Prediction of superconducting transition temperature using a machine-learning method

Abstract

A high-transition-temperature (high-TC) superconductor is an important material used in many practical applications like magnetically levitated trains and power transmission. The superconducting transition temperature TC is determined by the layered crystals, bond lengths, valency properties of the ions and Coulomb coupling between electronic bands in adjacent, spatially separated layers. The optimal TC can be attained upon doping and applying the pressure for the optimal compounds. There is an algebraic relation for the optimal TC of the optimal compounds, TCO = KB-1 b/(ix), where i and x are two structural parameters, KB is Boltzmann's constant, b is a universal constant and TCO is the optimal transition temperature. Nevertheless, the TC of the non-optimum compounds is smaller than TCO. To predict the TC for the all compounds, we developed a prediction model based on the machine-learning method called support vector regression (SVR) using structural and electronic parameters to predict TC. In addition, the principal component analysis (PCA) was applied to reduce dimensions and interdependencies among the parameters, and particle swarm optimization (PSO) was utilized to search for the optimal parameters of SVR for an improved performance of the prediction model. The results showed that the proposed PCA-PSO-SVR model takes advantage of the machine-learning method to directly predict TC and theoretically provide guidance on measuring TC.

Upper limit of the transition temperature of superconducting materials

“… 25 , 26 , 27 ML models using different algorithms were trained to predict the existence of superconductivity and the T c of superconductors. 28 , 29 , 30 , 31 , 32 , 33 , 34 , 35 , 36 , 37 , 38 , 39 , 40 , 41 , 42 , 43 , 44 , 45 , 46 , 47 , 48 , 49 , 50 , 51 , 52 , 53 , 54 Progress has been made in several areas, such as how T c varies with doping, 28 , 29 , 30 , 31 , 32 , 33 , 34 , 35 the descriptors indicating superconducting mechanism, 36 , 37 , 38 , 39 structural factors affecting T c , 43 , 44 and candidates of new high- T c superconductors. 46 , 51 So far, ML models predicting T c have yielded good predictive scores.…”

Application of machine learning for advanced material prediction and design

“…Liu et al 94 established a new model, named PCA‐PSO‐SVR, to predict the T c of different high T c superconductors (Figure 8). The principal component analysis (PCA) is used to reduce the dimensions and interdependencies of different parameters, whereas particle swarm optimization (PSO) is used to optimize the parameters and improve the performance of SVR.…”

Machine learning in materials design: Algorithm and application*

“…15), this was later discussed by Meredig et al who proposed the LOOCV. [155] The PCA, particle swarm optimization (PSO), and SVR algorithms were combined by Liu et al [210] to predict the T c . Using datasets extracted from literature and dividing data by LOOCV, the PCA-PSO-SVR model with a corresponding MAE of 5.34 K performed better than the model without PCA and the neural network model they trained.…”