{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T13:28:23Z","timestamp":1786368503230,"version":"build-2736575974"},"reference-count":54,"publisher":"American Chemical Society (ACS)","issue":"15","license":[{"start":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T00:00:00Z","timestamp":1781136000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T00:00:00Z","timestamp":1781136000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T00:00:00Z","timestamp":1781136000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council (EPSRC)","doi-asserted-by":"crossref","award":["EP\/Y029763\/1"],"award-info":[{"award-number":["EP\/Y029763\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,8,10]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Two-dimensional (2D) inorganic crystals are a class of materials that are gaining significant attention for use in electronic and optoelectronic devices. Among many other exciting applications, 2D materials offer a range of beneficial properties to such devices owing to charge carrier confinement, high carrier mobility, tunable band gaps, strong light\u2013matter interactions, and atomically thin geometries that enable excellent electrostatic control and mechanical flexibility. In parallel, data-driven approaches to predictions of inorganic material properties have gained considerable attention as computationally lightweight surrogate models for properties of interest. This is particularly important when screening candidate materials for particular sets of structure\u2013property relationships. Many of these approaches have targeted three-dimensional bulk crystalline materials. In this work, we develop a set of data-driven models for predicting the properties of 2D layered, van der Waals, and ultrathin film materials, namely, thermodynamic stability, metallicity, and electronic band gap. We train the models on materials sourced from open-source computational databases of 2D materials (Alexandria_2D, C2DB, MC2D, and 2DMatpedia) and use chemically relevant elemental, physical, and compositional features as input. The large feature space is reduced to a subset of critical features by a statistical and gradient-boosted feature selection strategy. The models are fully interpretable with feature relevance scores and SHapley Additive exPlanations analysis assessing the global and local influence of feature values. The classifiers for thermodynamic stability and metallicity achieve F1-scores of 0.832 and 0.870 and accuracies of 89.7% and 89.7%, respectively. The regressor model for the band gap achieves an R2 of 0.883, a mean-absolute error (MAE) of 0.317 eV, and a root-mean-squared error (RMSE) of 0.485 eV on the in-distribution test set. We assess the band gap predictor regressor against a 2D material band gap data set (N \u2208 177) manually extracted from the academic literature to quantify the model\u2019s ability to predict outside of the training distribution, achieving an R2 of 0.334, an MAE of 0.675 eV, and an RMSE of 0.961 eV. These results demonstrate the efficacy of feature selection in producing fully explainable machine learning surrogate models for high-throughput property prediction for 2D materials.<\/jats:p>","DOI":"10.1021\/acs.jcim.6c00675","type":"journal-article","created":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T09:43:28Z","timestamp":1781171008000},"page":"8772-8791","source":"Crossref","is-referenced-by-count":0,"title":["Band Gap Prediction of Two-Dimensional Materials Using\na Gradient-Boosted Feature Selection Approach"],"prefix":"10.1021","volume":"66","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7533-0579","authenticated-orcid":true,"given":"Ben D.","family":"Rowlinson","sequence":"first","affiliation":[{"name":"University of Edinburgh , , ,","place":["Edinburgh, U.K., EH9 3BF"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Subramanian","family":"Ramamoorthy","sequence":"additional","affiliation":[{"name":"University of Edinburgh , , ,","place":["Edinburgh, U.K., EH8 9AB"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1552-8743","authenticated-orcid":true,"given":"Jacqueline M.","family":"Cole","sequence":"additional","affiliation":[{"name":"University