An accelerating approach of designing ferromagnetic materials via machine learning modeling of magnetic ground state and Curie temperature

Abstract

Magnetic materials have a plethora of applications from information technologies to energy harvesting. However, their functionalities are often limited by the magnetic ordering temperature. In this work, we performed random forest on the magnetic ground state and the Curie temperature (T C) to classify ferromagnetic and antiferromagnetic compounds and to predict the T C of the ferromagnets. The resulting accuracy is about 87% for classification and 91% for regression. When the trained model is applied to magnetic intermetallic materials in Materials Project, the accuracy is comparable. Our work paves the way to accelerate the discovery of new magnetic compounds for technological applications. IMPACT STATEMENT A machine learning model to classify ferromagnetic and antiferromagnetic compounds and to predict the Curie temperature of the ferromagnets is constructed, which could accelerate the discovery of new magnetic compounds.

Machine learning assisted hierarchical filtering: a strategy for designing magnets with large moment and anisotropy energy

“…Nelson and Sanvito 12 applied ML to predict T c of FM materials. Based on high throughput computations and ML, new magnetic materials with high T c were predicted in the Heusler family by Sanvito et al 13 Long et al 14 applied ML to design of ferromagnetic materials by classifying magnetic materials as ferro-(FM) or anti-ferromagnets (AFM), and predicting T c of the FMs. Rhone et al 6 applied ML to predict formation energies and magnetic moments of TM trichalcogenide layers.…”

High-throughput design of magnetic materials

“…27 empirical features are taken as descriptors with detailed analysis on the feature relevance. Two recent work [607,608] started with the AtomWork database [609] and used more universal chemical and structural descriptors. It is observed that the Curie temperature is mostly driven by the chemical position, where compounds with polymorphs are to be studied in detail with structural features.…”

“…For instance, the T C and T N are collected for about 10 000 compounds in the AtomWork data [609], with significant uncertainty for compounds with multiple experimental values thus the database should be used with caution. In addition, both machine learning modelings of T C [607,608] are done based on the random forest algorithm, whereas our test using the Gaussian kernel regression method leads to less satisfactory accuracy. This implies that the data are quite heterogeneous.…”

Understanding and optimization of hard magnetic compounds from first principles

“…T with an accuracy of 50K [94]. Long et al applied random forrest for classifying ferromagnetic and antiferromagnetic compounds and predicting the Curie temperature [95]. Design of a good descriptor is an important issue in materials informatics.…”

“…Nelson and Sanvito compared the performance of several different regression models using experimental data for about 2500 known ferromagnetic compounds, and showed that the best model predicts with an accuracy of 50 K [ 94 ]. Long et al applied random forrest for classifying ferromagnetic and antiferromagnetic compounds and predicting the Curie temperature [ 95 ].

Figure 5.

…”