Lean CNNs for mapping electron charge density fields to material properties
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910944784809984 |
|---|---|
| author | Ray, Pranoy Choudhury, Kamal Kalidindi, Surya R. |
| author_facet | Ray, Pranoy Choudhury, Kamal Kalidindi, Surya R. |
| contents | This work introduces a lean CNN (convolutional neural network) framework, with a drastically reduced number of fittable parameters (<81K) compared to the benchmarks in current literature, to capture the underlying low-computational cost (i.e., surrogate) relationships between the electron charge density (ECD) fields and their associated effective properties. These lean CNNs are made possible by adding a pre-processing step (i.e., a feature engineering step) that involves the computation of the ECD fields' spatial correlations (specifically, 2-point spatial correlations). The viability and benefits of the proposed lean CNN framework are demonstrated by establishing robust structure-property relationships involving the prediction of effective material properties using the feature-engineered ECD fields as the only input. The framework is evaluated on a dataset of crystalline cubic systems consisting of 1410 molecular structures spanning 62 different elemental species and 3 space groups. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_09826 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Lean CNNs for mapping electron charge density fields to material properties Ray, Pranoy Choudhury, Kamal Kalidindi, Surya R. Materials Science Disordered Systems and Neural Networks Applied Physics This work introduces a lean CNN (convolutional neural network) framework, with a drastically reduced number of fittable parameters (<81K) compared to the benchmarks in current literature, to capture the underlying low-computational cost (i.e., surrogate) relationships between the electron charge density (ECD) fields and their associated effective properties. These lean CNNs are made possible by adding a pre-processing step (i.e., a feature engineering step) that involves the computation of the ECD fields' spatial correlations (specifically, 2-point spatial correlations). The viability and benefits of the proposed lean CNN framework are demonstrated by establishing robust structure-property relationships involving the prediction of effective material properties using the feature-engineered ECD fields as the only input. The framework is evaluated on a dataset of crystalline cubic systems consisting of 1410 molecular structures spanning 62 different elemental species and 3 space groups. |
| title | Lean CNNs for mapping electron charge density fields to material properties |
| topic | Materials Science Disordered Systems and Neural Networks Applied Physics |
| url | https://arxiv.org/abs/2505.09826 |