of Cambridge , , ,","place":["Cambridge, U.K., CB3 0US"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Themis","family":"Prodromakis","sequence":"additional","affiliation":[{"name":"University of Edinburgh , , ,","place":["Edinburgh, U.K., EH9 3BF"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,6,11]]},"reference":[{"key":"2026081008092407500_cit1","doi-asserted-by":"publisher","first-page":"666","DOI":"10.1126\/science.1102896","article-title":"Electric Field Effect\nin Atomically Thin Carbon Films","volume":"306","author":"Novoselov","year":"2004","journal-title":"Science"},{"key":"2026081008092407500_cit2","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1109\/LED.2007.891668","article-title":"A Graphene\nField-Effect\nDevice","volume":"28","author":"Lemme","year":"2007","journal-title":"IEEE Electron Device Lett."},{"key":"2026081008092407500_cit3","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1038\/s41586-025-08963-7","article-title":"A complementary two-dimensional material-based\none instruction set computer","volume":"642","author":"Ghosh","year":"2025","journal-title":"Nature"},{"key":"2026081008092407500_cit4","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1038\/s44287-024-00038-5","article-title":"3D integration\nof 2D electronics","volume":"1","author":"Jayachandran","year":"2024","journal-title":"Nat. Rev. Electr. Eng."},{"key":"2026081008092407500_cit5","doi-asserted-by":"publisher","first-page":"112218","DOI":"10.1016\/j.matdes.2023.112218","article-title":"Large-scale\nsynthesis of two-dimensional\nindium telluride films for broadband photodetectors","volume":"233","author":"Yang","year":"2023","journal-title":"Mater. Des."},{"key":"2026081008092407500_cit6","doi-asserted-by":"publisher","first-page":"103291","DOI":"10.1016\/j.isci.2021.103291","article-title":"2D Bi(2)Se(3)\nmaterials for optoelectronics","volume":"24","author":"Wang","year":"2021","journal-title":"iScience"},{"key":"2026081008092407500_cit7","doi-asserted-by":"publisher","first-page":"4882","DOI":"10.1021\/acs.chemmater.8b01707","article-title":"Optimal Bandgap in a 2D Ruddlesden\u2013Popper\nPerovskite Chalcogenide for Single-Junction Solar Cells","volume":"30","author":"Niu","year":"2018","journal-title":"Chem. Mater."},{"key":"2026081008092407500_cit8","doi-asserted-by":"publisher","first-page":"12722","DOI":"10.1021\/acs.nanolett.4c03321","article-title":"Bandgap\nEngineering of 2D Materials\ntoward High-Performing Straintronics","volume":"24","author":"Boland","year":"2024","journal-title":"Nano Lett."},{"key":"2026081008092407500_cit9","doi-asserted-by":"publisher","first-page":"014004","DOI":"10.1088\/2516-1075\/abd957","article-title":"Twistronics: a turning\npoint in 2D quantum materials","volume":"3","author":"Hennighausen","year":"2021","journal-title":"Electron. Struct."},{"key":"2026081008092407500_cit10","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.adm8825","article-title":"MoS2 phononic crystals for advanced\nthermal management","volume":"10","author":"Xiao","year":"2024","journal-title":"Sci. Adv."},{"key":"2026081008092407500_cit11","doi-asserted-by":"publisher","DOI":"10.1002\/adma.202401534","article-title":"Anisotropic 2D van der Waals Magnets Hosting 1D Spin\nChains","volume":"36","author":"Park","year":"2024","journal-title":"Adv. Mater."},{"key":"2026081008092407500_cit12","doi-asserted-by":"publisher","first-page":"113476","DOI":"10.1016\/j.commatsci.2024.113476","article-title":"Data driven insights\ninto the characteristics of wide bandgap semiconductors in 2D materials","volume":"246","author":"Balasubramanian","year":"2025","journal-title":"Comput. Mater. Sci."},{"key":"2026081008092407500_cit13","doi-asserted-by":"publisher","first-page":"011002","DOI":"10.1063\/1.4812323","article-title":"Commentary:\nThe Materials Project:\nA materials genome approach to accelerating materials innovation","volume":"1","author":"Jain","year":"2013","journal-title":"APL Mater."