- Research
- SERS
- Nanoparticles
| Machine learning for prediction of NP morphological properties |
Nanostructures have attracted huge interest as a rapidly growing class of materials for many applications ranging from biomedical, sensing and catalysis. The characterization of nanoparticles’ morphological properties such as shape, size, and surface characteristics is important as they dictate the particles’ properties and thus applications. The most widely used techniques such electron microscopy and x-ray diffractions are time-consuming, expensive and ill-suited for commercial use. Our group aims to leverage feature engineering and machine learning in combination with high-throughput analytical techniques for rapid, reliable and reproducible characterization nanoparticles’ morphological properties. In addition, our ML-driven strategy permits a data-driven approach to investigate the structure-property relationship of nanoparticles which is the cornerstone of nanomaterial research.
Relevant publications: Nanoscale Horiz. (2022) 7, 6, 626-633 Angew. Chem. Int. Ed. (2020) 59, 47, 21183-21189 |
