsevier B.V. |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.cej.2019.123412 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1873-3212 |
| ExternalDocumentID | 10_1016_j_cej_2019_123412 S1385894719328256 |
| GroupedDBID | --K --M -~X .~1 0R~ 1B1 1RT 1~. 1~5 29B 4.4 457 4G. 53G 5GY 5VS 7-5 71M 8P~ AABNK AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAXUO ABFNM ABFYP ABLST ABMAC ABNUV ABUDA ABYKQ ACDAQ ACRLP ADBBV ADEWK ADEZE AEBSH AEKER AENEX AFKWA AFTJW AFXIZ AGHFR AGUBO AGYEJ AHEUO AHPOS AIEXJ AIKHN AITUG AJOXV AKIFW AKURH ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AXJTR BKOJK BLECG BLXMC CS3 DU5 EBS EFJIC EFLBG ENUVR EO8 EO9 EP2 EP3 F5P FDB FIRID FNPLU FYGXN G-Q GBLVA IHE J1W KCYFY KOM M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 ROL RPZ SDF SDG SES SPC SPCBC SSG SSJ SSZ T5K ~G- 9DU AATTM AAXKI AAYWO AAYXX ABXDB ACLOT ACVFH ADCNI AEIPS AEUPX AFFNX AFJKZ AFPUW AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP ASPBG AVWKF AZFZN BKOMP CITATION EFKBS EJD FEDTE FGOYB HVGLF HZ~ R2- SEW ZY4 ~HD |
| ID | FETCH-LOGICAL-c340t-886b1c7f75c673f4eb85ebf958323aca688e1be86a4deee430d8ef69c1f8d12c3 |
| ISICitedReferencesCount | 44 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000527331600014&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1385-8947 |
| IngestDate | Sat Nov 29 07:04:21 EST 2025 Tue Nov 18 22:37:51 EST 2025 Fri Feb 23 02:49:29 EST 2024 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Symbolic regression Mixed-integer nonlinear programming (MINLP) Global optimization Chemical process development Automated model construction Model identification |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c340t-886b1c7f75c673f4eb85ebf958323aca688e1be86a4deee430d8ef69c1f8d12c3 |
| OpenAccessLink | https://www.repository.cam.ac.uk/handle/1810/298772 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_cej_2019_123412 crossref_primary_10_1016_j_cej_2019_123412 elsevier_sciencedirect_doi_10_1016_j_cej_2019_123412 |
| PublicationCentury | 2000 |
| PublicationDate | 2020-05-01 2020-05-00 |
| PublicationDateYYYYMMDD | 2020-05-01 |
| PublicationDate_xml | – month: 05 year: 2020 text: 2020-05-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationTitle | Chemical engineering journal (Lausanne, Switzerland : 1996) |
| PublicationYear | 2020 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | (accessed 05.08.19). Cozad, Sahinidis, Miller (b0100) 2014; 60 Solomatine, Ostfeld (b0075) 2008; 10 Duros, Grizou, Xuan, Hosni, Long, Miras, Cronin (b0030) 2017; 56 Vigerske, Gleixner (b0215) 2018; 33 Meurer, Smith, Paprocki, Čertík, Kirpichev, Rocklin, Kumar, Ivanov, Moore, Singh, Rathnayake, Vig, Granger, Muller, Bonazzi, Gupta, Vats, Johansson, Pedregosa, Curry, Terrel, Roučka, Saboo, Fernando, Kulal, Cimrman, Scopatz (b0230) 2017; 3 Akaike (b0240) 1974 Coley, Barzilay, Jaakkola, Green, Jensen (b0005) 2017; 3 Quade, Abel, Shafi, Niven, Noack (b0235) 2016; 94 Lapkin, Plucinski (b0050) 2009 Skoraczyński, Dittwald, Miasojedow, Szymkuć, Gajewska, Grzybowski, Gambin (b0035) 2017; 7 Klausen, Meier, Schwarzenbach (b0250) 1997; 74 Lin, Schrage (b0210) 2009; 24 Gao, Struble, Coley, Wang, Green, Jensen (b0015) 2018; 4 H. Schaeffer, G. Tran, R. Ward, L. Zhang, Extracting structured dynamical systems using sparse optimization with very few samples Robbins, Hartwig, MacMillan (b0060) 2011; 333 Wilson, Sahinidis (b0110) 2017; 106 Hart, Watson, Woodruff (b0225) 2011; 3 Schmidt, Lipson (b0080) 2009; 324 Goren, Fridkin (b0260) 1974; 41 Cozad, Sahinidis, Miller (b0105) 2015; 73 Coley, Jin, Rogers, Jamison, Jaakkola, Green, Barzilay, Jensen (b0025) 2019; 10 Reizman, Jensen (b0040) 2016; 49 Lapkin, Voutchkova, Anastas (b0095) 2011; 50 Wolkenhauer (b0085) 2014; 5 Narasingam, Sang-Il Kwon (b0125) 2018; 119 Jeraal, Holmes, Akien, Bourne (b0020) 2018; 74 (accessed August 5, 2019). Y. Wang, N. Wagner, J.M. Rondinelli, Symbolic