},{"key":"2026081008092407500_cit14","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1038\/s41597-019-0097-3","article-title":"2DMatPedia, an open\ncomputational\ndatabase of two-dimensional materials from top-down and bottom-up\napproaches","volume":"6","author":"Zhou","year":"2019","journal-title":"Sci. Data"},{"key":"2026081008092407500_cit15","doi-asserted-by":"publisher","first-page":"035007","DOI":"10.1088\/2053-1583\/accc43","article-title":"Symmetry-based\ncomputational search for novel binary and ternary 2D materials","volume":"10","author":"Wang","year":"2023","journal-title":"2D Mater."},{"key":"2026081008092407500_cit16","doi-asserted-by":"publisher","first-page":"101560","DOI":"10.1016\/j.mtphys.2024.101560","article-title":"Improving machine-learning\nmodels in materials science through large datasets","volume":"48","author":"Schmidt","year":"2024","journal-title":"Mater. Today Phys."},{"key":"2026081008092407500_cit17","doi-asserted-by":"publisher","first-page":"042002","DOI":"10.1088\/2053-1583\/aacfc1","article-title":"The Computational\n2D Materials Database: high-throughput modeling and discovery of atomically\nthin crystals","volume":"5","author":"Haastrup","year":"2018","journal-title":"2D Mater."},{"key":"2026081008092407500_cit18","doi-asserted-by":"publisher","first-page":"044002","DOI":"10.1088\/2053-1583\/ac1059","article-title":"Recent progress of the Computational 2D Materials Database (C2DB)","volume":"8","author":"Gjerding","year":"2021","journal-title":"2D Mater."},{"key":"2026081008092407500_cit19","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1038\/s41565-017-0035-5","article-title":"Two-dimensional materials from high-throughput\ncomputational exfoliation of experimentally known compounds","volume":"13","author":"Mounet","year":"2018","journal-title":"Nat. Nanotechnol."},{"key":"2026081008092407500_cit20","doi-asserted-by":"publisher","first-page":"11268","DOI":"10.1021\/acsnano.2c11510","article-title":"Expansion\nof the Materials Cloud 2D Database","volume":"17","author":"Campi","year":"2023","journal-title":"ACS Nano"},{"key":"2026081008092407500_cit21","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1021\/acs.accounts.9b00470","article-title":"A Design-to-Device\nPipeline for Data-Driven Materials Discovery","volume":"53","author":"Cole","year":"2020","journal-title":"Acc. Chem. Res."},{"key":"2026081008092407500_cit22","doi-asserted-by":"publisher","first-page":"033001","DOI":"10.1088\/2516-1075\/abbb25","article-title":"High-throughput\ndesign of magnetic materials","volume":"3","author":"Zhang","year":"2021","journal-title":"Electron. Struct."},{"key":"2026081008092407500_cit23","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1038\/s41586-023-06735-9","article-title":"Scaling deep learning\nfor materials discovery","volume":"624","author":"Merchant","year":"2023","journal-title":"Nature"},{"key":"2026081008092407500_cit24","doi-asserted-by":"publisher","first-page":"624","DOI":"10.1038\/s41586-025-08628-5","article-title":"A generative model for inorganic materials design","volume":"639","author":"Zeni","year":"2025","journal-title":"Nature"},{"key":"2026081008092407500_cit25","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1038\/s41524-024-01474-5","article-title":"Deep reinforcement\nlearning for inverse inorganic materials\ndesign","volume":"10","author":"Karpovich","year":"2024","journal-title":"npj Comput. Mater."},{"key":"2026081008092407500_cit26","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1038\/s41524-022-00765-z","article-title":"Accelerating\nmaterials discovery using artificial intelligence, high performance\ncomputing and robotics","volume":"8","author":"Pyzer-Knapp","year":"2022","journal-title":"npj Comput. Mater."},{"key":"2026081008092407500_cit27","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1038\/s41699-020-00162-4","article-title":"Bandgap engineering of two-dimensional semiconductor\nmaterials","volume":"4","author":"Chaves","year":"2020","journal-title":"npj 2D Mater. Appl."},{"key":"2026081008092407500_cit28","doi-asserted-by":"publisher","first-page":"468","DOI":"10.1038\/s41467-022-28122-0","article-title":"Representing individual electronic\nstates for machine\nlearning GW band structures of 2D materials","volume":"13","author":"Knosgaard","year":"2022","journal-title":"Nat. Commun."