Structure-Driven Prediction of Magnetic Order in Uranium Compounds

Abstract

The advancement of machine learning technologies has revolutionized the search and optimization of material properties. These algorithms often rely on theoretical calculations, such as density functional theory (DFT), for data inputs and validation, which are not always effective for uranium-based materials due to their strong electron correlations. This study presents a computationally inexpensive machine learning approach, specifically a random forest classifier, to predict the magnetic ground states of uranium compounds using only structural inputs. Our model, trained on a curated dataset of experimentally-verified magnetic orders, achieves a mean accuracy of 60.2%, significantly outperforming random chance. By excluding computationally intensive DFT calculations, our method offers a faster and reliable alternative for discovering new materials with desirable magnetic properties, addressing the challenges posed by strong correlations in quantum materials.

References in corpus (23)

• A linear response approach to the calculation of the effective interaction parameters in the LDA+U method
• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• On representing chemical environments
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Quantum Criticality in Heavy Fermion Metals
• Hubbard-corrected DFT energy functionals: the LDA+U description of correlated systems
• DScribe: Library of Descriptors for Machine Learning in Materials Science
• Comparing molecules and solids across structural and alchemical space
• Machine Learning Unifies the Modelling of Materials and Molecules
• Machine learning modeling of superconducting critical temperature
• Benchmarking Materials Property Prediction Methods: The Matbench Test Set and Automatminer Reference Algorithm
• Unconventional Superconductivity in UTe2
• Feature Optimization for Atomistic Machine Learning Yields A Data-Driven Construction of the Periodic Table of the Elements
• Quantum phase transitions in heavy fermion metals and Kondo insulators
• Hidden order and beyond: an experimental-theoretical overview of the multifaceted behavior of URu${}_2$Si${}_2$
• High-throughput search for magnetic and topological order in transition metal oxides
• An accelerating approach of designing ferromagnetic materials via machine learning modeling of magnetic ground state and Curie temperature
• Breakdown of the scaling relation of anomalous Hall effect in Kondo lattice ferromagnet USbTe
• Itinerant ferromagnetism in actinide 5f electrons system: Phenomenological analysis with spin fluctuation theory
• Sensitivity and Dimensionality of Atomic Environment Representations used for Machine Learning Interatomic Potentials
• Orbital-selective Kondo-lattice and enigmatic f-electrons emerging from inside the antiferromagnetic phase of a heavy fermion
• Understanding Magnetic Properties of Actinide-Based Compounds from Machine Learning
• Prediction of Large Magnetic Moment Materials With Graph Neural Networks and Random Forests

Cited by in corpus (1)

• Signature of Unconventional Superconductivity in the High Temperature Normal State Resistivity