Predicting lattice thermal conductivity from fundamental material properties using machine learning techniques

Abstract

High-throughput screening and material informatics have shown a great power in novel materials discovery including batteries, high entropy alloys, photocatalysts, etc. However, the lattice thermal conductivity (κ) oriented high-throughput screening...

High-throughput computational discovery of 3218 ultralow thermal conductivity and dynamically stable materials by dual machine learning models

“…We observe a positive correlation between mass density and LTC, which is consistent with domain knowledge and previous ML models. 14 Fig. 7b shows the correlation between the total weight of structures and the LTC, where a negative correlation is found.…”

“…Alternatively, other empirical models to evaluate LTC have been applied, including the Debye-Callaway model, 11,12 Slack model, 13 but these methods are less accurate. 14 The classical molecular dynamics (MD) simulation [15][16][17][18][19] can also be used to study the thermal transport processes and to predict the LTC of materials, however, the accuracy of this approach relies signicantly on that of the underlying interatomic potentials which are challenging to obtain for a large number of materials, 20,21 even with the help of the recently developed machine learning (ML) interatomic potential techniques. 22,23 ML has been successfully applied for solving complex problems and improving decision making at both the academic and industrial levels.…”

BNM-CDGNN: Batch Normalization Multilayer Perceptron Crystal Distance Graph Neural Network for Excellent-Performance Crystal Property Prediction

“…4 Wei et al proposed the model combining deep learning and a semisupervised technique to achieve large-scale screening of advanced thermal materials. 5 Alsaffar et al proposed a convolutional neural network with multilayer perceptron (MLP) with deep features, which adjusted the number of hidden layer neurons based on four innovative ideas to enhance the diagnosis ability of cervical cancer. 6 Zhang et al designed a universal deep reinforcement learning model that requires only one-dimensional amino acid sequence information to design novel drug molecules based on different protein targets.…”

“…Lin et al demonstrated for the first time the applicability of a 3D convolutional neural network (CNN) in material recognition for predicting adsorption properties . Wei et al proposed the model combining deep learning and a semisupervised technique to achieve large-scale screening of advanced thermal materials . Alsaffar et al proposed a convolutional neural network with multilayer perceptron (MLP) with deep features, which adjusted the number of hidden layer neurons based on four innovative ideas to enhance the diagnosis ability of cervical cancer .…”

Anti-bonding mediated record low and comparable-to-air lattice thermal conductivity of two metallic crystals

“…Recent advances in artificial intelligence (AI) techniques have significantly accelerated the discovery of materials with optimal properties for various applications, including superconductivity, catalysis, and thermoelectricity. [19][20][21][22] In our recent high-throughput prediction of the phonon transport properties of large-scale inorganic crystals based on deep learning, 22,23 after thoroughly screening 80 000 cubic crystals from the Open Quantum Materials Database (OQMD), 24,25 two metallic compounds, namely PbAuGa and CsKNa, are identified with anomalously low phononic thermal conductivity, having the lowest phononic thermal conductivity among all crystalline materials we have known so far. Obviously, the phononic thermal conductivity of metallic PbAuGa and CsKNa is well below the reasonable range.…”