MatCompGenAIGenerating Material Compositions from Desired PropertiesWhat is MatCompGenAI?
MatCompGenAI is an AI-powered inverse design tool that generates novel inorganic crystalline material compositions based on target properties. Trained on the Open Quantum Materials Database (OQMD), it predicts compositions that match property requirements provided as natural language input, such as formation energy, volume, total energy, band gap, net magnetic moment, and stability. Designed for rapid materials discovery, it supports research and development in materials science and engineering.
Author: Neerada Mapalagama
MatCompGenAI is owned and developed by ONM. All intellectual property rights in and to MatCompGenAI, including its software, algorithms, trained models, and related materials, are the exclusive property of ONM. The OQMD dataset is owned by its respective rights holders, and ONM does not claim ownership of the dataset.
Data Sources
Saal, J. E., Kirklin, S., Aykol, M., Meredig, B., and Wolverton, C. Materials Design and Discovery with High-Throughput Density Functional Theory: The Open Quantum Materials Database (OQMD) JOM, 65, 1501–1509 (2013). https://doi.org/10.1007/s11837-013-0755-4
Kirklin, S., Saal, J. E., Meredig, B., et al. The Open Quantum Materials Database (OQMD): assessing the accuracy of DFT formation energies npj Computational Materials, 1, 15010 (2015). https://doi.org/10.1038/npjcompumats.2015.10
Limitations
This project is intended for educational and research exploration purposes only. The generated material compositions are produced by AI models trained on density functional theory (DFT)-calculated data from the Open Quantum Materials Database (OQMD).
While these models capture statistical and quantum-informed trends, the resulting compositions are not guaranteed to correspond to experimentally known, synthesizable, or thermodynamically stable materials. All outputs should be treated as hypothetical candidates, subject to further validation through computational or experimental methods.