Improving the Interpretability of ANN-Based Predictions of Lattice Constants in Aliovalently Doped Perovskites Using Partial Dependence Plots
The relationship between structure and properties is fundamental in materials science, particularly for aliovalently doped perovskites, where structural changes significantly influence material performance. Accurate prediction of key structural parameters is essential for tailoring these materials f...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Crystals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4352/15/6/538 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The relationship between structure and properties is fundamental in materials science, particularly for aliovalently doped perovskites, where structural changes significantly influence material performance. Accurate prediction of key structural parameters is essential for tailoring these materials for advanced applications. In this study, we developed an Artificial Neural Network (ANN) model to predict lattice constants with high accuracy, achieving near-perfect R<sup>2</sup> values and minimal prediction errors across training and testing datasets. To address the interpretability challenge commonly associated with black-box models, we integrated Partial Dependence Plots (PDPs), enabling a transparent analysis of how input features, including lattice parameters <i>a</i>, <i>b</i>, <i>c</i>, and the number of formula units per unit cell (Z), affect model predictions. Our findings show that parameters <i>a</i>, <i>b</i>, and <i>c</i> generally contribute to lattice expansion, while Z exhibits an inverse relationship due to its impact on packing density. The inclusion of PDPs offers novel insights into the underlying physical relationships and enhances the trustworthiness of machine learning (ML) predictions in the context of perovskite design. This approach demonstrates the utility of combining high-accuracy ML models with interpretability techniques to accelerate discovery in materials science. |
|---|---|
| ISSN: | 2073-4352 |