Combining chemical, geometric, and novel topological features to develop generalizable machine learning models for predicting mechanically stable MOFs
We present a generalizable, interpretable ML model to predict MOF bulk modulus using novel topological and chemical features. Trained on diverse data, it enables high-throughput screening of ∼435k MOFs for mechanical stability.
Authors
- Changhwan Oh (ORCID: https://orcid.org/0000-0003-2120-6676)
- Heather Janine Kulik (ORCID: https://orcid.org/0000-0001-9342-0191)
- Akash Ball (ORCID: https://orcid.org/0000-0002-0482-9479)
- Gozel Dovranova
Institutions
- Massachusetts Institute of Technology (US)
Publication Details
- Journal
- Journal of Materials Chemistry A
- Published
- 2026-01-01
- DOI
- https://doi.org/10.1039/d5ta08080k
- Primary Topic
- Metal-Organic Frameworks: Synthesis and Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Alfred P. Sloan Foundation
- Massachusetts Institute of Technology