Transfer Learning-Enhanced Prediction of Glass Transition Temperature in Bismaleimide-Based Polyimides Article Swipe
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.20944/preprints202505.1953.v1
The glass transition temperature (Tg) is a pivotal parameter governing the thermal and mechanical properties of bismaleimide-based polyimide (BMI) resins. However, limited experimental data for BMI systems posed significant challenges for predictive modeling. To address this gap, this study introduces a hybrid modeling framework leveraging transfer learning. Specifically, a multilayer perceptron (MLP) deep neural network is pre-trained on a large-scale polymer database and subsequently fine-tuned on a small-sample BMI dataset. Complementing this approach, six interpretable machine learning algorithms—Random Forest, Ridge Regression, K-Nearest Neighbors, Bayesian Regression, Support Vector Regression, and Extreme Gradient Boosting —are employed to construct transparent predictive models. SHapley Additive exPlanations (SHAP) analysis is further utilized to quantify the relative contributions of molecular descriptors to Tg. Results demonstrate that the transfer learning strategy achieves superior predictive accuracy in data-scarce scenarios compared to direct training on BMI dataset. SHAP analysis identified charge distribution inhomogeneity, molecular topology, and molecular surface area properties as the major influences on Tg. This integrated framework not only improves the prediction performance, but also provides feasible insights into molecular structure design, laying a solid foundation for rational engineering of high-performance BMI resins.
Related Topics
- Type
- preprint
- Language
- en
- Landing Page
- https://doi.org/10.20944/preprints202505.1953.v1
- https://www.preprints.org/frontend/manuscript/d47d8fb8ee63fe697adcfa34207a88d5/download_pub
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4410768385
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4410768385Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.20944/preprints202505.1953.v1Digital Object Identifier
- Title
-
Transfer Learning-Enhanced Prediction of Glass Transition Temperature in Bismaleimide-Based PolyimidesWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-05-26Full publication date if available
- Authors
-
Ziqi Wang, Yu Liu, Xintong Xu, Jiale Zhang, Zongjin Li, Lei Zheng, Kang PengList of authors in order
- Landing page
-
https://doi.org/10.20944/preprints202505.1953.v1Publisher landing page
- PDF URL
-
https://www.preprints.org/frontend/manuscript/d47d8fb8ee63fe697adcfa34207a88d5/download_pubDirect link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://www.preprints.org/frontend/manuscript/d47d8fb8ee63fe697adcfa34207a88d5/download_pubDirect OA link when available
- Concepts
-
Glass transition, Materials science, Composite material, Thermodynamics, Engineering physics, Physics, PolymerTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4410768385 |
|---|---|
| doi | https://doi.org/10.20944/preprints202505.1953.v1 |
| ids.doi | https://doi.org/10.20944/preprints202505.1953.v1 |
| ids.openalex | https://openalex.org/W4410768385 |
| fwci | 0.0 |
| type | preprint |
| title | Transfer Learning-Enhanced Prediction of Glass Transition Temperature in Bismaleimide-Based Polyimides |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T12084 |
| topics[0].field.id | https://openalex.org/fields/25 |
| topics[0].field.display_name | Materials Science |
| topics[0].score | 0.9987999796867371 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/2507 |
| topics[0].subfield.display_name | Polymers and Plastics |
| topics[0].display_name | Synthesis and properties of polymers |
| topics[1].id | https://openalex.org/T10660 |
| topics[1].field.id | https://openalex.org/fields/25 |
| topics[1].field.display_name | Materials Science |
| topics[1].score | 0.9765999913215637 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2507 |
| topics[1].subfield.display_name | Polymers and Plastics |
| topics[1].display_name | Conducting polymers and applications |
| topics[2].id | https://openalex.org/T12570 |
| topics[2].field.id | https://openalex.org/fields/16 |
| topics[2].field.display_name | Chemistry |
| topics[2].score | 0.9606999754905701 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1605 |
| topics[2].subfield.display_name | Organic Chemistry |
| topics[2].display_name | Photopolymerization techniques and applications |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C122865956 |
| concepts[0].level | 3 |
| concepts[0].score | 0.7952425479888916 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q825643 |
| concepts[0].display_name | Glass transition |
| concepts[1].id | https://openalex.org/C192562407 |
