VASP
Category: DFT Simulation
Vienna Ab initio Simulation Package - A leading electronic structure calculation software
Research Resources
Computational Materials Research Tools
Tools and libraries I have used throughout my research journey in computational materials science, spanning DFT simulations, molecular dynamics, and machine learning applications.
AFLOW
Category: High-Throughput
Automatic FLOW for materials discovery - High-throughput computational materials design
pymatgen
Category: High-Throughput
Python Materials Genomics - A robust materials analysis library
scikit-learn
Category: Machine Learning
Machine learning library for Python - Classification, regression, and clustering algorithms
ASE
Category: Machine Learning
Atomic Simulation Environment - Python library for working with atoms
SHAP
Category: Machine Learning
SHapley Additive exPlanations - Explain machine learning model predictions
SISSO
Category: Machine Learning
Sure Independence Screening and Sparsifying Operator - Feature selection and regression
Python
Category: Programming Language
High-level programming language - The foundation for scientific computing
LAMMPS
Category: Molecular Dynamics
Large-scale Atomic/Molecular Massively Parallel Simulator
DeePMD-kit
Category: Deep Learning
Deep Potential Molecular Dynamics - Machine learning potential energy models
modAL
Category: Active Learning
Modular Active Learning framework - Python library for active learning workflows
All tools are actively maintained by their respective communities. Visit their repositories for documentation, examples, and support.
Master Thesis
This thesis employs Density Functional Theory (DFT) calculations and machine learning methods to systematically investigate how alloying elements and radiation-induced defects influence the behavior of non-metallic interstitial atoms in Hexagonal Close-Packed (HCP) metals, particularly zirconium alloys used as fuel cladding in nuclear reactors. The research combines first-principles calculations with innovative machine learning approaches to reveal microscopic mechanisms of oxygen diffusion and defect behavior, providing theoretical foundations for developing zirconium alloys with improved radiation and oxidation resistance.
Title: First Principles Combined with Machine Learning to Study Zirconium and HCP Metal Defect Properties
Key Topics: DFT calculations, radiation defects in zirconium, oxygen diffusion mechanisms, machine learning for materials property prediction, SHAP analysis for feature importance