Prediction of Scintillation Material Properties by Ml Internship

About Internship

Professor from Shiv Nadar University, India, is accepting interns interested in the field of Physics, in the research area of Artificial Intelligence and Machine Learning.

This research internship sits at the intersection of computational materials science and radiation detection. The project focuses on leveraging Machine Learning (ML) to accelerate the discovery and optimization of scintillation materials—crystals that emit light when struck by ionizing radiation. By applying predictive models to vast datasets of material characteristics, interns will help bypass traditional, time-consuming "trial and error" experimental methods. Roles and Responsibilities 1. Assist in gathering and cleaning experimental and theoretical data on known scintillator compositions and their performance metrics. 2. Identify and extract key physical descriptors—such as density, atomic number and bandgap—to serve as inputs for predictive models. 3. Apply ML tools (such as Regression trees, Neural Networks, or Random Forests) to predict critical properties like light yield, decay time, and energy resolution. 4. Compare ML-generated predictions against established experimental benchmarks to verify model accuracy and reliability. 5. Use trained models to screen candidate materials, identifying promising new compositions for future laboratory synthesis. Learning Outcomes & Benefits 1. Develop a rare skill set combining fundamental Radiation Physics with modern Data Science methodologies. 2. Gain hands-on experience in the "Materials Informatics" workflow, specifically applying Python-based ML libraries to physical systems. 3. Learn to interpret how microscopic material changes influence macroscopic detector performance.