regression in materials science Rudy, Brunton, Proctor, Kutz (b0120) 2017; 3 Schaeffer (b0130) 2017; 473 (accessed April 9, 2019). Belotti, Lee, Liberti, Margot, Wächter (b0205) 2009; 24 Horbaczewskyj, Willans, Lapkin, Bourne (b0090) 2018 S. Li, E. Kaiser, S. Laima, H. Li, S.L. Brunton, J. Nathan Kutz, Discovering time-varying aeroelastic models of a long-span suspension bridge from field measurements by sparse identification of nonlinear dynamical systems Tarawneh, Bodour, Al (b0160) 2019; 13 Richmond, Miras, de la Oliva, Zang, Sans, Paramonov, Makatsoris, Inglis, Brechin, Long, Cronin (b0055) 2012; 4 Grossmann (b0185) 2002; 3 J. Kronqvist, D. E. Bernal, A. Lundell, I. E. Grossmann, A review and comparison of solvers for convex MINLP, 20 (2019) 397–455. doi: 10.1007/s11081-018-9411-8. Kılınç, Sahinidis (b0200) 2018; 33 Echtermeyer, Amar, Zakrzewski, Lapkin (b0010) 2017; 13 Bongard, Lipson (b0155) 2007; 104 Misener, Floudas (b0195) 2014; 59 Lapkin, Heer, Jacob, Hutchby, Cunningham, Bull, Davidson (b0065) 2017; 202 Vrieze (b0245) 2012; 17 Vassiliadis, Wang, Arellano-Garcia, Yuan (b0170) 2015; 37 (accessed August 6, 2019). Brunton, Proctor, Kutz (b0150) 2016; 113 Mangan, Kutz, Brunton, Proctor (b0115) 2017; 473 Gansner, North, Vo (b0180) 1988; 18 Houben, Lapkin (b0045) 2015; 9 ILOG CPLEX Optimization Studio - Overview | IBM McMullen, Stone, Buchwald, Jensen (b0070) 2010; 49 (accessed 22.01.19). Lin, Zhang (b0145) 2018; 474 Cozad, Sahinidis (b0175) 2018 P.S. Marrs, Class Projects in Physical Organic Chemistry: The Hydrolysis of Aspirin, J. Chem. Educ. 81 (2004) 870–873. Reizman (10.1016/j.cej.2019.123412_b0040) 2016; 49 Richmond (10.1016/j.cej.2019.123412_b0055) 2012; 4 Mangan (10.1016/j.cej.2019.123412_b0115) 2017; 473 Meurer (10.1016/j.cej.2019.123412_b0230) 2017; 3 Coley (10.1016/j.cej.2019.123412_b0005) 2017; 3 Quade (10.1016/j.cej.2019.123412_b0235) 2016; 94 Akaike (10.1016/j.cej.2019.123412_b0240) 1974 Lapkin (10.1016/j.cej.2019.123412_b0050) 2009 Tarawneh (10.1016/j.cej.2019.123412_b0160) 2019; 13 Lapkin (10.1016/j.cej.2019.123412_b0095) 2011; 50 10.1016/j.cej.2019.123412_b0190 Hart (10.1016/j.cej.2019.123412_b0225) 2011; 3 Kılınç (10.1016/j.cej.2019.123412_b0200) 2018; 33 Goren (10.1016/j.cej.2019.123412_b0260) 1974; 41 Jeraal (10.1016/j.cej.2019.123412_b0020) 2018; 74 Echtermeyer (10.1016/j.cej.2019.123412_b0010) 2017; 13 Robbins (10.1016/j.cej.2019.123412_b0060) 2011; 333 Lapkin (10.1016/j.cej.2019.123412_b0065) 2017; 202 Schmidt (10.1016/j.cej.2019.123412_b0080) 2009; 324 Cozad (10.1016/j.cej.2019.123412_b0100) 2014; 60 10.1016/j.cej.2019.123412_b0140 Misener (10.1016/j.cej.2019.123412_b0195) 2014; 59 Coley (10.1016/j.cej.2019.123412_b0025) 2019; 10 Narasingam (10.1016/j.cej.2019.123412_b0125) 2018; 119 Wolkenhauer (10.1016/j.cej.2019.123412_b0085) 2014; 5 Wilson (10.1016/j.cej.2019.123412_b0110) 2017; 106 Vigerske (10.1016/j.cej.2019.123412_b0215) 2018; 33 10.1016/j.cej.2019.123412_b0220 Grossmann (10.1016/j.cej.2019.123412_b0185) 2002; 3 Lin (10.1016/j.cej.2019.123412_b0210) 2009; 24 Solomatine (10.1016/j.cej.2019.123412_b0075) 2008; 10 Vrieze (10.1016/j.cej.2019.123412_b0245) 2012; 17 Skoraczyński (10.1016/j.cej.2019.123412_b0035) 2017; 7 Lin (10.1016/j.cej.2019.123412_b0145) 2018; 474 Horbaczewskyj (10.1016/j.cej.2019.123412_b0090) 2018 Bongard (10.1016/j.cej.2019.123412_b0155) 2007; 104 Houben (10.1016/j.cej.2019.123412_b0045) 2015; 9 10.1016/j.cej.2019.123412_b0255 10.1016/j.cej.2019.123412_b0135 Cozad (10.1016/j.cej.2019.123412_b0105) 2015; 73 Gao (10.1016/j.cej.2019.123412_b0015) 2018; 4 Rudy (10.1016/j.cej.2019.123412_b0120) 2017; 3 Cozad (10.1016/j.cej.2019.123412_b0175) 2018 Vassiliadis (10.1016/j.cej.2019.123412_b0170) 2015; 37 McMullen (10.1016/j.cej.2019.123412_b0070) 2010; 49 Duros (10.1016/j.cej.2019.123412_b0030) 2017; 56 Brunton (10.1016/j.cej.2019.123412_b0150) 2016; 113 Klausen (10.1016/j.cej.2019.123412_b0250) 1997; 74 Belotti (10.1016/j.cej.2019.123412_b0205) 2009; 24 Gansner (10.1016/j.cej.2019.123412_b0180) 1988; 18 10.1016/j.cej.2019.123412_b0165 Schaeffer (10.1016/j.cej.2019.123412_b0130) 2017; 473 |
