Interpretable Machine Learning Prediction of Polyimide Dielectric Constants: A Feature-Engineered Approach with Experimental Validation

电介质 聚酰亚胺 材料科学 特征(语言学) 人工智能 机器学习 计算机科学 复合材料 光电子学 语言学 哲学 图层(电子)
作者
Xiaojie He,Jiachen Wan,Songyang Zhang,Chenggang Zhang,Peng Xiao,Feng Zheng,Qinghua Lu
出处
期刊:Polymers [Multidisciplinary Digital Publishing Institute]
卷期号:17 (12): 1622-1622 被引量:11
标识
DOI:10.3390/polym17121622
摘要

Low-dielectric polyimides (PIs) have emerged as essential materials for next-generation microelectronics and communication technologies, yet traditional experimental and theoretical calculation methods for acquiring dielectric constant data face challenges in cost, accuracy, and scalability. This study presents a machine learning (ML) framework that combines polymer domain knowledge with advanced data-driven modeling techniques for accurate prediction of PI dielectric constants at 1 kHz. A dataset of 439 PIs was constructed, and 208 molecular descriptors were derived from SMILES-encoded structures. Through rigorous feature engineering—variance filtering, correlation analysis, and recursive feature elimination—10 key descriptors were identified, capturing electronic and polar interaction, surface area, and structural complexity. Five ML algorithms were evaluated, with Gaussian Process Regression (GPR) achieving superior predictive accuracy (test set: R2 = 0.90, RMSE = 0.10). Shapley additive explanations (SHAP) analysis quantifies the contribution of molecular descriptors to PI dielectric constants. By means of SHAP values, it discloses the positive or negative impacts of descriptors on the predictions. Three novel PIs were synthesized for experimental validation, showing strong agreement between predicted and measured dielectric constants (mean percentage deviation: 2.24%). The model demonstrates robust predictions for other structurally similar polymers but reveals a 40% accuracy reduction (R2 = 0.60) in 10 GHz cross-frequency predictions, emphasizing the requirement for multi-frequency training datasets to enhance model generalizability. This work advances the research paradigm of polymer dielectric materials and provides a pathway for the rational design of materials guided by machine learning.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
syz1209完成签到,获得积分20
刚刚
wlg完成签到,获得积分10
刚刚
汉堡包的应助被eternal采纳,获得10
刚刚
Ava的应助被荼蘼采纳,获得10
1秒前
memo完成签到,获得积分10
1秒前
1秒前
清河聂氏完成签到,获得积分10
1秒前
Lyonthemoon发布了新的文献求助10
1秒前
爱撒娇的手套完成签到,获得积分10
1秒前
刘老哥6完成签到,获得积分10
2秒前
2秒前
酷波er的应助被张kk采纳,获得10
2秒前
XUAN发布了新的文献求助10
2秒前
hkp完成签到,获得积分10
2秒前
2秒前
tough完成签到,获得积分10
2秒前
豆包不当干粮完成签到,获得积分10
2秒前
布丁完成签到,获得积分10
3秒前
云曦的应助被科研通管家采纳,获得10
3秒前
3秒前
v0id的应助被科研通管家采纳,获得10
3秒前
ruia168的应助被旅行的天空采纳,获得10
3秒前
我是老大的应助被科研通管家采纳,获得10
3秒前
可爱的函函的应助被2025110031077采纳,获得10
4秒前
4秒前
4秒前
4秒前
4秒前
4秒前
4秒前
4秒前
4秒前
张继科keke完成签到,获得积分10
4秒前
Yangbingang发布了新的文献求助10
4秒前
4秒前
4秒前
我是老大的应助被huimin采纳,获得10
5秒前
夏浅发布了新的文献求助10
5秒前
5秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1500
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
Analyses de reconnaissances de dettes passées devant les échevins d'Ypres (1249-1291) 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8159581
求助须知:如何正确求助?哪些是违规求助? 9555100
关于积分的说明 21724719
捐赠科研通 7749543
什么是DOI,文献DOI怎么找? 3427281
关于科研通互助平台的介绍 2552278
邀请新用户注册赠送积分活动 2471619