| concepts[1].level | 0 |
| concepts[1].score | 0.6073200106620789 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q228736 |
| concepts[1].display_name | Materials science |
| concepts[2].id | https://openalex.org/C159985019 |
| concepts[2].level | 1 |
| concepts[2].score | 0.41241759061813354 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q181790 |
| concepts[2].display_name | Composite material |
| concepts[3].id | https://openalex.org/C97355855 |
| concepts[3].level | 1 |
| concepts[3].score | 0.35350361466407776 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q11473 |
| concepts[3].display_name | Thermodynamics |
| concepts[4].id | https://openalex.org/C61696701 |
| concepts[4].level | 1 |
| concepts[4].score | 0.3292333483695984 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q770766 |
| concepts[4].display_name | Engineering physics |
| concepts[5].id | https://openalex.org/C121332964 |
| concepts[5].level | 0 |
| concepts[5].score | 0.16341596841812134 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[5].display_name | Physics |
| concepts[6].id | https://openalex.org/C521977710 |
| concepts[6].level | 2 |
| concepts[6].score | 0.15937820076942444 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q81163 |
| concepts[6].display_name | Polymer |
| keywords[0].id | https://openalex.org/keywords/glass-transition |
| keywords[0].score | 0.7952425479888916 |
| keywords[0].display_name | Glass transition |
| keywords[1].id | https://openalex.org/keywords/materials-science |
| keywords[1].score | 0.6073200106620789 |
| keywords[1].display_name | Materials science |
| keywords[2].id | https://openalex.org/keywords/composite-material |
| keywords[2].score | 0.41241759061813354 |
| keywords[2].display_name | Composite material |
| keywords[3].id | https://openalex.org/keywords/thermodynamics |
| keywords[3].score | 0.35350361466407776 |
| keywords[3].display_name | Thermodynamics |
| keywords[4].id | https://openalex.org/keywords/engineering-physics |
| keywords[4].score | 0.3292333483695984 |
| keywords[4].display_name | Engineering physics |
| keywords[5].id | https://openalex.org/keywords/physics |
| keywords[5].score | 0.16341596841812134 |
| keywords[5].display_name | Physics |
| keywords[6].id | https://openalex.org/keywords/polymer |
| keywords[6].score | 0.15937820076942444 |
| keywords[6].display_name | Polymer |
| language | en |
| locations[0].id | doi:10.20944/preprints202505.1953.v1 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S6309402219 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | Preprints.org |
| locations[0].source.host_organization | |
| locations[0].source.host_organization_name | |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310310987 |
| locations[0].source.host_organization_lineage_names | Multidisciplinary Digital Publishing Institute |
| locations[0].license | cc-by |
| locations[0].pdf_url | https://www.preprints.org/frontend/manuscript/d47d8fb8ee63fe697adcfa34207a88d5/download_pub |
| locations[0].version | acceptedVersion |
| locations[0].raw_type | posted-content |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | True |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | https://doi.org/10.20944/preprints202505.1953.v1 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5100438232 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-5420-0145 |
| authorships[0].author.display_name | Ziqi Wang |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Ziqi Wang |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5100345669 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-8928-2558 |
| authorships[1].author.display_name | Yu Liu |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Yu Liu |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5050124053 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-2261-7525 |
| authorships[2].author.display_name | Xintong Xu |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Xintong Xu |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5100744176 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-2143-5666 |
| authorships[3].author.display_name | Jiale Zhang |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Jiale Zhang |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5011466881 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-8477-6863 |
| authorships[4].author.display_name | Zongjin Li |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Zhen Li |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5035145736 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-3637-7198 |
| authorships[5].author.display_name | Lei Zheng |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Lei Zheng |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5101460932 |
