Deep learning approach for prediction of critical temperature of superconductor materials described by chemical formulas

Vista sencilla de ítem
dc.contributor.authorViatkin, Dimitri
dc.contributor.authorGarcía-Zapirain, Begoña
dc.contributor.authorMéndez Zorrilla, Amaia
dc.contributor.authorZakharov, Maxim
dc.date.accessioned2025-08-11T08:23:32Z
dc.date.available2025-08-11T08:23:32Z
dc.date.issued2021-10-27
dc.date.updated2025-08-11T08:23:31Z
dc.description.abstractThis paper proposes a novel neural network architecture and its ensembles to predict the critical superconductivity temperature of materials based on their chemical formula. The research describes the methods and processes of extracting data from the chemical formula and preparing these extracted data for use in neural network training using TensorFlow. In our approach, recurrent neural networks are used including long short-term memory layers and neural networks based on one-dimensional convolution layers for data analysis. The proposed model is an ensemble of pre-trained neural network architectures for the prediction of the critical temperature of superconductors based on their chemical formula. The architecture of seven pre-trained neural networks is based on the long short-term memory layers and convolution layers. In the final ensemble, six neural networks are used: one network based on LSTM and four based on convolutional neural networks, and one embedding ensemble of convolution neural networks. LSTM neural network and convolution neural network were trained in 300 epochs. Ensembles of models were trained in 20 epochs. All neural networks are trained in two stages. At both stages, the optimizer Adam was used. In the first stage, training was carried out by the function of losses Mean Absolute Error (MAE) with the value of optimizer learning rate equal to 0.001. In the second stage, the previously trained model was trained by the function of losses Mean Squared Error (MSE) with a learning rate equal to 0.0001. The final ensemble is trained with a learning rate equal to 0.00001. The final ensemble model has the following accuracy values: MAE is 4.068, MSE is 67.272, and the coefficient of determination (R2) is 0.923. The final model can predict the critical temperature for the chemistry formula with an accuracy of 4.068°.en
dc.identifier.citationViatkin, D., Garcia-Zapirain, B., Méndez-Zorrilla, A., & Zakharov, M. (2021). Deep learning approach for prediction of critical temperature of superconductor materials described by chemical formulas. Frontiers in Materials, 8. https://doi.org/10.3389/FMATS.2021.714752
dc.identifier.doi10.3389/FMATS.2021.714752
dc.identifier.eissn2296-8016
dc.identifier.urihttps://hdl.handle.net/20.500.14454/3344
dc.language.isoeng
dc.publisherFrontiers Media S.A.
dc.rights© 2021 Viatkin, Garcia-Zapirain, Méndez-Zorrilla and Zakharov
dc.subject.otherConvolution neural network
dc.subject.otherCritical temperature
dc.subject.otherLSTM neural network
dc.subject.otherNeural networks ensemble
dc.subject.otherSuperconductor
dc.titleDeep learning approach for prediction of critical temperature of superconductor materials described by chemical formulasen
dc.typejournal article
dcterms.accessRightsopen access
oaire.citation.titleFrontiers in Materials
oaire.citation.volume8
oaire.licenseConditionhttps://creativecommons.org/licenses/by/4.0/
oaire.versionVoR
Archivos
Bloque original
Mostrando 1 - 1 de 1
Miniatura
Nombre:
viatkin_deep_2021.pdf
Tamaño:
2.66 MB
Formato:
Adobe Portable Document Format
Descargar
Colecciones
Artículos