{"688991":{"#nid":"688991","#data":{"type":"event","title":"PhD Defense by Yongsheng Chen","body":[{"value":"\u003Cp\u003E\u003Cstrong\u003ESchool of Civil and Environmental Engineering\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EPh.D. Thesis Defense Announcement\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EMACHINE LEARNING AIDED INVERSE DESIGN FOR POLYMERIC MEMBRANES: CASE STUDIES IN NANOFILTRATION AND GAS SEPARATION\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EBy Raghav Dangayach\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EAdvisor:\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EDr. Yongsheng Chen\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ECommittee Members:\u003C\/strong\u003E\u0026nbsp;Dr. Xing Xie (CEE), Dr. Ameet Pinto (CEE), Dr. Shane Snyder (CEE), Dr. Sankar Nair (ChBE)\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ED\u003Cstrong\u003Eate and Time:\u003C\/strong\u003E\u0026nbsp;April 02, 2026. 9 AM EST\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ELocation\u003C\/strong\u003E: Price Gilbert Memorial Library 4222 (Dissertation Defense Room)\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EOnline Link:\u0026nbsp;\u003C\/strong\u003E\u003Ca href=\u0022https:\/\/gatech.zoom.us\/j\/7448923349\u0022\u003Ehttps:\/\/gatech.zoom.us\/j\/7448923349\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EABSTRACT\u003Cbr\u003EPolymeric membranes have been widely used for liquid and gas separation in various\u003Cbr\u003Eindustrial applications over the past few decades because of their exceptional versatility\u003Cbr\u003Eand high tunability. Traditional trial-and-error methods for material synthesis are\u003Cbr\u003Einadequate to meet the growing demands for high-performance membranes. In that context, Machine learning (ML) has demonstrated huge potential to accelerate the\u003Cbr\u003Edesign and discovery of polymeric membranes.\u003Cbr\u003EML models are highly complex and behave as \u201cblack boxes\u201d, making it hard for\u003Cbr\u003Eresearchers to interpret the predictions made by them. Using Explainable Artificial\u003Cbr\u003EIntelligence tools such as Shapley additive explanations and Partial Dependence Plots\u003Cbr\u003Ecan help in visualizing the impact of features on ML models, giving insight into their\u003Cbr\u003Edecision-making behavior. These tools were used to develop synthesis-propertyperformance\u003Cbr\u003Erelationships to understand principles guiding the separation process of\u003Cbr\u003ELithium and Magnesium using polyamide-nanofiltration (NF) membranes. The goal is\u003Cbr\u003Eto ensure that the predictions made by ML models are consistent with domain\u003Cbr\u003Eknowledge.\u003Cbr\u003EUsing insights obtained from SHAP analysis, a novel, strategic framework was\u003Cbr\u003Eproposed for rational screening of monomers and polymers for NF and gas separation\u003Cbr\u003Eapplications. A metric called \u0022SHAP-score\u0022 was devised, which quantifies the impact\u003Cbr\u003Ethat a feature (in this case, a property of a polymer) has on an ML model. This\u003Cbr\u003Equantification is a product of the features\u0027 importance and their correlation to the\u003Cbr\u003Eperformance metric of choice, i.e., permeability or selectivity. The properties of\u003Cbr\u003Epotential materials are scaled on basis of this impact, allowing us to score materials and\u003Cbr\u003Efind potential candidates for membrane testing. This method is an attempt towards the\u003Cbr\u003Edevelopment of a general-purpose methodology for polymeric material discovery that\u003Cbr\u003Ehas huge applications not only limited to membrane science, but also various other\u003Cbr\u003Esubfields.\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EMACHINE LEARNING AIDED INVERSE DESIGN FOR POLYMERIC MEMBRANES: CASE STUDIES IN NANOFILTRATION AND GAS SEPARATION\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"MACHINE LEARNING AIDED INVERSE DESIGN FOR POLYMERIC MEMBRANES: CASE STUDIES IN NANOFILTRATION AND GAS SEPARATION"}],"uid":"27707","created_gmt":"2026-03-17 18:32:34","changed_gmt":"2026-03-17 18:34:15","author":"Tatianna Richardson","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2026-04-02T09:00:00-04:00","event_time_end":"2026-04-02T11:00:00-04:00","event_time_end_last":"2026-04-02T11:00:00-04:00","gmt_time_start":"2026-04-02 13:00:00","gmt_time_end":"2026-04-02 15:00:00","gmt_time_end_last":"2026-04-02 15:00:00","rrule":null,"timezone":"America\/New_York"},"location":"Price Gilbert Memorial Library 4222 (Dissertation Defense Room)","extras":[],"groups":[{"id":"221981","name":"Graduate Studies"}],"categories":[],"keywords":[{"id":"100811","name":"Phd Defense"}],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1788","name":"Other\/Miscellaneous"}],"invited_audience":[{"id":"78771","name":"Public"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[],"email":[],"slides":[],"orientation":[],"userdata":""}}}