{"id":{"repo_id":"mtu","oai_identifier":"oai:digitalcommons.mtu.edu:etdr-2631"},"canonical_url":"https://search.ndltd.org/etd/mtu/oai:digitalcommons.mtu.edu:etdr-2631","repository":{"repo_id":"mtu","name":"Michigan Technological University","base_url":"https://digitalcommons.mtu.edu/do/oai/"},"display":{"title":"Machine Learning-Driven Surrogate Models for Electrolytes","abstract":"We have developed a lattice Monte Carlo (MC) simulation based on the diffusion-limited aggregation model that accounts for the effect of the physical properties of ionic liquids (ILs) on lithium dendrite growth. Our simulations show that the size asymmetry between the cation and anion, the dielectric constant, and the volume fraction of ILs are critical factors to significantly suppress the dendrite growth, primarily due to substantial changes in electric-field screening. Specifically, the volume fraction of ILs has the optimal value for dendrite suppression. The present simulation method indicates potential challenges for the model extension to macroscopic systems. Therefore, we also develop ensemble neural networks (ENNs) in machine learning methods with training datasets derived from the MC simulations by considering the input descriptors with the dielectric constant, the model parameter for the fractal dimension of the dendrite, the volume fraction of ILs, and the applied voltage. Our ENNs can predict the highly nonmonotonic trend of the simulation results from only one-tenth of simulation runs, thus significantly reducing the required computation time. To further examine the efficacy of our new ENN methods in practical applications, we apply ENNs to the study of the dielectric constants of salt-free and salt-doped solvents. Seven common solvents and NaCl solutions with various salt concentrations are considered examples. Despite the significant 50-time reduction in the number of training data, the predictions of the ENNs with batch normalization or bootstrap aggregating are largely consistent with the ground truths, tracing the optimal values out of statistically noisy data. Furthermore, we investigate the phase behaviors of cellulose and ILs mixtures by combining ENNs with unsupervised learning. As a result, K-means clustering and hierarchical clustering can automatically classify solubility phases and determine the boundaries of phases. Our work proves that machine learning could be a promising tool for studying soft matter systems.","abstract_html":"We have developed a lattice Monte Carlo (MC) simulation based on the diffusion-limited aggregation model that accounts for the effect of the physical properties of ionic liquids (ILs) on lithium dendrite growth. Our simulations show that the size asymmetry between the cation and anion, the dielectric constant, and the volume fraction of ILs are critical factors to significantly suppress the dendrite growth, primarily due to substantial changes in electric-field screening. Specifically, the volume fraction of ILs has the optimal value for dendrite suppression. The present simulation method indicates potential challenges for the model extension to macroscopic systems. Therefore, we also develop ensemble neural networks (ENNs) in machine learning methods with training datasets derived from the MC simulations by considering the input descriptors with the dielectric constant, the model parameter for the fractal dimension of the dendrite, the volume fraction of ILs, and the applied voltage. Our ENNs can predict the highly nonmonotonic trend of the simulation results from only one-tenth of simulation runs, thus significantly reducing the required computation time. To further examine the efficacy of our new ENN methods in practical applications, we apply ENNs to the study of the dielectric constants of salt-free and salt-doped solvents. Seven common solvents and NaCl solutions with various salt concentrations are considered examples. Despite the significant 50-time reduction in the number of training data, the predictions of the ENNs with batch normalization or bootstrap aggregating are largely consistent with the ground truths, tracing the optimal values out of statistically noisy data. Furthermore, we investigate the phase behaviors of cellulose and ILs mixtures by combining ENNs with unsupervised learning. As a result, K-means clustering and hierarchical clustering can automatically classify solubility phases and determine the boundaries of phases. Our work proves that machine learning could be a promising tool for studying soft matter systems.","abstract_has_math":false,"creators":["Gao, Tong"],"institution":null,"degree_name":"Doctor of Philosophy in Applied Physics (PhD)","degree_level":"Open Access Dissertation","degree_discipline":"Department of Physics","degree_department":null,"school":null,"contributors":["Issei Nakamura"],"advisors":[],"committee_chairs":[],"committee_members":["Ranjit Pati","Will Cantrell","Susanta Ghosh"],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T08:18:46Z","subjects":["simulations","machine learning","electrolytes dielectric constants","Li-ion batteries","dendrites","ionic liquids","Statistical, Nonlinear, and Soft Matter Physics"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.mtu.edu/etdr/1472"],"render_values":[{"text":"https://digitalcommons.mtu.edu/etdr/1472","href":"https://digitalcommons.mtu.edu/etdr/1472","code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://doi.org/10.37099/mtu.dc.etdr/1472","outbound_label":"DOI","outbound_source":"dc:identifier","record_url":"https://doi.org/10.37099/mtu.dc.etdr/1472","record_label":"Repository record","record_kind":"doi","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://digitalcommons.mtu.