Curiosity Driven Exploration to Optimize Structure-Property Learning in Microscopy
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912500004421632 |
|---|---|
| author | Vatsavai, Aditya Narasimha, Ganesh Liu, Yongtao Chowdhury, Jawad Yang, Jan-Chi Funakubo, Hiroshi Ziatdinov, Maxim Vasudevan, Rama |
| author_facet | Vatsavai, Aditya Narasimha, Ganesh Liu, Yongtao Chowdhury, Jawad Yang, Jan-Chi Funakubo, Hiroshi Ziatdinov, Maxim Vasudevan, Rama |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_20011 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Curiosity Driven Exploration to Optimize Structure-Property Learning in Microscopy Vatsavai, Aditya Narasimha, Ganesh Liu, Yongtao Chowdhury, Jawad Yang, Jan-Chi Funakubo, Hiroshi Ziatdinov, Maxim Vasudevan, Rama Materials Science Machine Learning 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. |
| title | Curiosity Driven Exploration to Optimize Structure-Property Learning in Microscopy |
| topic | Materials Science Machine Learning |
| url | https://arxiv.org/abs/2504.20011 |