| authorships[6].author.orcid | https://orcid.org/0000-0002-1405-3272 |
| authorships[6].author.display_name | Kang Peng |
| authorships[6].author_position | last |
| authorships[6].raw_author_name | Peng Kang |
| authorships[6].is_corresponding | False |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://www.preprints.org/frontend/manuscript/d47d8fb8ee63fe697adcfa34207a88d5/download_pub |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Transfer Learning-Enhanced Prediction of Glass Transition Temperature in Bismaleimide-Based Polyimides |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T12084 |
| primary_topic.field.id | https://openalex.org/fields/25 |
| primary_topic.field.display_name | Materials Science |
| primary_topic.score | 0.9987999796867371 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/2507 |
| primary_topic.subfield.display_name | Polymers and Plastics |
| primary_topic.display_name | Synthesis and properties of polymers |
| related_works | https://openalex.org/W2899084033, https://openalex.org/W4404995717, https://openalex.org/W2016187641, https://openalex.org/W4404725684, https://openalex.org/W4246450666, https://openalex.org/W4388998267, https://openalex.org/W4409278740, https://openalex.org/W2898370298, https://openalex.org/W4410118003, https://openalex.org/W2137437058 |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | doi:10.20944/preprints202505.1953.v1 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S6309402219 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | Preprints.org |
| best_oa_location.source.host_organization | |
| best_oa_location.source.host_organization_name | |
| best_oa_location.source.host_organization_lineage | https://openalex.org/P4310310987 |
| best_oa_location.source.host_organization_lineage_names | Multidisciplinary Digital Publishing Institute |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | https://www.preprints.org/frontend/manuscript/d47d8fb8ee63fe697adcfa34207a88d5/download_pub |
| best_oa_location.version | acceptedVersion |
| best_oa_location.raw_type | posted-content |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | https://doi.org/10.20944/preprints202505.1953.v1 |
| primary_location.id | doi:10.20944/preprints202505.1953.v1 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S6309402219 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | Preprints.org |
| primary_location.source.host_organization | |
| primary_location.source.host_organization_name | |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310310987 |
| primary_location.source.host_organization_lineage_names | Multidisciplinary Digital Publishing Institute |
| primary_location.license | cc-by |
| primary_location.pdf_url | https://www.preprints.org/frontend/manuscript/d47d8fb8ee63fe697adcfa34207a88d5/download_pub |
| primary_location.version | acceptedVersion |
| primary_location.raw_type | posted-content |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | True |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | https://doi.org/10.20944/preprints202505.1953.v1 |
| publication_date | 2025-05-26 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 6, 40, 48, 58, 66, 176 |
| abstract_inverted_index.To | 33 |
| abstract_inverted_index.as | 151 |
| abstract_inverted_index.in | 128 |
| abstract_inverted_index.is | 5, 55, 104 |
| abstract_inverted_index.of | 15, 112, 182 |
| abstract_inverted_index.on | 57, 65, 135, 155 |
| abstract_inverted_index.to | 94, 107, 115, 132 |
| abstract_inverted_index.BMI | 25, 68, 136, 184 |
| abstract_inverted_index.Tg. | 116, 156 |
| abstract_inverted_index.The | 0 |
| abstract_inverted_index.and | 12, 62, 88, 146 |
| abstract_inverted_index.but | 166 |
| abstract_inverted_index.for | 24, 30, 179 |
| abstract_inverted_index.not | 160 |
| abstract_inverted_index.six | 73 |
| abstract_inverted_index.the | 10, 109, 120, 152, 163 |
| abstract_inverted_index.(Tg) | 4 |
| abstract_inverted_index.SHAP | 138 |
| abstract_inverted_index.This | 157 |
| abstract_inverted_index.also | 167 |
| abstract_inverted_index.area | 149 |
| abstract_inverted_index.data | 23 |
| abstract_inverted_index.deep | 52 |
| abstract_inverted_index.gap, | 36 |
| abstract_inverted_index.into | 171 |
| abstract_inverted_index.only | 161 |
| abstract_inverted_index.that | 119 |
| abstract_inverted_index.this | 35, 37, 71 |
| abstract_inverted_index.(BMI) | 18 |
| abstract_inverted_index.(MLP) | 51 |
| abstract_inverted_index.Ridge | 79 |
| abstract_inverted_index.glass | 1 |
| abstract_inverted_index.major | 153 |
| abstract_inverted_index.posed | 27 |
| abstract_inverted_index.solid | 177 |
| abstract_inverted_index.study | 38 |
| abstract_inverted_index.(SHAP) | 102 |
