Interpretable machine learning prediction of the dielectric constant and bandgap of polymers for flexible electronics

dc.contributor.authorGül, Fatih
dc.date.accessioned2026-11-18T07:33:41Z
dc.date.issued2026
dc.departmentRTEÜ, Mühendislik ve Mimarlık Fakültesi, Elektrik-Elektronik Mühendisliği Bölümü
dc.description.abstractPolymer 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 (Formula presented.) (MAE (Formula presented.) eV) and the total dielectric constant (Formula presented.) (MAE (Formula presented.)), but paired tests find the models statistically indistinguishable for the bandgap. Decomposing the permittivity explains its lower ceiling: the ionic component is only (Formula presented.) of the magnitude yet carries (Formula presented.) 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—raise 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.
dc.identifier.citationGül, F. (2026). Interpretable Machine Learning Prediction of the Dielectric Constant and Bandgap of Polymers for Flexible Electronics. Polymers, 18(18), 2182. https://doi.org/10.3390/polym18182182
dc.identifier.doi10.3390/polym18182182
dc.identifier.issn2073-4360
dc.identifier.issue18
dc.identifier.scopus2-s2.0-105052619185
dc.identifier.scopusqualityQ1
dc.identifier.startpage2182
dc.identifier.urihttps://doi.org/10.3390/polym18182182
dc.identifier.urihttps://hdl.handle.net/11436/13818
dc.identifier.volume18
dc.indekslendigikaynakScopus
dc.institutionauthorGül, Fatih
dc.institutionauthorid0000-0001-5072-2122
dc.language.isoen
dc.publisherMultidisciplinary Digital Publishing Institute (MDPI)
dc.relation.ispartofPolymers
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subjectbandgap
dc.subjectdielectric constant
dc.subjectflexible electronics
dc.subjecthigh-throughput screening
dc.subjectinterpretable machine learning
dc.subjectmachine learning
dc.subjectpolymer informatics
dc.subjectSHAP
dc.titleInterpretable machine learning prediction of the dielectric constant and bandgap of polymers for flexible electronics
dc.typeArticle

Dosyalar

Orijinal paket

Listeleniyor 1 - 1 / 1
Yükleniyor...
Küçük Resim
İsim:
gül-2026 (7).pdf
Boyut:
1.91 MB
Biçim:
Adobe Portable Document Format

Lisans paketi

Listeleniyor 1 - 1 / 1
Yükleniyor...
Küçük Resim
İsim:
license.txt
Boyut:
1.17 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama: