Synergistic effects of rare-earth doping on the magnetic properties of orthochromates: A machine learning approach

TL;DR

This work addresses how rare-earth doping affects the magnetic and ferroic properties of rare-earth orthochromates $RECrO_3$ by employing a CNN-based framework trained on experimental and literature data to predict the Neél temperature $T_{\textrm{N}}$, remanent polarization $P_{\textrm{r}}$, and piezoelectric coefficient $d_{33}$. The authors demonstrate that targeted RE-doping, co-doping, and high-entropy multi-element doping can tune $T_{\textrm{N}}$, with qualitative agreement to literature and DFT trends, though quantitative deviations remain for some $4f$-electron-containing ions. The study also finds that $P_{\textrm{r}}$ and $d_{33}$ in these materials are relatively modest, limiting ferroelectric and piezoelectric applications. Overall, the paper provides a robust ML-driven framework for high-throughput screening and optimization of RECrO$_3$ materials for energy storage and sensor technologies, enabling rational design of multi-element doped systems.

Abstract

Multiferroic materials, particularly rare-earth orthochromates (RECrO$_3$), have garnered significant interest due to their unique magnetic and electric-polar properties, making them promising candidates for multifunctional devices. Although extensive research has been conducted on their antiferromagnetic (AFM) transition temperature (N$\acute{\textrm{e}}$el temperature, $T_\textrm{N}$), ferroelectricity, and piezoelectricity, the effects of doping and substitution of rare-earth (RE) elements on these properties remain insufficiently explored. In this study, convolutional neural networks (CNNs) were employed to predict and analyze the physical properties of RECrO$_3$ compounds under various doping scenarios. Experimental and literature data were integrated to train machine learning models, enabling accurate predictions of $T_\textrm{N}$, besides remanent polarization ($P_\textrm{r}$) and piezoelectric coefficients ($d_{33}$). The results indicate that doping with specific RE elements significantly impacts $T_\textrm{N}$, with optimal doping levels identified for enhanced performance. Furthermore, high-entropy RECrO$_3$ compounds were systematically analyzed, demonstrating how the inclusion of multiple RE elements influences magnetic properties. This work establishes a robust framework for predicting and optimizing the properties of RECrO$_3$ materials, offering valuable insights into their potential applications in energy storage and sensor technologies.

Figures (8)

• Figure 1: Workflow for predicting the physical properties of the RECrO$_3$ compound family. a We compiled data from prior studies in the literature, b which was then integrated into a convolutional neural network model, c subsequently trained, and the model's performance evaluated for the stability and accuracy of the predicted results. d These include parameters such as the N$\acute{\textrm{e}}$el temperature ($T_\textrm{N}$), remanent electric polarization ($P_\textrm{r}$), and piezoelectric coefficient ($d_{33}$).
• Figure 2: (Left) Predicted AFM transition temperature ($T_\textrm{N}$) as a function of RE elements for RECrO$3$ orthochromates, as obtained from a convolutional neural network model. (Right) Summary of $T_\textrm{N}$ values for RECrO$_3$ compounds as reported in the literature.
• Figure 3: (Left) Predicted AFM transition temperature ($T_\textrm{N}$) as a function of RE elements for (La$_{0.5}$RE$_{0.5}$)CrO$_3$ orthochromates, as obtained from a convolutional neural network model. (Right) Comparison of $T_\textrm{N}$ values for (La$_{0.5}$RE$_{0.5}$)CrO$_3$ compounds summarized from the literature.
• Figure 4: Predicted performance metrics of the AFM transition temperature ($T_\textrm{N}$) as a function of doping with various RE elements in (La$_{1-x}$RE$_x$)CrO$_3$ orthochromates at the optimal doping concentration (x), as calculated using a convolutional neural network model.
• Figure 5: Predicted overall performance metrics of the AFM transition temperature ($T_\textrm{N}$) as a function of co-doping with two RE elements (RE1 and RE2) for the (La$_{0.5}$RE1$_{0.25}$RE2$_{0.25}$)CrO$_3$ orthochromate, as calculated using a convolutional neural network model.