Integration of multiscale simulations and machine learning for predicting dendritic microstructures in solidification of alloys

I am pleased to share our newest open-access article just published in #ActaMaterialia. 

In our study, we  present an integration of machine learning (ML) with a multiscale computational framework to predict primary dendrite arm spacing (PDAS) during alloy solidification. The findings of this work highlight the value of physics-based ML, especially parametric regression models, for optimizing alloy manufacturing processes and controlling the microstructures.

This work was supported by the National Science Foundation (NSF).

Sepideh Kavousi and Mohsen Asle Zaeem. Integration of multiscale simulations and machine learning for predicting dendritic microstructures in solidification of alloys. Acta Materialia 289 (2025) 120860.

https://www.sciencedirect.com/science/article/pii/S1359645425001521?via…