| References_xml | – volume: 74 start-page: 1440 year: 1997 end-page: 1444 ident: b0250 article-title: Assessing the fate of organic contaminants in aquatic environments: mechanism and kinetics of hydrolysis of a carboxylic ester publication-title: J. Chem. Educ. – reference: J. Kronqvist, D. E. Bernal, A. Lundell, I. E. Grossmann, A review and comparison of solvers for convex MINLP, 20 (2019) 397–455. doi: 10.1007/s11081-018-9411-8. – volume: 33 start-page: 563 year: 2018 end-page: 593 ident: b0215 article-title: SCIP: global optimization of mixed-integer nonlinear programs in a branch-and-cut framework publication-title: Optim. Methods Softw. – reference: S. Li, E. Kaiser, S. Laima, H. Li, S.L. Brunton, J. Nathan Kutz, Discovering time-varying aeroelastic models of a long-span suspension bridge from field measurements by sparse identification of nonlinear dynamical systems, – volume: 10 start-page: 370 year: 2019 end-page: 377 ident: b0025 article-title: A graph-convolutional neural network model for the prediction of chemical reactivity publication-title: Chem. Sci. – volume: 10 start-page: 3 year: 2008 end-page: 22 ident: b0075 article-title: Data-driven modelling: some past experiences and new approaches publication-title: J. Hydroinf. – volume: 49 start-page: 1786 year: 2016 end-page: 1796 ident: b0040 article-title: Feedback in flow for accelerated reaction development publication-title: Acc. Chem. Res. – reference: (accessed April 9, 2019). – start-page: 1 year: 2018 end-page: 23 ident: b0175 article-title: A global MINLP approach to symbolic regression publication-title: Math. Program. – volume: 474 start-page: 0305 year: 2018 ident: b0145 article-title: Robust data-driven discovery of governing physical laws with error bars publication-title: Proc. R. Soc. A – volume: 4 start-page: 1037 year: 2012 end-page: 1043 ident: b0055 article-title: A flow-system array for the discovery and scale up of inorganic clusters publication-title: Nat. Chem. – volume: 7 start-page: 3582 year: 2017 ident: b0035 article-title: Predicting the outcomes of organic reactions via machine learning: are current descriptors sufficient? publication-title: Sci. Rep. – volume: 3 start-page: 434 year: 2017 end-page: 443 ident: b0005 article-title: Prediction of organic reaction outcomes using machine learning publication-title: ACS Cent. Sci. – volume: 3 year: 2017 ident: b0120 article-title: Data-driven discovery of partial differential equations publication-title: Sci. Adv. – reference: (accessed August 6, 2019). – reference: P.S. Marrs, Class Projects in Physical Organic Chemistry: The Hydrolysis of Aspirin, J. Chem. Educ. 81 (2004) 870–873. – start-page: 1 year: 2009 end-page: 43 ident: b0050 article-title: Engineering factors for efficient flow processes in chemical industries – volume: 73 start-page: 116 year: 2015 end-page: 127 ident: b0105 article-title: A combined first-principles and data-driven approach to model building publication-title: Comput. Chem. Eng. – reference: . (accessed 05.08.19). – reference: (accessed 22.01.19). – start-page: 215 year: 1974 end-page: 222 ident: b0240 article-title: A new look at the statistical model identification publication-title: Selected Papers of Hirotugu Akaike – volume: 17 start-page: 228 year: 2012 end-page: 243 ident: b0245 article-title: Model selection and psychological theory: a discussion of the differences between the Akaike information criterion (AIC) and the Bayesian information criterion (BIC) publication-title: Psychol. Methods – reference: (accessed August 5, 2019). – volume: 13 start-page: 1 year: 2019 end-page: 9 ident: b0160 article-title: Ajmi, intelligent computing based formulas to predict the settlement of shallow foundations on cohesionless soils publication-title: Open Civ. Eng. J. – volume: 50 start-page: 1027 year: 2011 end-page: 1034 ident: b0095 article-title: A conceptual framework for description of complexity in intensive chemical processes publication-title: Chem. Eng. Process. Process Intensif. – volume: 3 start-page: 227 year: 2002 end-page: 252 ident: b0185 article-title: Review of nonlinear mixed-integer and disjunctive programming techniques publication-title: Optim. Eng. – volume: 49 start-page: 7076 year: 2010 end-page: 7080 ident: b0070 article-title: An integrated microreactor system for self-optimization of a heck reaction: from micro- to mesoscale flow systems publication-title: Angew. Chemie Int. Ed. – volume: 104 start-page: 9943 year: 2007 end-page: 9948 ident: b0155 article-title: Automated reverse engineering of nonlinear dynamical systems publication-title: Proc. Nat. Acad. Sci. – volume: 74 start-page: 3158 year: 2018 end-page: 3164 ident: b0020 article-title: Enhanced process development using automated continuous reactors by self-optimisation algorithms and statistical empirical modelling publication-title: Tetrahedron – volume: 473 start-page: 0009 year: 2017 ident: b0115 article-title: Model selection for dynamical systems via sparse regression and information criteria publication-title: Proc. R. Soc. A – reference: Y. Wang, N. Wagner, J.M. Rondinelli, Symbolic regression in materials science, – volume: 59 start-page: 503 year: 2014 end-page: 526 ident: b0195 article-title: ANTIGONE: algorithms for coNTinuous/Integer global optimization of nonlinear equations publication-title: J. Glob. Optim. – volume: 94 start-page: 12214 year: 2016 ident: b0235 article-title: Prediction of dynamical systems by symbolic regression publication-title: Phys. Rev. E. – volume: 9 start-page: 1 year: 2015 end-page: 7 ident: b0045 article-title: Automatic discovery and optimization of chemical processes publication-title: Curr. Opin. Chem. Eng. – volume: 3 start-page: 219 year: 2011 end-page: 260 ident: b0225 article-title: Pyomo: modeling and solving mathematical programs in Python publication-title: Math. Program. Comput. – volume: 473 start-page: 0446 year: 2017 ident: b0130 article-title: Learning partial differential equations via data discovery and sparse optimization publication-title: Proc. R. Soc. A. – volume: 33 start-page: 540 year: 2018 end-page: 562 ident: b0200 article-title: Exploiting integrality in the global optimization of mixed-integer nonlinear programming problems with BARON publication-title: Optim. Methods Softw. – volume: 13 start-page: 150 year: 2017 end-page: 163 ident: b0010 article-title: Self-optimisation and model-based design of experiments for developing a C-H activation flow process publication-title: Beilstein J. Org. Chem. – volume: 202 start-page: 483 year: 2017 end-page: 496 ident: b0065 article-title: Automation of route identification and optimisation based on data-mining and chemical intuition publication-title: Faraday Discuss. – volume: 60 start-page: 2211 year: 2014 end-page: 2227 ident: b0100 article-title: Learning surrogate models for simulation-based optimization publication-title: AIChE J. – volume: 324 start-page: 81 year: 2009 end-page: 85 ident: b0080 article-title: Distilling free-form natural laws from experimental data publication-title: Science – year: 2018 ident: b0090 article-title: An introduction to closed-loop process optimization and online analysis publication-title: Green Chemical Engineering – volume: 113 start-page: 3932 year: 2016 end-page: 3937 ident: b0150 article-title: Discovering governing equations from data by sparse identification of nonlinear dynamical systems publication-title: Proc. Natl. Acad. Sci. U.S.A. – volume: 333 start-page: 1423 year: 2011 end-page: 1427 ident: