Machine learning framework improves material defect and adsorption site search
PYTHIA, a transferable machine learning framework for simultaneous defect and adsorption site optimization
Machine Learning
Summary
Finding the best spots for defects or molecules to stick to materials can be really hard and slow. The authors created a new tool called PYTHIA, which learns from related materials and uses clever transfer learning techniques. This helps it predict good places even when there isn’t much data about a material. By combining this with smart searching methods, PYTHIA finds the best spots efficiently in different material types.
What this means in practice
- •For materials engineers: Identify optimal defect configurations and adsorption sites on novel materials with limited experimental data.
- •For chemical process developers: Optimize catalyst surfaces by predicting effective adsorption sites to improve reaction efficiency.
Authors
Ioannis Kouroudis, Zhaosu Gu, Poonam, Leon Muller, Alessio Gagliardi
Abstract
Machine learning has permeated material optimization, providing high value. Nevertheless, its re- liance on a high number of samples limits its applicability to relatively explored material families. In this paper we extend the applicability of machine learning to novel and understudied materials through the PYTHIA (Probabilistic Yet Transferable Hierarchical Interaction Architecture) framework. Pythia utilizes two of the most powerful machine learning concepts, foundational models and transfer learning. We employ a complex foundational model trained on a large dataset of chemically similar molecules, on a target that is physically close to our prediction target. Then, we freeze the weights and perform subspace alignment with the use of a transformer layer and add uncertainty quantification with gaussian processes. These two layers can be trained on a limited dataset yet allow us to leverage the gained knowl- edge and the studied materials and complex architectures. The resulting model is used as a surrogate for a Bayesian Optimization scheme. To showcase the robustness of the framework, we applied it to the investigation of adsorption and defect optimization of two distinct systems. Not only were we able to correctly and efficiently identify the optimal adsorption sites of even complex a