A New Workflow for Materials Discovery Bridging the Gap Between Experimental Databases and Graph Neural Networks

2026-01-31

AI Summary

This work addresses the critical limitation of existing experimental materials databases, which typically lack atomic coordinates and thus hinder the application of advanced machine learning models such as graph neural networks (GNNs) for property prediction. For the first time, the study systematically aligns experimental data with crystallographic information from the Inorganic Crystal Structure Database (ICSD), constructing a novel materials database that includes complete atomic coordinates. This alignment enables direct utilization of experimental data in GNN-based modeling and facilitates transfer learning. Evaluated on tasks predicting magnetic ordering temperatures and ground-state magnetic properties, the approach significantly reduces mean absolute error (MAE) and improves correct classification rate (CCR), demonstrating both its effectiveness and methodological innovation.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Incorporating Machine Learning (ML) into material property prediction has become a crucial step in accelerating materials discovery. A key challenge is the severe lack of training data, as many properties are too complicated to calculate with high-throughput first principles techniques. To address this, recent research has created experimental databases from information extracted from scientific literature. However, most existing experimental databases do not provide full atomic coordinate information, which prevents them from supporting advanced ML architectures such as Graph Neural Networks (GNNs). In this work, we propose to bridge this gap through an alignment process between experimental databases and Crystallographic Information Files (CIF) from the Inorganic Crystal Structure Database (ICSD). Our approach enables the creation of a database that can fully leverage state-of-the-art model architectures for material property prediction. It also opens the door to utilizing transfer learning to improve prediction accuracy. To validate our approach, we align NEMAD with the ICSD and compare models trained on the resulting database to those trained on NEMAD originally. We demonstrate significant improvements in both Mean Absolute Error (MAE) and Correct Classification Rate (CCR) in predicting the ordering temperatures and magnetic ground states of magnetic materials, respectively.

Problem

• experimental databases
• atomic coordinates
• Graph Neural Networks
• materials discovery
• machine learning

Innovation

• Graph Neural Networks
• Materials Discovery
• Experimental Database Alignment
• Crystallographic Information File
• Transfer Learning