b0060 article-title: A simple, multidimensional approach to high-throughput discovery of catalytic reactions publication-title: Science – reference: ILOG CPLEX Optimization Studio - Overview | IBM, – volume: 3 start-page: e103 year: 2017 ident: b0230 article-title: SymPy: symbolic computing in Python publication-title: PeerJ Comput. Sci. – volume: 119 start-page: 101 year: 2018 end-page: 111 ident: b0125 article-title: Data-driven identification of interpretable reduced-order models using sparse regression publication-title: Comput. Chem. Eng. – volume: 56 start-page: 10815 year: 2017 end-page: 10820 ident: b0030 article-title: Human versus robots in the discovery and crystallization of gigantic polyoxometalates publication-title: Angew. Chem. Int. Ed. – volume: 18 start-page: 1047 year: 1988 end-page: 1062 ident: b0180 article-title: DAG—a program that draws directed graphs publication-title: Softw. Pract. Exp. – volume: 24 start-page: 657 year: 2009 end-page: 668 ident: b0210 article-title: The global solver in the LINDO API publication-title: Optim. Methods Softw. – volume: 5 start-page: 21 year: 2014 ident: b0085 article-title: Why model? publication-title: Front. Physiol. – reference: H. Schaeffer, G. Tran, R. Ward, L. Zhang, Extracting structured dynamical systems using sparse optimization with very few samples, – volume: 106 start-page: 785 year: 2017 end-page: 795 ident: b0110 article-title: The ALAMO approach to machine learning publication-title: Comput. Chem. Eng. – volume: 24 start-page: 597 year: 2009 end-page: 634 ident: b0205 article-title: Branching and bounds tightening techniques for non-convex MINLP publication-title: Optim. Methods Softw. – volume: 41 start-page: 263 year: 1974 end-page: 272 ident: b0260 article-title: The hydrolysis of p-nitrophenylacetate in water. Mechanism and method of measurement publication-title: Eur. J. Biochem. – volume: 37 start-page: 707 year: 2015 end-page: 712 ident: b0170 article-title: A novel rigorous mathematical programming approach to construct phenomenological models publication-title: Comput. Aided Chem. Eng. – volume: 4 start-page: 1465 year: 2018 end-page: 1476 ident: b0015 article-title: Using machine learning to predict suitable conditions for organic reactions publication-title: ACS Cent. Sci. – volume: 74 start-page: 1440 year: 1997 ident: 10.1016/j.cej.2019.123412_b0250 article-title: Assessing the fate of organic contaminants in aquatic environments: mechanism and kinetics of hydrolysis of a carboxylic ester publication-title: J. Chem. Educ. doi: 10.1021/ed074p1440 – start-page: 1 year: 2009 ident: 10.1016/j.cej.2019.123412_b0050 – start-page: 1 year: 2018 ident: 10.1016/j.cej.2019.123412_b0175 article-title: A global MINLP approach to symbolic regression publication-title: Math. Program. – volume: 33 start-page: 540 year: 2018 ident: 10.1016/j.cej.2019.123412_b0200 article-title: Exploiting integrality in the global optimization of mixed-integer nonlinear programming problems with BARON publication-title: Optim. Methods Softw. doi: 10.1080/10556788.2017.1350178 – volume: 4 start-page: 1037 year: 2012 ident: 10.1016/j.cej.2019.123412_b0055 article-title: A flow-system array for the discovery and scale up of inorganic clusters publication-title: Nat. Chem. doi: 10.1038/nchem.1489 – ident: 10.1016/j.cej.2019.123412_b0190 doi: 10.1007/s11081-018-9411-8 – volume: 13 start-page: 150 year: 2017 ident: 10.1016/j.cej.2019.123412_b0010 article-title: Self-optimisation and model-based design of experiments for developing a C-H activation flow process publication-title: Beilstein J. Org. Chem. doi: 10.3762/bjoc.13.18 – year: 2018 ident: 10.1016/j.cej.2019.123412_b0090 article-title: An introduction to closed-loop process optimization and online analysis – volume: 474 start-page: 0305 year: 2018 ident: 10.1016/j.cej.2019.123412_b0145 article-title: Robust data-driven