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.mtu.edu%3Aetdr-2631","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Issei Nakamura"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Ranjit Pati","Will Cantrell","Susanta Ghosh"]},{"key":"dc:creator","label":"Author","values":["Gao, Tong"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.created","label":"Dc Date Created","values":["2022-01-01T08:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Department of Physics"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Open Access Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctor of Philosophy in Applied Physics (PhD)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["simulations","machine learning","electrolytes dielectric constants","Li-ion batteries","dendrites","ionic liquids","Statistical, Nonlinear, and Soft Matter Physics"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["10.37099/mtu.dc.etdr/1472","https://digitalcommons.mtu.edu/etdr/1472"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["We have developed a lattice Monte Carlo (MC) simulation based on the diffusion-limited aggregation model that accounts for the effect of the physical properties of ionic liquids (ILs) on lithium dendrite growth. Our simulations show that the size asymmetry between the cation and anion, the dielectric constant, and the volume fraction of ILs are critical factors to significantly suppress the dendrite growth, primarily due to substantial changes in electric-field screening. Specifically, the volume fraction of ILs has the optimal value for dendrite suppression. The present simulation method indicates potential challenges for the model extension to macroscopic systems. Therefore, we also develop ensemble neural networks (ENNs) in machine learning methods with training datasets derived from the MC simulations by considering the input descriptors with the dielectric constant, the model parameter for the fractal dimension of the dendrite, the volume fraction of ILs, and the applied voltage. Our ENNs can predict the highly nonmonotonic trend of the simulation results from only one-tenth of simulation runs, thus significantly reducing the required computation time. To further examine the efficacy of our new ENN methods in practical applications, we apply ENNs to the study of the dielectric constants of salt-free and salt-doped solvents. Seven common solvents and NaCl solutions with various salt concentrations are considered examples. Despite the significant 50-time reduction in the number of training data, the predictions of the ENNs with batch normalization or bootstrap aggregating are largely consistent with the ground truths, tracing the optimal values out of statistically noisy data. Furthermore, we investigate the phase behaviors of cellulose and ILs mixtures by combining ENNs with unsupervised learning. As a result, K-means clustering and hierarchical clustering can automatically classify solubility phases and determine the boundaries of phases. Our work proves that machine learning could be a promising tool for studying soft matter systems."]},{"key":"dc:title","label":"Title","values":["Machine Learning-Driven Surrogate Models for Electrolytes"]}]}],"canonical_facts":{"dc:contributor":["Issei Nakamura"],"dc:contributor.committeemember":["Ranjit Pati","Will Cantrell","Susanta Ghosh"],"dc:creator":["Gao, Tong"],"dc:date.created":["2022-01-01T08:00:00Z"],"dc:description.abstract":["We have developed a lattice Monte Carlo (MC) simulation based on the diffusion-limited aggregation model that accounts for the effect of the physical properties of ionic liquids (ILs) on lithium dendrite growth. Our simulations show that the size asymmetry between the cation and anion, the dielectric constant, and the volume fraction of ILs are critical factors to significantly suppress the dendrite growth, primarily due to substantial changes in electric-field screening. Specifically, the volume fraction of ILs has the optimal value for dendrite suppression. The present simulation method indicates potential challenges for the model extension to macroscopic systems. Therefore, we also develop ensemble neural networks (ENNs) in machine learning methods with training datasets derived from the MC simulations by considering the input descriptors with the dielectric constant, the model parameter for the fractal dimension of the dendrite, the volume fraction of ILs, and the applied voltage. Our ENNs can predict the highly nonmonotonic trend of the simulation results from only one-tenth of simulation runs, thus significantly reducing the required computation time. To further examine the efficacy of our new ENN methods in practical applications, we apply ENNs to the study of the dielectric constants of salt-free and salt-doped solvents. Seven common solvents and NaCl solutions with various salt concentrations are considered examples. Despite the significant 50-time reduction in the number of training data, the predictions of the ENNs with batch normalization or bootstrap aggregating are largely consistent with the ground truths, tracing the optimal values out of statistically noisy data. Furthermore, we investigate the phase behaviors of cellulose and ILs mixtures by combining ENNs with unsupervised learning. As a result, K-means clustering and hierarchical clustering can automatically classify solubility phases and determine the boundaries of phases. Our work proves that machine learning could be a promising tool for studying soft matter systems."],"dc:identifier":["10.37099/mtu.dc.etdr/1472","https://digitalcommons.mtu.edu/etdr/1472"],"dc:subject":["simulations","machine learning","electrolytes dielectric constants","Li-ion batteries","dendrites","ionic liquids","Statistical, Nonlinear, and Soft Matter Physics"],"dc:title":["Machine Learning-Driven Surrogate Models for Electrolytes"],"thesis:degree_discipline":["Department of Physics"],"thesis:degree_level":["Open Access Dissertation"],"thesis:degree_name":["Doctor of Philosophy in Applied Physics (PhD)"]},"updated_at":"2026-11-19T08:18:46Z"}