},{"key":"2026081008092407500_cit29","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1038\/s41586-021-03472-9","article-title":"Ultralow contact resistance\nbetween semimetal and monolayer semiconductors","volume":"593","author":"Shen","year":"2021","journal-title":"Nature"},{"key":"2026081008092407500_cit30","doi-asserted-by":"crossref","unstructured":"Yang, N.; et al.; Computational Screening and Multiscale Simulation\nof Barrier-Free\nContacts for 2D Semiconductor pFETs,  2022\nInternational Electron Devices Meeting (IEDM), 2022.","DOI":"10.1109\/IEDM45625.2022.10019377"},{"key":"2026081008092407500_cit31","doi-asserted-by":"publisher","first-page":"194106","DOI":"10.1063\/5.0171540","article-title":"Gradient\nboosted and statistical\nfeature selection workflow for materials property predictions","volume":"159","author":"Jung","year":"2023","journal-title":"J. Chem. Phys."},{"key":"2026081008092407500_cit32","doi-asserted-by":"publisher","first-page":"3865","DOI":"10.1103\/PhysRevLett.77.3865","article-title":"Generalized\nGradient Approximation\nMade Simple","volume":"77","author":"Perdew","year":"1996","journal-title":"Phys. Rev. Lett."},{"key":"2026081008092407500_cit33","doi-asserted-by":"publisher","first-page":"224106","DOI":"10.1063\/1.2404663","article-title":"Influence of the\nexchange screening parameter on the performance of screened hybrid\nfunctionals","volume":"125","author":"Krukau","year":"2006","journal-title":"J. Chem. Phys."},{"key":"2026081008092407500_cit34","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1038\/s41524-020-00375-7","article-title":"An artificial intelligence-aided\nvirtual screening recipe for two-dimensional materials discovery","volume":"6","author":"Sorkun","year":"2020","journal-title":"npj Comput. Mater."},{"key":"2026081008092407500_cit35","doi-asserted-by":"publisher","first-page":"755","DOI":"10.1038\/s41586-024-07566-y","article-title":"AI models\ncollapse when trained on recursively generated data","volume":"631","author":"Shumailov","year":"2024","journal-title":"Nature"},{"key":"2026081008092407500_cit36","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1038\/s41597-021-00974-z","article-title":"OPTIMADE, an API for\nexchanging materials data","volume":"8","author":"Andersen","year":"2021","journal-title":"Sci. Data"},{"key":"2026081008092407500_cit37","doi-asserted-by":"publisher","first-page":"1198","DOI":"10.1021\/acs.jpclett.5b02870","article-title":"Resolution of\nthe Band Gap Prediction\nProblem for Materials Design","volume":"7","author":"Crowley","year":"2016","journal-title":"J. Phys. Chem.\nLett."},{"key":"2026081008092407500_cit38","doi-asserted-by":"publisher","first-page":"1777","DOI":"10.1021\/acsaelm.0c00105","article-title":"Synthesis and Applications\nof Wide Bandgap 2D Layered\nSemiconductors Reaching the Green and Blue Wavelengths","volume":"2","author":"Lu","year":"2020","journal-title":"ACS Appl. Electron. Mater."},{"key":"2026081008092407500_cit39","doi-asserted-by":"publisher","first-page":"6475","DOI":"10.1021\/acs.nanolett.9b02700","article-title":"Two-Dimensional Covalent Crystals by Chemical Conversion of Thin\nvan der Waals Materials","volume":"19","author":"Sreepal","year":"2019","journal-title":"Nano Lett."},{"key":"2026081008092407500_cit40","doi-asserted-by":"publisher","first-page":"314","DOI":"10.1016\/j.commatsci.2012.10.028","article-title":"Python Materials Genomics\n(pymatgen): A robust, open-source python\nlibrary for materials analysis","volume":"68","author":"Ong","year":"2013","journal-title":"Comput. Mater.\nSci."},{"key":"2026081008092407500_cit41","volume-title":"Machine Learning:\nA Probabilistic Perspective","author":"Murphy","year":"2012"},{"key":"2026081008092407500_cit42","first-page":"1929","article-title":"Dropout: a\nsimple way to prevent neural networks from\noverfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"2026081008092407500_cit43","unstructured":"Ke, G.; Meng, Q.; Finley, T.; Wang, T.; Chen, W.; Ma, W.; Ye, Q.; Liu, T.-Y.\n          LightGBM: A Highly Efficient Gradient Boosting Decision\nTree.  31st Conference on Neural Information\nProcessing Systems, 2017; pp 3149\u20133157."