discovery of governing physical laws with error bars publication-title: Proc. R. Soc. A – volume: 3 year: 2017 ident: 10.1016/j.cej.2019.123412_b0120 article-title: Data-driven discovery of partial differential equations publication-title: Sci. Adv. doi: 10.1126/sciadv.1602614 – volume: 60 start-page: 2211 year: 2014 ident: 10.1016/j.cej.2019.123412_b0100 article-title: Learning surrogate models for simulation-based optimization publication-title: AIChE J. doi: 10.1002/aic.14418 – volume: 106 start-page: 785 year: 2017 ident: 10.1016/j.cej.2019.123412_b0110 article-title: The ALAMO approach to machine learning publication-title: Comput. Chem. Eng. doi: 10.1016/j.compchemeng.2017.02.010 – volume: 13 start-page: 1 year: 2019 ident: 10.1016/j.cej.2019.123412_b0160 article-title: Ajmi, intelligent computing based formulas to predict the settlement of shallow foundations on cohesionless soils publication-title: Open Civ. Eng. J. doi: 10.2174/1874149501913010001 – volume: 17 start-page: 228 year: 2012 ident: 10.1016/j.cej.2019.123412_b0245 article-title: Model selection and psychological theory: a discussion of the differences between the Akaike information criterion (AIC) and the Bayesian information criterion (BIC) publication-title: Psychol. Methods doi: 10.1037/a0027127 – volume: 49 start-page: 1786 year: 2016 ident: 10.1016/j.cej.2019.123412_b0040 article-title: Feedback in flow for accelerated reaction development publication-title: Acc. Chem. Res. doi: 10.1021/acs.accounts.6b00261 – volume: 324 start-page: 81 year: 2009 ident: 10.1016/j.cej.2019.123412_b0080 article-title: Distilling free-form natural laws from experimental data publication-title: Science doi: 10.1126/science.1165893 – volume: 59 start-page: 503 year: 2014 ident: 10.1016/j.cej.2019.123412_b0195 article-title: ANTIGONE: algorithms for coNTinuous/Integer global optimization of nonlinear equations publication-title: J. Glob. Optim. doi: 10.1007/s10898-014-0166-2 – ident: 10.1016/j.cej.2019.123412_b0220 – volume: 119 start-page: 101 year: 2018 ident: 10.1016/j.cej.2019.123412_b0125 article-title: Data-driven identification of interpretable reduced-order models using sparse regression publication-title: Comput. Chem. Eng. doi: 10.1016/j.compchemeng.2018.08.010 – volume: 41 start-page: 263 year: 1974 ident: 10.1016/j.cej.2019.123412_b0260 article-title: The hydrolysis of p-nitrophenylacetate in water. Mechanism and method of measurement publication-title: Eur. J. Biochem. doi: 10.1111/j.1432-1033.1974.tb03267.x – volume: 4 start-page: 1465 year: 2018 ident: 10.1016/j.cej.2019.123412_b0015 article-title: Using machine learning to predict suitable conditions for organic reactions publication-title: ACS Cent. Sci. doi: 10.1021/acscentsci.8b00357 – ident: 10.1016/j.cej.2019.123412_b0135 – volume: 74 start-page: 3158 year: 2018 ident: 10.1016/j.cej.2019.123412_b0020 article-title: Enhanced process development using automated continuous reactors by self-optimisation algorithms and statistical empirical modelling publication-title: Tetrahedron doi: 10.1016/j.tet.2018.02.061 – volume: 9 start-page: 1 year: 2015 ident: 10.1016/j.cej.2019.123412_b0045 article-title: Automatic discovery and optimization of chemical processes publication-title: Curr. Opin. Chem. Eng. doi: 10.1016/j.coche.2015.07.001 – volume: 73 start-page: 116 year: 2015 ident: 10.1016/j.cej.2019.123412_b0105 article-title: A combined first-principles and data-driven approach to model building publication-title: Comput. Chem. Eng. doi: 10.1016/j.compchemeng.2014.11.010 – volume: 50 start-page: 1027 year: 2011 ident: 10.1016/j.cej.2019.123412_b0095 article-title: A conceptual framework for description of complexity in intensive chemical processes publication-title: Chem. Eng. Process. Process Intensif. doi: 10.1016/j.cep.2011.06.005 – volume: 24 start-page: 657 year: 2009 ident: 10.1016/j.cej.2019.123412_b0210 