| abstract_inverted_index.Vector | 86 |
| abstract_inverted_index.charge | 141 |
| abstract_inverted_index.direct | 133 |
| abstract_inverted_index.hybrid | 41 |
| abstract_inverted_index.laying | 175 |
| abstract_inverted_index.neural | 53 |
| abstract_inverted_index.—are | 92 |
| abstract_inverted_index.Extreme | 89 |
| abstract_inverted_index.Forest, | 78 |
| abstract_inverted_index.Results | 117 |
| abstract_inverted_index.SHapley | 99 |
| abstract_inverted_index.Support | 85 |
| abstract_inverted_index.address | 34 |
| abstract_inverted_index.design, | 174 |
| abstract_inverted_index.further | 105 |
| abstract_inverted_index.limited | 21 |
| abstract_inverted_index.machine | 75 |
| abstract_inverted_index.models. | 98 |
| abstract_inverted_index.network | 54 |
| abstract_inverted_index.pivotal | 7 |
| abstract_inverted_index.polymer | 60 |
| abstract_inverted_index.resins. | 19, 185 |
| abstract_inverted_index.surface | 148 |
| abstract_inverted_index.systems | 26 |
| abstract_inverted_index.thermal | 11 |
| abstract_inverted_index.Additive | 100 |
| abstract_inverted_index.Bayesian | 83 |
| abstract_inverted_index.Boosting | 91 |
| abstract_inverted_index.Gradient | 90 |
| abstract_inverted_index.However, | 20 |
| abstract_inverted_index.accuracy | 127 |
| abstract_inverted_index.achieves | 124 |
| abstract_inverted_index.analysis | 103, 139 |
| abstract_inverted_index.compared | 131 |
| abstract_inverted_index.database | 61 |
| abstract_inverted_index.dataset. | 69, 137 |
| abstract_inverted_index.employed | 93 |
| abstract_inverted_index.feasible | 169 |
| abstract_inverted_index.improves | 162 |
| abstract_inverted_index.insights | 170 |
| abstract_inverted_index.learning | 76, 122 |
| abstract_inverted_index.modeling | 42 |
| abstract_inverted_index.provides | 168 |
| abstract_inverted_index.quantify | 108 |
| abstract_inverted_index.rational | 180 |
| abstract_inverted_index.relative | 110 |
| abstract_inverted_index.strategy | 123 |
| abstract_inverted_index.superior | 125 |
| abstract_inverted_index.training | 134 |
| abstract_inverted_index.transfer | 45, 121 |
| abstract_inverted_index.utilized | 106 |
| abstract_inverted_index.K-Nearest | 81 |
| abstract_inverted_index.approach, | 72 |
| abstract_inverted_index.construct | 95 |
| abstract_inverted_index.framework | 43, 159 |
| abstract_inverted_index.governing | 9 |
| abstract_inverted_index.learning. | 46 |
| abstract_inverted_index.modeling. | 32 |
| abstract_inverted_index.molecular | 113, 144, 147, 172 |
| abstract_inverted_index.parameter | 8 |
| abstract_inverted_index.polyimide | 17 |
| abstract_inverted_index.scenarios | 130 |
| abstract_inverted_index.structure | 173 |
| abstract_inverted_index.topology, | 145 |
| abstract_inverted_index.Neighbors, | 82 |
| abstract_inverted_index.challenges | 29 |
| abstract_inverted_index.fine-tuned | 64 |
| abstract_inverted_index.foundation | 178 |
| abstract_inverted_index.identified | 140 |
| abstract_inverted_index.influences | 154 |
| abstract_inverted_index.integrated | 158 |
| abstract_inverted_index.introduces | 39 |
| abstract_inverted_index.leveraging | 44 |
| abstract_inverted_index.mechanical | 13 |
| abstract_inverted_index.multilayer | 49 |
| abstract_inverted_index.perceptron | 50 |
| abstract_inverted_index.prediction | 164 |
| abstract_inverted_index.predictive | 31, 97, 126 |
| abstract_inverted_index.properties | 14, 150 |
| abstract_inverted_index.transition | 2 |
| abstract_inverted_index.Regression, | 80, 84, 87 |
| abstract_inverted_index.data-scarce | 129 |
| abstract_inverted_index.demonstrate | 118 |
| abstract_inverted_index.descriptors | 114 |
| abstract_inverted_index.engineering | 181 |
| abstract_inverted_index.large-scale | 59 |
| abstract_inverted_index.pre-trained | 56 |
| abstract_inverted_index.significant | 28 |
| abstract_inverted_index.temperature | 3 |
| abstract_inverted_index.transparent | 96 |
| abstract_inverted_index.distribution | 142 |
| abstract_inverted_index.exPlanations | 101 |
| abstract_inverted_index.experimental | 22 |
| abstract_inverted_index.performance, | 165 |
| abstract_inverted_index.small-sample | 67 |
| abstract_inverted_index.subsequently | 63 |
| abstract_inverted_index.Complementing | 70 |
| abstract_inverted_index.Specifically, | 47 |
| abstract_inverted_index.contributions | 111 |
| abstract_inverted_index.interpretable | 74 |
| abstract_inverted_index.inhomogeneity, | 143 |
| abstract_inverted_index.high-performance | 183 |
| abstract_inverted_index.bismaleimide-based | 16 |
| abstract_inverted_index.algorithms—Random | 77 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 7 |
| citation_normalized_percentile.value | 0.19464909 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |