CoChat
Sign Up
Cited by 22Machine Learning in Materials SciencePhysics of Superconductivity and MagnetismMachine Learning and Data Classification

Prediction of the Critical Temperature of Superconductors Based on Two-Layer Feature Selection and the Optuna-Stacking Ensemble Learning Model

Open access
Yu, Jiahao, Zhao, Yongman, Pan, Rongshun, Zhou, Xue, Wei, Zikai·2023·ACS Omega
DOI 10.1021/acsomega.2c06324PMC PMC9878623
Open this paper in CoChat — free accountOpen PDF

Abstract

High Resolution Image Download MS PowerPoint Slide The study of superconductors’ critical temperature ( T c ) has been a matter of interest. A method combining a two-layer feature selection (TL) and Optuna-Stacking ensemble learning model is proposed in the study for predicting T c from physicochemical components. Since most machine-learning models require a large amount of prior knowledge to construct the feature vectors associated with T c manually, they may contain redundant or invalid features that adversely affect the analysis and prediction of T c . The TL model combines the advantages of filtered and packed feature selection. In the first layer, feature importance is ranked by “SHapley Additive explain (SHAP)” in combination with CatBoost, followed by maximum mutual information coefficient (MIC) and distance correlation coefficient (DCC) for initial feature selection in terms of feature importance ranking. The second layer uses a cross-validation-based genetic algorithm (cv-GA) to eliminate the remaining redundant/invalid features. The selected features are fed into the Stacking integrated learning model to achieve prediction of Tc, and the multidimensional hyperparametric optimization of the metamodel is achieved by Optuna, an improved Bayesian hyperparametric optimization framework based on the Tree-structured Parzen Estimator (TPE) and pruning strategy. The model has obvious advantages and generality in terms of prediction performance and feature reduction rate, and it also proves to be suitable for high-temperature superconductor T c prediction. It provides an efficient and cost-effective method for data-driven superconductor research.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1021/acsomega.2c06324

Cites

1 of 1 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • The default tree-structured parzen estimator (TPE) optimization algorithm in the Optuna optimization framework enables hyperparameters to be automatically optimized to reduce fitting errors.

    “The default tree-structured parzen estimator (TPE) optimization algorithm [32] in the Optuna optimization framework enables hyperparameters to be automatically optimized to reduce fitting errors.”

    From Research on Energy-Saving Optimization of Mushroom Growing Control Room Based on Neural Network Model Predictive Control (2025) · cites this paper as [32]

    The Abstract describes Optuna as a framework based on TPE and says it optimizes metamodel hyperparameters. The Results and Discussion report lower prediction errors for the Optuna-Stacking model. Our copy does not say TPE is Optuna’s default algorithm or establish that TPE itself, rather than the combined model, reduced fitting errors. (LLM, conf=0.83)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 38

