Curiosity Driven Exploration to Optimize Structure-Property Learning in Microscopy
By: Aditya Vatsavai , Ganesh Narasimha , Yongtao Liu and more
Potential Business Impact:
Finds new materials faster by guessing where to look.
Rapidly determining structure-property correlations in materials is an important challenge in better understanding fundamental mechanisms and greatly assists in materials design. In microscopy, imaging data provides a direct measurement of the local structure, while spectroscopic measurements provide relevant functional property information. Deep kernel active learning approaches have been utilized to rapidly map local structure to functional properties in microscopy experiments, but are computationally expensive for multi-dimensional and correlated output spaces. Here, we present an alternative lightweight curiosity algorithm which actively samples regions with unexplored structure-property relations, utilizing a deep-learning based surrogate model for error prediction. We show that the algorithm outperforms random sampling for predicting properties from structures, and provides a convenient tool for efficient mapping of structure-property relationships in materials science.
Similar Papers
Persistence is All You Need -- A Topological Lens on Microstructural Characterization
Computational Engineering, Finance, and Science
Finds hidden patterns in materials to make them better.
Neural Contrast Expansion for Explainable Structure-Property Prediction and Random Microstructure Design
Machine Learning (CS)
Helps design new materials by understanding their tiny parts.
Causal integration of chemical structures improves representations of microscopy images for morphological profiling
Machine Learning (CS)
Helps find drug effects by linking cell pictures and drug shapes.