Machine learning based high temperature superconducting material interpretable prediction method, system, and computer readable storage medium

By constructing a random forest model based on the SuperCon database and Magpie software, extracting key features and performing weighted optimization, the problems of low efficiency and poor accuracy in the prediction of high-temperature superconducting materials are solved, and efficient and interpretable screening and design of high-temperature superconducting materials are realized.

CN122598828APending Publication Date: 2026-08-18MATERIAL INST OF CHINA ACADEMY OF ENG PHYSICS
0 Cites 0 Cited by

Patent Information

Application Number
CN202610726014.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-05-25
Publication Date
2026-08-18

AI Technical Summary

Technical Problem

Existing technologies for the discovery and prediction of high-temperature superconducting materials suffer from limitations such as time-consuming and labor-intensive experimental trial-and-error methods, high computational complexity and long processing time for DFT-based quantum computing methods, and poor data uniformity and interpretability of machine learning methods. These limitations restrict the prediction accuracy and generalization ability of high-temperature superconducting materials.

Method used

A superconducting materials dataset was constructed based on the SuperCon database. Material features were generated using Magpie software, redundancy was removed using Pearson correlation coefficients, and a random forest model was used for training. The average deviation of ground-state atomic volume, the average deviation of unfilled s-orbital electrons, and the average deviation of elemental electronegativity were extracted as key features to form an interpretable prediction model. The stability was verified by calculating the Ehull value.

Benefits of technology

Efficient and interpretable prediction of high-temperature superconducting materials was achieved. The model achieved an R² of 0.935 and an RMSE of 7.4 on the test set. Seven candidate materials with Tc>70K were successfully screened, ensuring that the prediction results are consistent with the superconducting physical mechanism and guiding the directional design of material composition and structure.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The application discloses a high-temperature superconducting material interpretable prediction method and system based on machine learning and a computer readable storage medium. The method comprises the following steps: constructing a superconducting material dataset to generate material characteristics; constructing a random forest model for training, outputting the importance ranking of the material characteristics through feature_importance, thereby extracting three material characteristics, i.e., ground state atomic volume average deviation, unfilled s orbital electron average deviation and element electronegativity average deviation, as key characteristics for determining the superconducting critical temperature; performing weighted optimization on the trained random forest model by using the key characteristics to form an interpretable prediction model; and predicting candidate materials by using the interpretable prediction model and completing stability verification and screening through Ehull value calculation. The application successfully identifies three key characteristics affecting the superconducting critical temperature through feature importance analysis, thereby ensuring that the prediction result is consistent with the superconducting physical mechanism.
Need to check novelty before this filing date? Find Prior Art