Reconstructing Chromatic-Dispersion Relations and Predicting Refractive Indices Using Text Mining and Machine Learning

Abstract

Predicting the properties of materials prior to their synthesis is of great significance in materials science. Optical materials exhibit a large number of interesting properties that make them useful in a wide range of applications, including optical glasses, optical fibers, and laser optics. In all of these applications, refraction and its chromatic dispersion can directly reflect the characteristics of the transmitted light and determine the practical utility of the material. We demonstrate the feasibility of reconstructing chromatic-dispersion relations of well-known optical materials by aggregating data over a large number of independent sources, which are contained within a material database of experimentally determined refractive indices and wavelength values. We also employ this database to develop a machine-learning platform that can predict refractive indices of compounds without needing to know the structure or other properties of a material of interest. We present a web-based application that enables users to build their customized machine-learning models; this will help the scientific community to conduct further research into the discovery of optical materials.

A database of thermally activated delayed fluorescent molecules auto-generated from scientific literature with ChemDataExtractor

“…Their data are usually very reliable given that they often based on experimental results and have been vetted by peer review. The chemistry-aware natural-language-processing (NLP) toolkit ChemDataExtractor 10 – 12 provides a means of this automatic data extraction from the scientific literature 13 – 21 . The thus obtained databases are characterized by consistent computer-readable structures and can subsequently be used for the analysis of structure-property relationships (SPRs) which provide the patterns required for predicting and thence validating the discovery of new materials for a given application 20 , 21 .…”

Flexible, model-agnostic method for materials data extraction from text using general purpose language models

“…Other recent examples of databases created in a similar way include photovoltaic properties and device material data for dye-sensitized solar cells, 31 yield strength and grain size, 32 and refractive index. 33,34 Other notable databases gathered with NLP-based approaches include more complex information than just data values, such as synthesis procedures. 19,27 Recently, another method for structured information extraction, making use of the GPT-3 capabilities was presented.…”

Swarm Smart Meta-Estimator for 2D/2D Heterostructure Design

“…For example, first-principles calculations are particularly useful for simulating small sets of compounds with high accuracy . To lift this deadlock of computational demand, machine learning (ML) approaches are used. , These methods empower research to perform tasks ranging from predicting material properties such as adsorption energy and formation energy, p K a of macromolecules, or chromatic dispersion of compounds, to simulating structures with high accuracy using deep neural networks . The cost/accuracy trade-off can increase in sophistication by using ML to decrease the computational effort of such methods, , or by recommending compounds (molecules, materials) on which to apply high accuracy, computationally demanding methods.…”