Sayam Singla, Sajid Mannan, Mohd Zaki, N. Krishnan
{"title":"Accelerated design of chalcogenide glasses through interpretable machine learning for composition–property relationships","authors":"Sayam Singla, Sajid Mannan, Mohd Zaki, N. Krishnan","doi":"10.1088/2515-7639/acc6f2","DOIUrl":null,"url":null,"abstract":"Chalcogenide glasses (ChGs) possess various outstanding properties enabling essential applications, such as optical discs, infrared cameras, and thermal imaging systems. Despite their ubiquitous usage, these materials’ composition–property relationships remain poorly understood, impeding the pace of their discovery. Here, we use a large experimental dataset comprising ∼24 000 glass compositions made of 51 distinct elements from the periodic table to develop machine learning (ML) models for predicting 12 properties, namely, annealing point, bulk modulus, density, Vickers hardness, Littleton point, Young’s modulus, shear modulus, softening point, thermal expansion coefficient, glass transition temperature, liquidus temperature, and refractive index. These models are the largest regarding the compositional space and the number of properties covered for ChGs. Further, we use Shapley additive explanations, a game theory-based algorithm, to explain the properties’ compositional control by quantifying each element’s role toward model predictions. This work provides a powerful tool for interpreting the model’s prediction and designing new ChG compositions with targeted properties. Finally, using the trained ML models, we develop several glass-selection charts that can potentially aid in the rational design of novel ChGs for various applications.","PeriodicalId":16520,"journal":{"name":"Journal of Nonlinear Optical Physics & Materials","volume":null,"pages":null},"PeriodicalIF":2.9000,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Nonlinear Optical Physics & Materials","FirstCategoryId":"101","ListUrlMain":"https://doi.org/10.1088/2515-7639/acc6f2","RegionNum":4,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"OPTICS","Score":null,"Total":0}
引用次数: 1
Abstract
Chalcogenide glasses (ChGs) possess various outstanding properties enabling essential applications, such as optical discs, infrared cameras, and thermal imaging systems. Despite their ubiquitous usage, these materials’ composition–property relationships remain poorly understood, impeding the pace of their discovery. Here, we use a large experimental dataset comprising ∼24 000 glass compositions made of 51 distinct elements from the periodic table to develop machine learning (ML) models for predicting 12 properties, namely, annealing point, bulk modulus, density, Vickers hardness, Littleton point, Young’s modulus, shear modulus, softening point, thermal expansion coefficient, glass transition temperature, liquidus temperature, and refractive index. These models are the largest regarding the compositional space and the number of properties covered for ChGs. Further, we use Shapley additive explanations, a game theory-based algorithm, to explain the properties’ compositional control by quantifying each element’s role toward model predictions. This work provides a powerful tool for interpreting the model’s prediction and designing new ChG compositions with targeted properties. Finally, using the trained ML models, we develop several glass-selection charts that can potentially aid in the rational design of novel ChGs for various applications.
期刊介绍:
This journal is devoted to the rapidly advancing research and development in the field of nonlinear interactions of light with matter. Topics of interest include, but are not limited to, nonlinear optical materials, metamaterials and plasmonics, nano-photonic structures, stimulated scatterings, harmonic generations, wave mixing, real time holography, guided waves and solitons, bistabilities, instabilities and nonlinear dynamics, and their applications in laser and coherent lightwave amplification, guiding, switching, modulation, communication and information processing. Original papers, comprehensive reviews and rapid communications reporting original theories and observations are sought for in these and related areas. This journal will also publish proceedings of important international meetings and workshops. It is intended for graduate students, scientists and researchers in academic, industrial and government research institutions.