  1. Seo J. R.; Nam G.-D.; Park M. Design and characteristics study of a 1 MW class superconducting motor for small-ship propulsions. J. Korean Soc. Mar. Eng. 2019, 43, 750– 754. 10.5916/jkosme.2019.43.9.750. · DOI
  2. Manolopoulos C. D.; Iacchetti M. F.; Smith A. C.; Berger K.; Husband M.; Miller P. Stator Design and Performance of Superconducting Motors for Aerospace Electric Propulsion Systems. IEEE Trans. Appl. Supercond. 2018, 28, 1– 5. 10.1109/TASC.2018.2814742. · DOI
  3. Maslennikov Y. V.; Slobodchikov V. Y.; Krymov V. A.; Khanin V. V.; Koshelets V. P. Gradiometers based on superconducting quantum interference device for nondestructive testing. J. Commun. Technol. Electron. 2016, 61, 1383– 1389. 10.1134/S1064226916120172. · DOI
  4. Dhillon A. K.; Ghosh P. Exergetic analysis of reverse Brayton cryocooler with different turbine arrangements for HTS power cables. Cryogenics 2021, 115, 103262 10.1016/j.cryogenics.2021.103262. · DOI
  5. Dan Y.; Dong R.; Cao Z.; Li X.; Niu C.; Li S.; Hu J. Computational Prediction of Critical Temperatures of Superconductors Based on Convolutional Gradient Boosting Decision Trees. IEEE Access 2020, 8, 57868– 57878. 10.1109/ACCESS.2020.2981874. · DOI
  6. Krinitsina T. P.; Kuznetsova E. I.; Degtyarev M. V.; Blinova Y. V. MgB2-Based Superconductors: Structure and Properties. Phys. Met. Metallogr. 2021, 122, 1183– 1206. 10.1134/S0031918X2112005X. · DOI
  7. Drozdov A. P.; Kong P. P.; Minkov V. S.; Besedin S. P.; Kuzovnikov M. A.; Mozaffari S.; Balicas L.; Balakirev F. F.; Graf D. E.; Prakapenka V. B.; Greenberg E.; Knyazev D. A.; Tkacz M.; Eremets M. I. Superconductivity at 250 K in lanthanum hydride under high pressures. Nature 2019, 569, 528– 531. 10.1038/s41586-019-1201-8. 31118520 · DOI
  8. Ravaioli E.; Davis D.; Marchevsky M.; Sabbi G. L.; Shen T.; Verweij A.; Zhang K. A new quench detection method for HTS magnets: stray-capacitance change monitoring. Phys. Scr. 2020, 95, 015002 10.1088/1402-4896/ab4570. · DOI
  9. Zhang Y.; Xu X. Yttrium barium copper oxide superconducting transition temperature modeling through gaussian process regression. Comput. Mater. Sci. 2020, 179, 109583 10.1016/j.commatsci.2020.109583. · DOI
  10. Sharma A.; Singh P.; Liaw P. K.; Balasubramanian G.; Johnson D. D. Atomistic clustering-ordering and high-strain deformation of an Al0.1CrCoFeNi high-entropy alloy. Sci. Rep. 2016, 6, 31028 10.1038/srep31028. 27498807 PMC4976365 · DOI
  11. Yeh J. W.; Chen S. K.; Lin S. J.; Gan J. Y.; Chin T. S.; Shun T. T.; Tsau C. H.; Chang S. Y. Nanostructured High-Entropy Alloys with Multiple Principal Elements: Novel Alloy Design Concepts and Outcomes. Adv. Eng. Mater. 2004, 6, 299– 303. 10.1002/adem.200300567. · DOI · Paper page
  12. Sharma A.; Balasubramanian G. Dislocation dynamics in Al 0.1 CoCrFeNi high-entropy alloy under tensile loading. Intermetallics 2017, 91, 31– 34. 10.1016/j.intermet.2017.08.004. · DOI
  13. Li S.; Dan Y.; Li X.; Hu T.; Dong R.; Cao Z.; Hu J. Critical Temperature Prediction of Superconductors Based on Atomic Vectors and Deep Learning. Symmetry 2020, 12, 262 10.3390/sym12020262. · DOI
  14. Perdew J. P.; Burke K.; Ernzerhof M. Erratum, Generalized Gradient Approximation Made Simple. Phys. Rev. Lett. 1996, 77, 3865– 3868. 10.1103/PhysRevLett.77.3865. 10062328 · DOI · Paper page
  15. Dimiduk D. M.; Holm E. A.; Niezgoda S. R. Perspectives on the Impact of Machine Learning, Deep Learning, and Artificial Intelligence on Materials, Processes, and Structures Engineering. Integr. Mater. Manuf. Innovation 2018, 7, 157– 172. 10.1007/s40192-018-0117-8. · DOI · Paper page
  16. Le T. D.; Noumeir R.; Quach H. L.; Kim J. H.; Ji H. K.; Kim H. M. Critical Temperature Prediction for a Superconductor: A Variational Bayesian Neural Network Approach. IEEE Trans. Appl. Supercond. 2020, 30, 1– 5. 10.1109/TASC.2020.2971456. · DOI
  17. Cai C. Z.; Xiao T. T.; Tang J. L.; Huang S. J. Analysis of process parameters in the laser deposition of YBa2Cu3O7 superconducting films by using SVR. Phys. C 2013, 493, 100– 103. 10.1016/j.physc.2013.03.038. · DOI
  18. Zhang Y.; Xu X. Predicting doped MgB2 superconductor critical temperature from lattice parameters using Gaussian process regression. Phys. C 2020, 573, 1353633 10.1016/j.physc.2020.1353633. · DOI
  19. Zeng S.; Zhao Y.; Li G.; Wang R.; Wang X.; Ni J. Atom table convolutional neural networks for an accurate prediction of compounds properties. npj Comput. Mater. 2019, 5, 84 10.1038/s41524-019-0223-y. · DOI
  20. Zhang Y.; Xu X. Predicting doped Fe-based superconductor critical temperature from structural and topological parameters using machine learning. Int. J. Mater. Res. 2021, 112, 2– 9. 10.1515/ijmr-2020-7986. · DOI
  21. Hamidieh K. A data-driven statistical model for predicting the critical temperature of a superconductor. Comput. Mater. Sci. 2018, 154, 346– 354. 10.1016/j.commatsci.2018.07.052. · DOI
  22. Lu Z. Q. J. The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd edition. J. R. Stat. Soc.: Ser. A 2010, 173, 693– 694. 10.1111/j.1467-985X.2010.00646_6.x. · DOI
  23. Kim Y.; Kim S. B. Collinear groupwise feature selection via discrete fusion group regression. Pattern Recognit. 2018, 83, 1– 13. 10.1016/j.patcog.2018.05.013. · DOI
  24. Hu Z.; Bao Y.; Tao X.; Chiong R. Hybrid filter-wrapper feature selection for short-term load forecasting. Eng. Appl. Artif. Intell. 2015, 40, 17– 27. 10.1016/j.engappai.2014.12.014. · DOI
  25. Yang C.; Zhang W.; Zou J.; Hu S.; Qiu J. Feature Selection in Decision Systems: A Mean-Variance Approach. Math. Probl. Eng. 2013, 2013, 1– 8. 10.1155/2013/268063. · DOI
  26. Nasir I. M.; Khan M. A.; Yasmin M.; Shah J. H.; Damasevicius R.; et al. Pearson Correlation-Based Feature Selection for Document Classification Using Balanced Training. Sensors 2020, 20, 6793 10.3390/s20236793. 33261136 PMC7730850 · DOI
  27. Dhindsa A.; Bhatia S.; Agrawal S.; Sohi B. S. An Improvised Machine Learning Model Based on Mutual Information Feature Selection Approach for Microbes Classification. Entropy 2021, 23, 257 10.3390/e23020257. 33672252 PMC7927045 · DOI
  28. Rosario S. F.; Thangadurai K. RELIEF: Feature Selection Approach. Int. J. Innovative Res. Dev. 2015, 4, 12– 15.
  29. Amini F.; Hu G. A two-layer feature selection method using Genetic Algorithm and Elastic Net. Expert Syst. Appl. 2021, 166, 114072 10.1016/j.eswa.2020.114072. · DOI
  30. Chandrashekar G.; Sahin F. A survey on feature selection methods. Comput. Electr. Eng. 2014, 40, 16– 28. 10.1016/j.compeleceng.2013.11.024. · DOI · Paper page
  31. Pashaei E.; Pashaei E. Hybrid binary arithmetic optimization algorithm with simulated annealing for feature selection in high-dimensional biomedical data. J. Supercomput. 2022, 78, 15598– 15637. 10.1007/s11227-022-04507-2. · DOI
  32. Li A.-D.; Xue B.; Zhang M. Improved binary particle swarm optimization for feature selection with new initialization and search space reduction strategies. Appl. Soft Comput. 2021, 106, 81– 86. 10.1016/j.asoc.2021.107302. · DOI
  33. Li J.; Cheng K.; Wang S.; Morstatter F.; Trevino R. P.; Tang J.; Liu H. Feature Selection: A Data Perspective. ACM. Comput. Surv. 2018, 50, 1– 45. 10.1145/3136625. · DOI · Paper page
  34. Lee G.; Kim J.; Lee C. State-of-health estimation of Li-ion batteries in the early phases of qualification tests: An interpretable machine learning approach. Expert Syst. Appl. 2022, 197, 31– 36. 10.1016/j.eswa.2022.116817. · DOI
  35. Edelmann D.; Mori T. F.; Szekely G. J. On relationships between the Pearson and the distance correlation coefficients. Stat. Probab. Lett. 2021, 169, 108960 10.1016/j.spl.2020.108960. · DOI
  36. García-Nieto P.; García-Gonzalo E.; Paredes-Sánchez J. Prediction of the critical temperature of a superconductor by using the WOA/MARS, Ridge, Lasso and Elastic-net machine learning techniques. Neural Comput. Appl. 2021, 33, 17131– 17145. 10.1007/s00521-021-06304-z. · DOI
  37. Viatkin D.; Garcia-Zapirain B.; Méndez-Zorrilla A.; Zakharov M. Deep Learning Approach for Prediction of Critical Temperature of Superconductor Materials Described by Chemical Formulas. Front. Mater. 2021, 8, 714752 10.3389/fmats.2021.714752. · DOI
  38. Maxwell E. The isotope effect in superconductivity. Phys. Today 1952, 5, 14– 18. 10.1063/1.3067418. · DOI