article-title: The global solver in the LINDO API publication-title: Optim. Methods Softw. doi: 10.1080/10556780902753221 – volume: 5 start-page: 21 year: 2014 ident: 10.1016/j.cej.2019.123412_b0085 article-title: Why model? publication-title: Front. Physiol. doi: 10.3389/fphys.2014.00021 – volume: 473 start-page: 0009 year: 2017 ident: 10.1016/j.cej.2019.123412_b0115 article-title: Model selection for dynamical systems via sparse regression and information criteria publication-title: Proc. R. Soc. A doi: 10.1098/rspa.2017.0009 – volume: 3 start-page: 434 year: 2017 ident: 10.1016/j.cej.2019.123412_b0005 article-title: Prediction of organic reaction outcomes using machine learning publication-title: ACS Cent. Sci. doi: 10.1021/acscentsci.7b00064 – volume: 94 start-page: 12214 year: 2016 ident: 10.1016/j.cej.2019.123412_b0235 article-title: Prediction of dynamical systems by symbolic regression publication-title: Phys. Rev. E. doi: 10.1103/PhysRevE.94.012214 – volume: 49 start-page: 7076 year: 2010 ident: 10.1016/j.cej.2019.123412_b0070 article-title: An integrated microreactor system for self-optimization of a heck reaction: from micro- to mesoscale flow systems publication-title: Angew. Chemie Int. Ed. doi: 10.1002/anie.201002590 – volume: 37 start-page: 707 year: 2015 ident: 10.1016/j.cej.2019.123412_b0170 article-title: A novel rigorous mathematical programming approach to construct phenomenological models publication-title: Comput. Aided Chem. Eng. doi: 10.1016/B978-0-444-63578-5.50113-4 – volume: 18 start-page: 1047 year: 1988 ident: 10.1016/j.cej.2019.123412_b0180 article-title: DAG—a program that draws directed graphs publication-title: Softw. Pract. Exp. doi: 10.1002/spe.4380181104 – volume: 3 start-page: e103 year: 2017 ident: 10.1016/j.cej.2019.123412_b0230 article-title: SymPy: symbolic computing in Python publication-title: PeerJ Comput. Sci. doi: 10.7717/peerj-cs.103 – volume: 104 start-page: 9943 year: 2007 ident: 10.1016/j.cej.2019.123412_b0155 article-title: Automated reverse engineering of nonlinear dynamical systems publication-title: Proc. Nat. Acad. Sci. doi: 10.1073/pnas.0609476104 – volume: 10 start-page: 370 year: 2019 ident: 10.1016/j.cej.2019.123412_b0025 article-title: A graph-convolutional neural network model for the prediction of chemical reactivity publication-title: Chem. Sci. doi: 10.1039/C8SC04228D – volume: 10 start-page: 3 year: 2008 ident: 10.1016/j.cej.2019.123412_b0075 article-title: Data-driven modelling: some past experiences and new approaches publication-title: J. Hydroinf. doi: 10.2166/hydro.2008.015 – ident: 10.1016/j.cej.2019.123412_b0165 – volume: 56 start-page: 10815 year: 2017 ident: 10.1016/j.cej.2019.123412_b0030 article-title: Human versus robots in the discovery and crystallization of gigantic polyoxometalates publication-title: Angew. Chem. Int. Ed. doi: 10.1002/anie.201705721 – volume: 7 start-page: 3582 year: 2017 ident: 10.1016/j.cej.2019.123412_b0035 article-title: Predicting the outcomes of organic reactions via machine learning: are current descriptors sufficient? publication-title: Sci. Rep. doi: 10.1038/s41598-017-02303-0 – volume: 333 start-page: 1423 year: 2011 ident: 10.1016/j.cej.2019.123412_b0060 article-title: A simple, multidimensional approach to high-throughput discovery of catalytic reactions publication-title: Science doi: 10.1126/science.1207922 – volume: 33 start-page: 563 year: 2018 ident: 10.1016/j.cej.2019.123412_b0215 article-title: SCIP: global optimization of mixed-integer nonlinear programs in a branch-and-cut framework publication-title: Optim. Methods Softw. doi: 10.1080/10556788.2017.1335312 – ident: 10.1016/j.cej.2019.123412_b0255 doi: 10.1021/ed081p870 – volume: 3 start-page: 219 year: 2011 ident: 10.1016/j.cej.2019.123412_b0225 article-title: Pyomo: modeling and solving mathematical programs in Python publication-title: