Research Highlight: Mirkin
Machine learning used to predict synthesis of complex novel materials
Nanochemistry enables vast compositional and structural tunability, but serial experimental approaches to identify new materials impose insurmountable limits on discovery. Now, Professor Chad Mirkin's group and the Toyota Research Institute have successfully applied machine learning to guide the synthesis of new nanomaterials, eliminating barriers associated with materials discovery.
Machine learning applications are ideally suited to tackle the complexity of defining and mining the materials genome, but they are gated by the ability to create datasets to train algorithms in the space. The combination of machine learning and this new data-generation tool, the “Megalibrary”, may finally eradicate that problem. Invented by Professor Mirkin, each Megalibrary houses millions or even billions of nanostructures all positionally encoded on a two-by-two square centimeter chip.
In the study, the team compiled previously generated Megalibrary structural data consisting of nanoparticles with complex compositions, structures, sizes, and morphologies. They used this data to train the model and asked it to predict compositions of four, five, and six elements that would result in a certain structural feature. In 19 predictions, the machine learning model predicted new materials correctly 18 times. Professor Mirkin anticipates that their model will only get better at predicting correct materials as it is fed more high quality data collected under controlled conditions. The team is now using this approach to find catalysts critical to fueling processes in the clean energy, automotive, and chemical industries.
The research was published in the journal Science Advances.
For more on the story read Northwestern Now.