Northeast Materials Database (NEMAD): Enabling Discovery of High Transition Temperature Magnetic Compounds

2024-09-24

arXiv.org

AI Summary

To address the bottlenecks of small scale, sparse labeling, and weak feature representation in experimental databases for intelligent magnetic materials design, this work introduces NEMAD—the first experimentally oriented magnetic materials database automatically constructed using large language models (LLMs), encompassing 26,706 materials with compositional, crystallographic, Curie/Néel temperature, and magnetic property data. We propose an LLM-driven paradigm for automated magnetic data curation, integrating magnetic property-aware feature engineering, graph neural networks, and ensemble regression models—rigorously validated via cross-dataset evaluation on Materials Project. Our approach achieves 90% classification accuracy and R² scores of 0.86 (MAE = 62 K) and 0.85 (MAE = 32 K) for Curie and Néel temperature prediction, respectively, substantially surpassing conventional database limitations in both quality and scale. Furthermore, we successfully identify 62 high-Curie-temperature (>500 K) ferromagnetic and 19 high-Néel-temperature (>100 K) antiferromagnetic candidate materials.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Natural Language Processing: (Large) Language Models

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Web Mining and Content Analysis: Large pretrained models with web data
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

The discovery of novel magnetic materials with greater operating temperature ranges and optimized performance is essential for advanced applications. Current data-driven approaches are challenging and limited due to the lack of accurate, comprehensive, and feature-rich databases. This study aims to address this challenge by introducing a new approach that uses Large Language Models (LLMs) to create a comprehensive, experiment-based, magnetic materials database named the Northeast Materials Database (NEMAD), which consists of 26,706 magnetic materials (www.nemad.org). The database incorporates chemical composition, magnetic phase transition temperatures, structural details, and magnetic properties. Enabled by NEMAD, machine learning models were developed to classify materials and predict transition temperatures. Our classification model achieved an accuracy of 90% in categorizing materials as ferromagnetic (FM), antiferromagnetic (AFM), and non-magnetic (NM). The regression models predict Curie (N'eel) temperature with a coefficient of determination (R2) of 0.86 (0.85) and a mean absolute error (MAE) of 62K (32K). These models identified 62 (19) FM (AFM) candidates with a predicted Curie (N'eel) temperature above 500K (100K) from the Materials Project. This work shows the feasibility of combining LLMs for automated data extraction and machine learning models in accelerating the discovery of magnetic materials.

Problem

• Lack of accurate comprehensive databases for magnetic materials discovery
• Limited data-driven approaches for predicting magnetic material properties
• Need to accelerate discovery of high-temperature magnetic materials

Innovation

• LLMs create magnetic materials database
• Machine learning predicts magnetic transition temperatures
• Combining LLMs with ML accelerates material discovery