| About this Abstract |
| Meeting |
MS&T24: Materials Science & Technology
|
| Symposium
|
ACerS-ECerS Joint Symposium: Emerging Leaders in Glass and Ceramics
|
| Presentation Title |
Integrated Data Science and Computational Materials Science for Understanding Complex Materials |
| Author(s) |
Dilpuneet S. Aidhy |
| On-Site Speaker (Planned) |
Dilpuneet S. Aidhy |
| Abstract Scope |
As we push the boundaries of materials for applications, novel and often complex materials are needed that require creative design strategies. The traditional computational tools, that have been highly successful, need to be integrated with sophisticated methods. A fitting example are high entropy materials (HEMs) that consist of multiple principal elements in large proportions in contrast to one principal element in conventional/dilute materials. Robust data-science methods offer a rigorous path forward to overcome the multi-dimensional challenge. We use machine learning algorithms in conjunction with physics-based principles to unveil key structure-property correlations that are otherwise unintuitive in complex materials. I will discuss our new data-science integrated computational materials science approach namely PREDICT (Predict properties from Existing Databases in Complex materials Territory) whereby properties in complex materials are predicted by learning from simpler materials. I will also discuss how charge-density can be a used as a universal descriptor for properties’ prediction. |