Cited by

Sorted by citations

Authors
Yu, J., Zhao, Y., Pan, R., Zhou, X., & Wei, Z.
Affiliations
Shihezi University (CN)
Corresponding author
Zhao, Yongman
ORCID
Venue
ACS Omega
Publisher
American Chemical Society (ACS)
Published
2023-01-13
Volume
8
Issue
3
Pages
3078-3090
ISSN
2470-1343 (ISSN-L)
DOI
10.1021/acsomega.2c06324
PMC
PMC9878623
OpenAlex
W4316036497
Cited by
22
References
1
Citations by year
2026: 6 · 2025: 5 · 2024: 5 · 2023: 6
FWCI
1.62
Type
journal article
Language
en
Open access
Licence
Locations
  • ACS Omega (publishedVersion, cc-by-nc-nd)
  • PubMed Central (publishedVersion, cc-by-nc-nd)
  • PubMed (publishedVersion)
Funders
  • National New Material Production and Application Demonstration Platform Construction Project (TC200H01X-5)
  • Key Laboratory of the Modern Agricultural Machinery (XJBTBJ[2021]1188 -001)
Topics
  • Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
  • Physical Sciences › Physics and Astronomy › Condensed Matter Physics › Physics of Superconductivity and Magnetism
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Data Classification
Keywords
superconductors, critical temperature prediction, high-temperature superconductors, stacked ensemble learning, SHAP feature importance, CatBoost, genetic algorithm feature selection, Optuna hyperparameter optimization, tree-structured Parzen estimator, physicochemical properties

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review