{"title":"利用机器学习算法预测玻璃基材料的半值层","authors":"D.E. Zenkhri, M.I. Sayyed","doi":"10.1016/j.radphyschem.2025.113373","DOIUrl":null,"url":null,"abstract":"Accurate prediction of the half-value layer (HVL) in radiation shielding materials is essential for optimizing their composition and performance. In this study, we employ four ensemble machine learning models XGBoost, LightGBM, Gradient Boosting Regressor (GBR), and Random Forest to predict HVL based on the chemical composition of glass-based materials. Each model was fine-tuned using Optuna’s Bayesian optimization and evaluated through 5-fold cross-validation and a separate testing phase using metrics including <mml:math altimg=\"si68.svg\" display=\"inline\"><mml:msup><mml:mrow><mml:mi>R</mml:mi></mml:mrow><mml:mrow><mml:mn>2</mml:mn></mml:mrow></mml:msup></mml:math> , RMSE, MAE, and MAPE. All models demonstrated high predictive performance (<mml:math altimg=\"si2.svg\" display=\"inline\"><mml:mrow><mml:msup><mml:mrow><mml:mi>R</mml:mi></mml:mrow><mml:mrow><mml:mn>2</mml:mn></mml:mrow></mml:msup><mml:mo linebreak=\"goodbreak\" linebreakstyle=\"after\">></mml:mo><mml:mn>0</mml:mn><mml:mo>.</mml:mo><mml:mn>996</mml:mn></mml:mrow></mml:math>), with the GBR model achieving the best results (<mml:math altimg=\"si3.svg\" display=\"inline\"><mml:mrow><mml:msup><mml:mrow><mml:mi>R</mml:mi></mml:mrow><mml:mrow><mml:mn>2</mml:mn></mml:mrow></mml:msup><mml:mo linebreak=\"goodbreak\" linebreakstyle=\"after\">=</mml:mo><mml:mn>0</mml:mn><mml:mo>.</mml:mo><mml:mn>999</mml:mn></mml:mrow></mml:math>, <mml:math altimg=\"si4.svg\" display=\"inline\"><mml:mrow><mml:mi>R</mml:mi><mml:mi>M</mml:mi><mml:mi>S</mml:mi><mml:mi>E</mml:mi><mml:mo linebreak=\"goodbreak\" linebreakstyle=\"after\">=</mml:mo><mml:mn>0</mml:mn><mml:mo>.</mml:mo><mml:mn>0772</mml:mn></mml:mrow></mml:math>, <mml:math altimg=\"si5.svg\" display=\"inline\"><mml:mrow><mml:mi>M</mml:mi><mml:mi>A</mml:mi><mml:mi>P</mml:mi><mml:mi>E</mml:mi><mml:mo linebreak=\"goodbreak\" linebreakstyle=\"after\">=</mml:mo><mml:mn>0</mml:mn><mml:mo>.</mml:mo><mml:mn>09</mml:mn><mml:mtext>%</mml:mtext></mml:mrow></mml:math>). XGBoost also performed competitively, offering a balance between accuracy and computational efficiency. These results highlight the potential of gradient boosting approaches to speed up the design and study of radiation shielding materials and show how effective they are at identifying intricate nonlinear correlations within material databases.","PeriodicalId":20861,"journal":{"name":"Radiation Physics and Chemistry","volume":"19 1","pages":""},"PeriodicalIF":2.8000,"publicationDate":"2025-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Prediction of Half-Value Layer of glass-based materials using machine learning algorithms\",\"authors\":\"D.E. Zenkhri, M.I. Sayyed\",\"doi\":\"10.1016/j.radphyschem.2025.113373\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Accurate prediction of the half-value layer (HVL) in radiation shielding materials is essential for optimizing their composition and performance. In this study, we employ four ensemble machine learning models XGBoost, LightGBM, Gradient Boosting Regressor (GBR), and Random Forest to predict HVL based on the chemical composition of glass-based materials. Each model was fine-tuned using Optuna’s Bayesian optimization and evaluated through 5-fold cross-validation and a separate testing phase using metrics including <mml:math altimg=\\\"si68.svg\\\" display=\\\"inline\\\"><mml:msup><mml:mrow><mml:mi>R</mml:mi></mml:mrow><mml:mrow><mml:mn>2</mml:mn></mml:mrow></mml:msup></mml:math> , RMSE, MAE, and MAPE. All models demonstrated high predictive performance (<mml:math altimg=\\\"si2.svg\\\" display=\\\"inline\\\"><mml:mrow><mml:msup><mml:mrow><mml:mi>R</mml:mi></mml:mrow><mml:mrow><mml:mn>2</mml:mn></mml:mrow></mml:msup><mml:mo linebreak=\\\"goodbreak\\\" linebreakstyle=\\\"after\\\">></mml:mo><mml:mn>0</mml:mn><mml:mo>.