Deep Learning Model for Finding New Superconductors

Abstract

Exploration of new superconductors still relies on the experience and intuition of experts and is largely a process of experimental trial and error. In one study, only 3% of the candidate materials showed superconductivity. Here, we report the first deep learning model for finding new superconductors. We introduced the method named "reading periodic table" which represented the periodic table in a way that allows deep learning to learn to read the periodic table and to learn the law of elements for the purpose of discovering novel superconductors that are outside the training data. It is recognized that it is difficult for deep learning to predict something outside the training data. Although we used only the chemical composition of materials as information, we obtained an $R^2$ value of 0.92 for predicting $T_{\text{c}}$ for materials in a database of superconductors. We also introduced the method named "garbage-in" to create synthetic data of non-superconductors that do not exist. Non-superconductors are not reported, but the data must be required for deep learning to distinguish between superconductors and non-superconductors. We obtained three remarkable results. The deep learning can predict superconductivity for a material with a precision of 62%, which shows the usefulness of the model; it found the recently discovered superconductor CaBi2 and another one Hf0.5Nb0.2V2Zr0.3, neither of which is in the superconductor database; and it found Fe-based high-temperature superconductors (discovered in 2008) from the training data before 2008. These results open the way for the discovery of new high-temperature superconductor families. The candidate materials list, data, and method are openly available from the link https://github.com/tomo835g/Deep-Learning-to-find-Superconductors.

10 pages in main text. Deep learning, Machine learning, Material search, Superconductors

References in corpus (8)

• Conventional superconductivity at 203 K at high pressures
• Evidence for superconductivity above 260 K in lanthanum superhydride at megabar pressures
• DScribe: Library of Descriptors for Machine Learning in Materials Science
• Data-driven materials science: status, challenges and perspectives
• Machine learning modeling of superconducting critical temperature
• Exploration of new superconductors and functional materials and fabrication of superconducting tapes and wires of iron pnictides
• Superconductivity in CaBi${}_2$
• Deep-Learning Estimation of Band Gap with the Reading-Periodic-Table Method and Periodic Convolution Layer

Cited by in corpus (22)

• Towards high-throughput superconductor discovery via machine learning
• SuperMat: Construction of a linked annotated dataset from superconductors-related publications
• Predicting Superconducting Transition Temperature through Advanced Machine Learning and Innovative Feature Engineering
• Accelerating superconductor discovery through tempered deep learning of the electron-phonon spectral function
• Deep Learning Based Superconductivity: Prediction and Experimental Tests
• Applications of Lattice Gauge Equivariant Neural Networks
• Classification-based detection and quantification of cross-domain data bias in materials discovery
• A deep learning approach to search for superconductors from electronic bands
• Leveraging Composition-Based Material Descriptors for Machine Learning Optimization
• Semi-automatic staging area for high-quality structured data extraction from scientific literature
• Superconductor discovery in the emerging paradigm of Materials Informatics
• Data analysis of $ab$ $initio$ effective Hamiltonians in iron-based superconductors $\unicode{x2014}$ Construction of predictors for superconducting critical temperature
• Machine-learning Guided Search for Phonon-mediated Superconductivity in Boron and Carbon Compounds
• Accelerating the Search for Superconductors Using Machine Learning
• Exploring explicit coarse-grained structure in artificial neural networks
• Developing a Complete AI-Accelerated Workflow for Superconductor Discovery
• Tree Models Machine Learning to Identify Liquid Metal based Alloy Superconductor
• Critical Temperature Prediction for a Superconductor: A Variational Bayesian Neural Network Approach
• Composition-Based Machine Learning for Screening Superconducting Ternary Hydrides from a Curated Dataset
• Synergistic Fusion of Multi-Source Knowledge via Evidence Theory for High-Entropy Alloy Discovery
• Effects of Li Doping on Superconducting Properties of Citrate Gel Prepared Y1-xLixBa2Cu3O7-d Compound
• Signature of Unconventional Superconductivity in the High Temperature Normal State Resistivity