Math. Program. Comput. doi: 10.1007/s12532-011-0026-8 – volume: 24 start-page: 597 year: 2009 ident: 10.1016/j.cej.2019.123412_b0205 article-title: Branching and bounds tightening techniques for non-convex MINLP publication-title: Optim. Methods Softw. doi: 10.1080/10556780903087124 – start-page: 215 year: 1974 ident: 10.1016/j.cej.2019.123412_b0240 article-title: A new look at the statistical model identification – volume: 473 start-page: 0446 year: 2017 ident: 10.1016/j.cej.2019.123412_b0130 article-title: Learning partial differential equations via data discovery and sparse optimization publication-title: Proc. R. Soc. A. doi: 10.1098/rspa.2016.0446 – volume: 202 start-page: 483 year: 2017 ident: 10.1016/j.cej.2019.123412_b0065 article-title: Automation of route identification and optimisation based on data-mining and chemical intuition publication-title: Faraday Discuss. doi: 10.1039/C7FD00073A – ident: 10.1016/j.cej.2019.123412_b0140 – volume: 3 start-page: 227 year: 2002 ident: 10.1016/j.cej.2019.123412_b0185 article-title: Review of nonlinear mixed-integer and disjunctive programming techniques publication-title: Optim. Eng. doi: 10.1023/A:1021039126272 – volume: 113 start-page: 3932 year: 2016 ident: 10.1016/j.cej.2019.123412_b0150 article-title: Discovering governing equations from data by sparse identification of nonlinear dynamical systems publication-title: Proc. Natl. Acad. Sci. U.S.A. doi: 10.1073/pnas.1517384113 |
| SSID | ssj0006919 |
| Score | 2.5302248 |
| Snippet | •Automated identification of physical laws from noisy experimental data demonstrated.•Symbolic regression problem is formulated using directed acyclic... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 123412 |
| SubjectTerms | Automated model construction Chemical process development Global optimization Mixed-integer nonlinear programming (MINLP) Model identification Symbolic regression |
| Title | A new formulation for symbolic regression to identify physico-chemical laws from experimental data |
| URI | https://dx.doi.org/10.1016/j.cej.2019.123412 |
| Volume | 387 |
| WOSCitedRecordID | wos000527331600014&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1873-3212 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0006919 issn: 1385-8947 databaseCode: AIEXJ dateStart: 19970115 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9QwELaWlgMcEE9RXvKBE1VWm9hx7OOqKgKEVkgt1d4i23FQVmlSbdJu6c_qL8SO7SRdKKIHLlFiOY6V-eQZj2e-AeB9FMosJjILhIp4gInkAZMMB6HWbpLqPRfqeApOviaLBV0u2bfJ5NrnwlyUSVXRy0t29l9Frdu0sE3q7B3E3Q-qG_S9Frq-arHr6z8Jfm6qhHdJia4yVxdJ2Pw8FYYCeH-tftjQ18qYnUWXp5t7D0cdSE8gUPJNY5NPbhQBcLlsA7uB768GYsOejsKUC-Em7Me6TY82RXtls4udJ4KRkSdiocyBQmXt2kbyPvbjgNfWfbBRRX9AdK5_o8-RL2vffKL3AkVZ8MxVebePdbN_NB37N6LZEE3olmRE44Ayy8vp12zktLRddbX2xTYY-zeFYH0Tq6lUKxPHx6ZD35vk21tKsQ9V9FFwq1QPkZohUjvEPbAbJTHTK-nu_PPh8kuv_wnrysn08_Zn6V1U4dY8_mwNjSyc48fgkduawLmF1BMwUdVT8HBEWPkMiDnU4IIjcJl76MEFB3DBtoYeXHAbXNCACxpwwTG4oAHXc_D94-HxwafAVekIJMKzNqCUiFAmeRJLkqAcK0FjJXIWa12BuOSEUhUKRQnHmVIKo1lGVU6YDHOahZFEL8BOVVfqJYCCIq6yWc5CoQ1dRWiOMxHhRGC9y8gStAdm_m-l0lHYm0oqZXqrlPbAh_6VM8vf8rfO2IsgdQaoNSxTDafbX3t1l2-8Bg8GlL8BO-36XL0F9-VFWzTrdw5LvwCgWaji |
| linkProvider | Elsevier |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+new+formulation+for+symbolic+regression+to+identify+physico-chemical+laws+from+experimental+data&rft.jtitle=Chemical+engineering+journal+%28Lausanne%2C+Switzerland+%3A+1996%29&rft.au=Neumann%2C+Pascal&rft.au=Cao%2C+Liwei&rft.au=Russo%2C+Danilo&rft.au=Vassiliadis%2C+Vassilios+S.&rft.date=2020-05-01&rft.issn=1385-8947&rft.volume=387&rft.spage=123412&rft_id=info:doi/10.1016%2Fj.cej.2019.123412&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_cej_2019_123412 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1385-8947&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1385-8947&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1385-8947&client=summon |