The quest for new materials: the network theory and machine learning perspectives
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913689390546944 |
|---|---|
| author | Moi, Jacopo Spallarossa, Davide Bonetti, Stefano Burioni, Raffaella Caldarelli, Guido |
| author_facet | Moi, Jacopo Spallarossa, Davide Bonetti, Stefano Burioni, Raffaella Caldarelli, Guido |
| contents | Understanding and predicting the emergence of novel materials is a fundamental challenge in condensed matter physics, materials science and technology. With the rapid growth of materials databases in both size and reliability, the challenge shifts from data collection to efficient exploration of this vast and complex space. A key strategy lies in a smart use of descriptors at multiple scales, ranging from atomic arrangements to macroscopic properties, to represent materials in high-dimensional abstract spaces. Network theory provides a powerful framework to structure and analyze these relationships, capturing hidden patterns and guiding discovery. Machine Learning complements this approach by enabling predictive modeling, dimensionality reduction, and the identification of promising material candidates. By integrating network-based methods with Machine Learning techniques, researchers can construct, analyze, and efficiently navigate the material space, uncovering novel materials with tailored properties. This review explores the synergy between network theory and ML, highlighting their role in accelerating materials discovery through a systematic and interpretable approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_09250 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | The quest for new materials: the network theory and machine learning perspectives Moi, Jacopo Spallarossa, Davide Bonetti, Stefano Burioni, Raffaella Caldarelli, Guido Materials Science Disordered Systems and Neural Networks Other Condensed Matter Statistical Mechanics Computational Physics Understanding and predicting the emergence of novel materials is a fundamental challenge in condensed matter physics, materials science and technology. With the rapid growth of materials databases in both size and reliability, the challenge shifts from data collection to efficient exploration of this vast and complex space. A key strategy lies in a smart use of descriptors at multiple scales, ranging from atomic arrangements to macroscopic properties, to represent materials in high-dimensional abstract spaces. Network theory provides a powerful framework to structure and analyze these relationships, capturing hidden patterns and guiding discovery. Machine Learning complements this approach by enabling predictive modeling, dimensionality reduction, and the identification of promising material candidates. By integrating network-based methods with Machine Learning techniques, researchers can construct, analyze, and efficiently navigate the material space, uncovering novel materials with tailored properties. This review explores the synergy between network theory and ML, highlighting their role in accelerating materials discovery through a systematic and interpretable approach. |
| title | The quest for new materials: the network theory and machine learning perspectives |
| topic | Materials Science Disordered Systems and Neural Networks Other Condensed Matter Statistical Mechanics Computational Physics |
| url | https://arxiv.org/abs/2502.09250 |