</mml:mo><mml:mn>996</mml:mn></mml:mrow></mml:math>), with the GBR model achieving the best results (<mml:math altimg=\\\"si3.svg\\\" display=\\\"inline\\\"><mml:mrow><mml:msup><mml:mrow><mml:mi>R</mml:mi></mml:mrow><mml:mrow><mml:mn>2</mml:mn></mml:mrow></mml:msup><mml:mo linebreak=\\\"goodbreak\\\" linebreakstyle=\\\"after\\\">=</mml:mo><mml:mn>0</mml:mn><mml:mo>.</mml:mo><mml:mn>999</mml:mn></mml:mrow></mml:math>, <mml:math altimg=\\\"si4.svg\\\" display=\\\"inline\\\"><mml:mrow><mml:mi>R</mml:mi><mml:mi>M</mml:mi><mml:mi>S</mml:mi><mml:mi>E</mml:mi><mml:mo linebreak=\\\"goodbreak\\\" linebreakstyle=\\\"after\\\">=</mml:mo><mml:mn>0</mml:mn><mml:mo>.</mml:mo><mml:mn>0772</mml:mn></mml:mrow></mml:math>, <mml:math altimg=\\\"si5.svg\\\" display=\\\"inline\\\"><mml:mrow><mml:mi>M</mml:mi><mml:mi>A</mml:mi><mml:mi>P</mml:mi><mml:mi>E</mml:mi><mml:mo linebreak=\\\"goodbreak\\\" linebreakstyle=\\\"after\\\">=</mml:mo><mml:mn>0</mml:mn><mml:mo>.</mml:mo><mml:mn>09</mml:mn><mml:mtext>%</mml:mtext></mml:mrow></mml:math>). XGBoost also performed competitively, offering a balance between accuracy and computational efficiency. These results highlight the potential of gradient boosting approaches to speed up the design and study of radiation shielding materials and show how effective they are at identifying intricate nonlinear correlations within material databases.\",\"PeriodicalId\":20861,\"journal\":{\"name\":\"Radiation Physics and Chemistry\",\"volume\":\"19 1\",\"pages\":\"\"},\"PeriodicalIF\":2.8000,\"publicationDate\":\"2025-10-13\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Radiation Physics and Chemistry\",\"FirstCategoryId\":\"92\",\"ListUrlMain\":\"https://doi.org/10.1016/j.radphyschem.2025.113373\",\"RegionNum\":3,\"RegionCategory\":\"物理与天体物理\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"CHEMISTRY, PHYSICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Radiation Physics and Chemistry","FirstCategoryId":"92","ListUrlMain":"https://doi.org/10.1016/j.radphyschem.2025.113373","RegionNum":3,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"CHEMISTRY, PHYSICAL","Score":null,"Total":0}
Prediction of Half-Value Layer of glass-based materials using machine learning algorithms
Accurate prediction of the half-value layer (HVL) in radiation shielding materials is essential for optimizing their composition and performance. In this study, we employ four ensemble machine learning models XGBoost, LightGBM, Gradient Boosting Regressor (GBR), and Random Forest to predict HVL based on the chemical composition of glass-based materials. Each model was fine-tuned using Optuna’s Bayesian optimization and evaluated through 5-fold cross-validation and a separate testing phase using metrics including R2 , RMSE, MAE, and MAPE. All models demonstrated high predictive performance (R2>0.996), with the GBR model achieving the best results (R2=0.999, RMSE=0.0772, MAPE=0.09%). XGBoost also performed competitively, offering a balance between accuracy and computational efficiency. These results highlight the potential of gradient boosting approaches to speed up the design and study of radiation shielding materials and show how effective they are at identifying intricate nonlinear correlations within material databases.
期刊介绍:
Radiation Physics and Chemistry is a multidisciplinary journal that provides a medium for publication of substantial and original papers, reviews, and short communications which focus on research and developments involving ionizing radiation in radiation physics, radiation chemistry and radiation processing.
The journal aims to publish papers with significance to an international audience, containing substantial novelty and scientific impact. The Editors reserve the rights to reject, with or without external review, papers that do not meet these criteria. This could include papers that are very similar to previous publications, only with changed target substrates, employed materials, analyzed sites and experimental methods, report results without presenting new insights and/or hypothesis testing, or do not focus on the radiation effects.