{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T09:08:31Z","timestamp":1788858511626,"version":"build-2803163510"},"reference-count":35,"publisher":"MDPI AG","issue":"18","license":[{"start":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T00:00:00Z","timestamp":1788825600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Recep Tayyip Erdo\u011fan University Development Foundation","award":["020260070090469"],"award-info":[{"award-number":["020260070090469"]}]},{"award":["020260070090469"],"award-info":[{"award-number":["020260070090469"]}],"id":[{"id":"https:\/\/ror.org\/0468j1635","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Polymers"],"abstract":"<jats:p>Polymer dielectrics are central to flexible and printed electronics, where a material must combine a sufficiently high dielectric constant with a wide electronic bandgap to suppress leakage. Experimental or first-principles screening is slow, motivating data-driven surrogates. Here we develop an interpretable machine learning workflow that predicts both the total dielectric constant and the HSE bandgap of polymer repeat units directly from a monomer structure, using an open density-functional-theory dataset of 284 four-block polymers. Polymers are encoded with 217 RDKit descriptors and a 1024-bit Morgan fingerprint; four regressors are benchmarked under nested five-fold cross-validation with paired significance testing. The bandgap reaches R2=0.83\u00b10.04 (MAE =0.35 eV) and the total dielectric constant R2=0.64\u00b10.06 (MAE =0.44), but paired tests find the models statistically indistinguishable for the bandgap. Decomposing the permittivity explains its lower ceiling: the ionic component is only 15% of the magnitude yet carries 28% of the squared error, and learning curves confirm a representational rather than a data-quantity limit. Read through the Penn relation, the SHAP descriptors yield an explicit design rule\u2014raise permittivity with polar, non-conjugated motifs rather than extended conjugation. Screening 571 unseen candidates with bootstrap uncertainties, an applicability domain and a threshold sensitivity analysis nominates carbamate\/urea-type wide-bandgap high-k repeat units.<\/jats:p>","DOI":"10.3390\/polym18182182","type":"journal-article","created":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T08:10:22Z","timestamp":1788855022000},"page":"2182","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Interpretable Machine Learning Prediction of the Dielectric Constant and Bandgap of Polymers for Flexible Electronics"],"prefix":"10.3390","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5072-2122","authenticated-orcid":false,"given":"Fatih","family":"G\u00fcl","sequence":"first","affiliation":[{"name":"Artificial Intelligence and Internet of Things Research Laboratory, Department of Electrical-Electronics Engineering, Recep Tayyip Erdo\u011fan University, Rize 53100, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,8]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1021\/cr9001275","article-title":"High-k Organic, Inorganic, and Hybrid Dielectrics for Low-Voltage Organic Field-Effect Transistors","volume":"110","author":"Ortiz","year":"2010","journal-title":"Chem. Rev."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"733","DOI":"10.1021\/cm102419z","article-title":"\u03c0-Conjugated Polymers for Organic Electronics and Photovoltaic Cell Applications","volume":"23","author":"Facchetti","year":"2011","journal-title":"Chem. Mater."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"4845","DOI":"10.1038\/ncomms5845","article-title":"Rational Design of All Organic Polymer Dielectrics","volume":"5","author":"Sharma","year":"2014","journal-title":"Nat. Commun."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"2308670","DOI":"10.1002\/adma.202308670","article-title":"Engineering the Dielectric Constants of Polymers: From Molecular to Mesoscopic Scales","volume":"36","author":"Chen","year":"2023","journal-title":"Adv. Mater."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"20952","DOI":"10.1038\/srep20952","article-title":"Machine Learning Strategy for Accelerated Design of Polymer Dielectrics","volume":"6","author":"Pilania","year":"2016","journal-title":"Sci. Rep."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"160012","DOI":"10.1038\/sdata.2016.12","article-title":"A Polymer Dataset for Accelerated Property Prediction and Design","volume":"3","author":"Huan","year":"2016","journal-title":"Sci. Data"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1038\/s41524-017-0056-5","article-title":"Machine Learning in Materials Informatics: Recent Applications and Prospects","volume":"3","author":"Ramprasad","year":"2017","journal-title":"npj Comput. Mater."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1078","DOI":"10.1021\/acsmacrolett.7b00228","article-title":"Polymer Informatics: Opportunities and Challenges","volume":"6","author":"Audus","year":"2017","journal-title":"ACS Macro Lett."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"100595","DOI":"10.1016\/j.mser.2020.100595","article-title":"Polymer Informatics: Current Status and Critical Next Steps","volume":"144","author":"Chen","year":"2021","journal-title":"Mater. Sci. Eng. R"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"866","DOI":"10.1038\/s41578-024-00708-8","article-title":"Design of functional and sustainable polymers assisted by artificial intelligence","volume":"9","author":"Tran","year":"2024","journal-title":"Nat. Rev. Mater."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"10486","DOI":"10.1039\/D2SC02839E","article-title":"A graph representation of molecular ensembles for polymer property prediction","volume":"13","author":"Aldeghi","year":"2022","journal-title":"Chem. Sci."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1560","DOI":"10.1021\/acs.chemmater.2c02991","article-title":"Polymer Informatics at Scale with Multitask Graph Neural Networks","volume":"35","author":"Gurnani","year":"2023","journal-title":"Chem. Mater."