},{"key":"2026081008092407500_cit44","doi-asserted-by":"publisher","first-page":"arXiv:1705.07874","DOI":"10.48550\/arXiv.1705.07874","article-title":"A Unified\nApproach to Interpreting Model Predictions","author":"Lundberg","year":"2017","journal-title":"arXiv"},{"key":"2026081008092407500_cit45","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From Local Explanations to Global\nUnderstanding with Explainable AI for Trees","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nat. Mach. Intell."},{"key":"2026081008092407500_cit46","doi-asserted-by":"publisher","first-page":"1187","DOI":"10.1021\/acs.jcim.3c01897","article-title":"Automatic\nPrediction of Band Gaps\nof Inorganic Materials Using a Gradient Boosted and Statistical Feature\nSelection Workflow","volume":"64","author":"Jung","year":"2024","journal-title":"J. Chem. Inf. Model."},{"key":"2026081008092407500_cit47","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1038\/s41524-020-00362-y","article-title":"A critical examination of compound\nstability predictions from machine-learned\nformation energies","volume":"6","author":"Bartel","year":"2020","journal-title":"npj Comput. Mater."},{"key":"2026081008092407500_cit48","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.aaq0148","article-title":"Thermodynamic\nlimit\nfor synthesis of metastable inorganic materials","volume":"4","author":"Aykol","year":"2018","journal-title":"Sci. Adv."},{"key":"2026081008092407500_cit49","doi-asserted-by":"publisher","first-page":"4168","DOI":"10.1038\/s41467-018-06682-4","article-title":"Physical descriptor\nfor the Gibbs\nenergy of inorganic crystalline solids and temperature-dependent materials\nchemistry","volume":"9","author":"Bartel","year":"2018","journal-title":"Nat. Commun."},{"key":"2026081008092407500_cit50","doi-asserted-by":"publisher","first-page":"091103","DOI":"10.1063\/5.0277611","article-title":"Machine learning prediction of thermodynamic stability\nand electronic properties of 2D layered conductive metal\u2013organic\nframeworks","volume":"13","author":"Zhang","year":"2025","journal-title":"APL Mater."},{"key":"2026081008092407500_cit51","doi-asserted-by":"publisher","DOI":"10.1002\/advs.202305277","article-title":"When\nMachine Learning Meets 2D Materials:\nA Review","volume":"11","author":"Lu","year":"2024","journal-title":"Adv. Sci."},{"key":"2026081008092407500_cit52","doi-asserted-by":"publisher","first-page":"26736","DOI":"10.1038\/s41598-024-77081-7","article-title":"Machine learning-enhanced\nband gaps prediction for low-symmetry double and layered perovskites","volume":"14","author":"Sabagh Moeini","year":"2024","journal-title":"Sci. Rep."},{"key":"2026081008092407500_cit53","doi-asserted-by":"publisher","first-page":"9633","DOI":"10.1021\/acs.chemrev.4c00055","article-title":"Self-Driving Laboratories\nfor Chemistry and Materials Science","volume":"124","author":"Tom","year":"2024","journal-title":"Chem. Rev."},{"key":"2026081008092407500_cit54","doi-asserted-by":"publisher","first-page":"A796","DOI":"10.1103\/PhysRev.139.A796","article-title":"New Method\nfor Calculating the One-Particle Green\u2019s Function with Application\nto the Electron-Gas Problem","volume":"139","author":"Hedin","year":"1965","journal-title":"Phys. Rev."}],"container-title":["Journal of Chemical Information and Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.6c00675","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/15\/8772\/66257628\/acs.jcim.6c00675.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/15\/8772\/66257628\/acs.jcim.6c00675.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T12:32:15Z","timestamp":1786365135000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article\/66\/15\/8772\/5232515\/Band-Gap-Prediction-of-Two-Dimensional-Materials"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,11]]},"references-count":54,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2026,6,11]]},"published-print":{"date-parts":[[2026,8,10]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.jcim.6c00675","relation":{},"ISSN":["1549-9596","1549-960X"],"issn-type":[{"value":"1549-9596","type":"print"},{"value":"1549-960X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,11]]}}}