Machine Learning-Driven Analytical Models for Threshold Displacement Energy Prediction in Materials
Published in arXiv, 2025
The threshold displacement energy (Ed) is a fundamental parameter for understanding radiation damage in materials, yet its determination typically relies on costly experiments or computationally expensive simulations. In this work, we employ the Sure Independence Screening and Sparsifying Operator (SISSO) machine learning method to develop analytical models that predict Ed based on fundamental material properties. Our models achieve high accuracy for monoatomic materials, outperforming traditional empirical approaches. For polyatomic systems, we identify key challenges and highlight pathways for improvement with enhanced datasets. This study identifies cohesive energy and melting temperature as the dominant descriptors of Ed, providing a predictive framework for radiation damage assessment in diverse materials.
Recommended citation: Duque, Rosty B. Martinez, Arman Duha, and Mario F. Borunda. "Machine Learning-Driven Analytical Models for Threshold Displacement Energy Prediction in Materials." arXiv preprint arXiv:2502.01813 (2025).
Download Paper
