{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"volume":["16(43)"],"submitter":["Hickey JC"],"pubmed_abstract":["Developing multifunctional materials with superior mechanical properties, including high hardness and oxidation resistance, remains essential for aerospace, defense, and industrial applications. Machine learning offers a powerful, data-driven pathway for discovering new hard, oxidation-resistant materials for these uses, providing an efficient and scalable alternative to conventional materials discovery methods. Here, we present a pair of extreme gradient boosting (XGBoost) models, trained on compositional and structural descriptors. A Vickers hardness (<i>H</i> <sub>V</sub>) model was developed using a curated dataset of 1225 while a model for predicting the oxidation temperature (<i>T</i> <sub>p</sub>) was constructed using 348 compounds. The model was subsequently validated against a di"],"journal":["Chemical science"],"pagination":["20601-20611"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC12506783"],"repository":["biostudies-literature"],"pubmed_title":["Identifying inorganic solids for harsh environments &lt;i&gt;via&lt;/i&gt; machine learning."],"pmcid":["PMC12506783"],"pubmed_authors":["Cuervo G","Arrieta R","Zhu P","Hoang S","Brgoch J","Flores M","Karimaghaei AM","Hickey JC","Kumar A"],"additional_accession":[]},"is_claimable":false,"name":"Identifying inorganic solids for harsh environments &lt;i&gt;via&lt;/i&gt; machine learning.","description":"Developing multifunctional materials with superior mechanical properties, including high hardness and oxidation resistance, remains essential for aerospace, defense, and industrial applications. Machine learning offers a powerful, data-driven pathway for discovering new hard, oxidation-resistant materials for these uses, providing an efficient and scalable alternative to conventional materials discovery methods. Here, we present a pair of extreme gradient boosting (XGBoost) models, trained on compositional and structural descriptors. A Vickers hardness (<i>H</i> <sub>V</sub>) model was developed using a curated dataset of 1225 while a model for predicting the oxidation temperature (<i>T</i> <sub>p</sub>) was constructed using 348 compounds. The model was subsequently validated against a di","dates":{"release":"2025-01-01T00:00:00Z","publication":"2025 Nov","modification":"2026-06-05T12:04:50.444Z","creation":"2026-05-16T03:12:35.34Z"},"accession":"S-EPMC12506783","cross_references":{"pubmed":["41069788"],"doi":["10.1039/d5sc05800g"]}}