From Patents to Dataset: Scraping for Oxide Glass Compositions and Properties

TL;DR

This paper develops web scraping methods to extract and structure glass composition and property data from patents, expanding existing databases and enabling improved machine learning models for glass development.

Contribution

It introduces novel web scraping techniques to extract diverse glass data from patents and integrates this data into existing databases for advanced modeling.

Findings

Increased data volume by approximately 10.4% for liquidus temperature.

Expanded compositional diversity with more titanium, magnesium, zirconium, and other oxides.

Enhanced database coverage for glass property prediction models.

Abstract

In this work, we present web scraping techniques to extract in- formation from patent tables, clean and structure them for future use in predictive machine learning models to develop new glasses. We extracted compositions and three properties relevant to the development of new glasses and structured them into a database to be used together with information from other available datasets. We also analyzed the consistency of the information obtained and what it adds to the existing databases. The extracted liquidus temperatures comprise 5,696 compositions; the second subset includes 4,298 refractive indexes and, finally, 1,771 compositions with Abbe numbers. The extraction performed here increases the available information by approximately 10.4% for liquidus temperature, 6.6% for refractive index, and 4.9% for Abbe number. The impact extends beyond quantity: the newly extracted data introduce compositions with property values that are more diverse than those in existing databases, thereby expanding the accessible compositional and property space for glass modeling applications. We emphasize that the compositions of the new database contain relatively more titanium, magnesium, zirconium, niobium, iron, tin, and yttrium oxides than those of the existing bases.