Developing physics-informed machine learning models that bridge quantum mechanical accuracy with classical simulation efficiency.
Overview
My research in machine learning for materials science focuses on creating computational methods that combine the physical accuracy of quantum mechanics with the efficiency and scalability of data-driven approaches. By developing physics-informed machine learning techniques, I aim to accelerate materials discovery and provide deeper insights into complex materials phenomena that are challenging to model with traditional methods.
Visualization of a machine learning potential energy surface compared with quantum mechanical calculations, showing high accuracy across different atomic configurations.
Key Research Directions
Neural Network Interatomic Potentials
I develop machine learning models that can predict atomic interactions with quantum mechanical accuracy, focusing on:
- Training neural networks on quantum mechanical data to predict energies and forces
- Incorporating physical constraints and symmetries into machine learning architectures
- Optimizing models for transferability across different chemical environments
These machine learning potentials enable simulations of large, complex systems with accuracy approaching quantum mechanical methods but at a fraction of the computational cost, opening new possibilities for materials modeling.
Uncertainty Quantification in Machine Learning Predictions
A critical aspect of my work is quantifying the reliability of machine learning predictions, including:
- Developing Bayesian neural networks for materials property prediction with uncertainty estimates
- Analyzing the domain of applicability for trained models
- Creating active learning frameworks that can identify when additional training data is needed
This research ensures that predictions made by machine learning models are accompanied by reliable uncertainty estimates, which is essential for making informed decisions in materials design and optimization.
Interpretable AI for Materials Discovery
I work on making machine learning models more interpretable and physically meaningful:
- Developing feature extraction techniques that identify the key descriptors of material properties
- Creating visualization methods to understand how neural networks represent physical concepts
- Building hybrid models that combine symbolic regression with deep learning
By making machine learning more interpretable, my research aims to not only predict material properties but also generate new physical insights and guide the development of improved theoretical models.
Methodology
My machine learning research employs a range of advanced techniques:
- Deep Neural Networks - Including graph neural networks and equivariant architectures for representing atomic structures
- Physics-Informed Machine Learning - Incorporating physical principles as constraints or regularization terms
- Transfer Learning - Leveraging knowledge from well-studied materials to make predictions for novel systems
- Explainable AI Methods - Techniques for interpreting what neural networks learn about physical systems
Impact
My research in machine learning for materials science bridges the gap between quantum mechanical accuracy and classical simulation efficiency, enabling new approaches to materials discovery and design. This work has applications across multiple domains, including energy storage, catalysis, electronic materials, and structural materials. By accelerating the materials discovery cycle and providing deeper insights into materials behavior, my research contributes to addressing urgent technological challenges in energy, environment, and sustainable manufacturing.
Related Publications
Select publications related to machine learning in materials science:
Physics-informed machine learning exploration of Na storage mechanisms in disordered carbon
Energy Storage Materials, 104967, 2026
View All Machine Learning Publications