About | Contact Us | Register | Login
ProceedingsSeriesJournalsSearchEAI
airo 23(1):

Research Article

A Machine Learning Based Investigative Analysis for Predicting the Critical Temperature of Superconductors

Download149 downloads
Cite
BibTeX Plain Text
  • @ARTICLE{10.4108/airo.3622,
        author={Fatin Abrar Shams and Rashed Hasan Ratul and Ahanf Islam Naf and Syed Shaek Hossain Samir and Samiur Rashid Abir and Fahim Faisal and Mirza Muntasir Nishat and Md Ashraful Hoque},
        title={A Machine Learning Based Investigative Analysis for Predicting the Critical Temperature of Superconductors},
        journal={EAI Endorsed Transactions on AI and Robotics},
        volume={2},
        number={1},
        publisher={EAI},
        journal_a={AIRO},
        year={2023},
        month={10},
        keywords={Superconductor, Critical Temperature, Machine Learning, Stacking Ensemble Method},
        doi={10.4108/airo.3622}
    }
    
  • Fatin Abrar Shams
    Rashed Hasan Ratul
    Ahanf Islam Naf
    Syed Shaek Hossain Samir
    Samiur Rashid Abir
    Fahim Faisal
    Mirza Muntasir Nishat
    Md Ashraful Hoque
    Year: 2023
    A Machine Learning Based Investigative Analysis for Predicting the Critical Temperature of Superconductors
    AIRO
    EAI
    DOI: 10.4108/airo.3622
Fatin Abrar Shams1, Rashed Hasan Ratul1, Ahanf Islam Naf1, Syed Shaek Hossain Samir1, Samiur Rashid Abir1, Fahim Faisal1,*, Mirza Muntasir Nishat1, Md Ashraful Hoque1
  • 1: Islamic University of Technology
*Contact email: faisaleee@iut-dhaka.edu

Abstract

INTRODUCTION: Ever since the initial discovery of superconductivity, the fundamental concept and the complex relationship between critical temperature and superconductive materials have been subject to extensive investigation. However, identifying superconductors that exhibit such behavior at normal temperatures remains a significant challenge, and there are still significant gaps in our understanding of this unique phenomenon, particularly regarding the fundamental criteria used to estimate critical temperature. OBJECTIVES: To address this knowledge gap, a plethora of machine learning techniques have been developed to model critical temperatures, given the inherent difficulty in predicting them using traditional methods. METHODS: Additionally, the limitations of the standard empirical formula in determining the temperature range require the development of more advanced and viable methods. This article presents an investigative analysis on the performance achieved by different supervised machine learning algorithms when used with three different feature selection techniques. RESULTS: The stacking model used in this work is found to be the best performer among all the algorithms tested, as reflected by the Root Mean Squared Error (RMSE) of 9.68, R2 score of 0.922, Mean Absolute Error (MAE) score of 5.383, and Mean Absolute Percentage Error (MAPE) score of 4.575. CONCLUSION: Therefore, it is observed that ML algorithms can contribute significantly in the domain of predictive analysis of modeling critical temperatures in superconductors and can assist in developing a robust computer-aided system to aid the education personals and research scientists to further assess the performance of the ML models.

Keywords
Superconductor, Critical Temperature, Machine Learning, Stacking Ensemble Method
Received
2023-07-25
Accepted
2023-10-27
Published
2023-10-30
Publisher
EAI
http://dx.doi.org/10.4108/airo.3622

Copyright © 2023 F. A. Shams et al., licensed to EAI. This is an open access article distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.

EBSCOProQuestDBLPDOAJPortico
EAI Logo

About EAI

  • Who We Are
  • Leadership
  • Research Areas
  • Partners
  • Media Center

Community

  • Membership
  • Conference
  • Recognition
  • Sponsor Us

Publish with EAI

  • Publishing
  • Journals
  • Proceedings
  • Books
  • EUDL