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1038\/s41524-023-01034-3","article-title":"Polymer graph neural networks for multitask property learning","volume":"9","author":"Queen","year":"2023","journal-title":"npj Comput. Mater."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1038\/s41524-023-01016-5","article-title":"TransPolymer: A Transformer-Based Language Model for Polymer Property Predictions","volume":"9","author":"Xu","year":"2023","journal-title":"npj Comput. Mater."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"4099","DOI":"10.1038\/s41467-023-39868-6","article-title":"polyBERT: A Chemical Language Model to Enable Fully Machine-Driven Ultrafast Polymer Informatics","volume":"14","author":"Kuenneth","year":"2023","journal-title":"Nat. Commun."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"17575","DOI":"10.1021\/acs.jpcc.8b02913","article-title":"Polymer Genome: A Data-Powered Polymer Informatics Platform for Property Predictions","volume":"122","author":"Kim","year":"2018","journal-title":"J. Phys. Chem. C"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"171104","DOI":"10.1063\/5.0023759","article-title":"Machine-Learning Predictions of Polymer Properties with Polymer Genome","volume":"128","author":"Kim","year":"2020","journal-title":"J. Appl. Phys."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"4684","DOI":"10.1021\/acs.jcim.0c00726","article-title":"PI1M: A Benchmark Database for Polymer Informatics","volume":"60","author":"Ma","year":"2020","journal-title":"J. Chem. Inf. Model."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"127603","DOI":"10.1016\/j.polymer.2024.127603","article-title":"Multi-property prediction and high-throughput screening of polyimides: An application case for interpretable machine learning","volume":"312","author":"Zhang","year":"2024","journal-title":"Polymer"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2809","DOI":"10.1021\/acsapm.4c03279","article-title":"Machine Learning Model for Predicting Dielectric Constant of Epoxy Resin with Additional Data Selection and Design of Monomer Structures for Low Dielectric Constant","volume":"7","author":"Shiraki","year":"2025","journal-title":"ACS Appl. Polym. Mater."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Rahman, M.H., Arifuzzaman, M., Haque, M.E., Naidu, R.S., Hoque, M.E., and Martuza, M.A. (2026). Machine Learning-Based Prediction of Polymer Properties Using Structure\u2013Property Relationship Modeling. Polymers, 18.","DOI":"10.20944\/preprints202605.0833.v1"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"123732","DOI":"10.1016\/j.ces.2026.123732","article-title":"Machine learning with physically grounded, interpretable descriptors for polymer property prediction and monomer design","volume":"328","author":"Averochkin","year":"2026","journal-title":"Chem. Eng. Sci."},{"key":"ref_23","unstructured":"Landrum, G. (2026, July 03). RDKit: Open-Source Cheminformatics. Available online: https:\/\/www.rdkit.org."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"742","DOI":"10.1021\/ci100050t","article-title":"Extended-Connectivity Fingerprints","volume":"50","author":"Rogers","year":"2010","journal-title":"J. Chem. Inf. Model."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016, January 13\u201317). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_27","unstructured":"Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., and Liu, T.-Y. (2017, January 4\u20139). LightGBM: A Highly Efficient Gradient Boosting Decision Tree. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_28","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"025006","DOI":"10.1088\/2632-2153\/ab7e1a","article-title":"Methods for comparing uncertainty quantifications for material property predictions","volume":"1","author":"Tran","year":"2020","journal-title":"Mach. Learn. Sci. Technol."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1912","DOI":"10.1021\/ci049782w","article-title":"Similarity to Molecules in the Training Set Is a Good Discriminator for Prediction Accuracy in QSAR","volume":"44","author":"Sheridan","year":"2004","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"ref_31","unstructured":"Lundberg, S.M., and Lee, S.I. (2017, January 4\u20139). A Unified Approach to Interpreting Model Predictions. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"2093","DOI":"10.1103\/PhysRev.128.2093","article-title":"Wave-Number-Dependent Dielectric Function of Semiconductors","volume":"128","author":"Penn","year":"1962","journal-title":"Phys. Rev."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1088\/0370-1301\/63\/3\/302","article-title":"A Relationship between the Refractive Index and the Infra-Red Threshold of Sensitivity for Photoconductors","volume":"63","author":"Moss","year":"1950","journal-title":"Proc. Phys. Soc. B"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"6128","DOI":"10.1038\/s41598-017-06357-y","article-title":"Electronic Structure of Polyethylene: Role of Chemical, Morphological and Interfacial Complexity","volume":"7","author":"Chen","year":"2017","journal-title":"Sci. Rep."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"7699","DOI":"10.1021\/acs.chemmater.8b02997","article-title":"Electronic Structure of Polymer Dielectrics: The Role of Chemical and Morphological Complexity","volume":"30","author":"Chen","year":"2018","journal-title":"Chem. Mater."}],"container-title":["Polymers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-4360\/18\/18\/2182\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T08:21:39Z","timestamp":1788855699000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-4360\/18\/18\/2182"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,8]]},"references-count":35,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["polym18182182"],"URL":"https:\/\/doi.org\/10.3390\/polym18182182","relation":{},"ISSN":["2073-4360"],"issn-type":[{"value":"2073-4360","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,8]]}}}