Machine learning of cytoskeletal machines

Traditional bottom-up physical-mathematical models have longstanding popularity and success in studying cytoskeleton and mechanochemical machines driving cell movements and division. These models brought and will continue to bring mechanistic insights into cell migration. However, such models are either too simple to embrace the complexity of the multiscale cell processes or are hopelessly cumbersome and unwieldy to be used to nimbly test multiple hypotheses. Machine learning and AI approaches have demonstrated immense strength in identifying statistical patterns in cytoskeletal machines and in predicting cytoskeletal dynamics from microscopy data. However, these data-driven approaches largely neglect the laws of physics and chemistry needed to ground the discoveries in biological mechanisms. These complementary strengths and weaknesses between the traditional modeling and modern data-scientific approaches suggest a promising avenue forward: augmenting traditional models with data-scientific and AI methods for the sake of building more complex traditional models that can be directly connected with the enormous volumes of biological data of cytoskeletal machines.

This workshop will convene data scientists, experimental biologists, mathematical modelers and biophysicists using or interested in starting to use ML to study cytoskeletal dynamics, cell migration and mitosis. The goal is to foster an exchange of ideas between these research communities. The workshop is structured to help participants identify the most promising opportunities for developing and using ML tools to answer biological questions. The program includes both overview and research talks, poster sessions and lightning talks by poster presenters, and will have ample time for participants to get to know each other, exchange ideas and foster collaborations.

Related Info

Register Now

Machine learning of cytoskeletal machines

Traditional bottom-up physical-mathematical models have longstanding popularity and success in studying cytoskeleton and mechanochemical machines driving cell movements and division. These models brought and will continue to bring mechanistic insights into cell migration. However, such models are either too simple to embrace the complexity of the multiscale cell processes or are hopelessly cumbersome and unwieldy to be used to nimbly test multiple hypotheses. Machine learning and AI approaches have demonstrated immense strength in identifying statistical patterns in cytoskeletal machines and in predicting cytoskeletal dynamics from microscopy data. However, these data-driven approaches largely neglect the laws of physics and chemistry needed to ground the discoveries in biological mechanisms. These complementary strengths and weaknesses between the traditional modeling and modern data-scientific approaches suggest a promising avenue forward: augmenting traditional models with data-scientific and AI methods for the sake of building more complex traditional models that can be directly connected with the enormous volumes of biological data of cytoskeletal machines.

This workshop will convene data scientists, experimental biologists, mathematical modelers and biophysicists using or interested in starting to use ML to study cytoskeletal dynamics, cell migration and mitosis. The goal is to foster an exchange of ideas between these research communities. The workshop is structured to help participants identify the most promising opportunities for developing and using ML tools to answer biological questions. The program includes both overview and research talks, poster sessions and lightning talks by poster presenters, and will have ample time for participants to get to know each other, exchange ideas and foster collaborations.

Related Info

Register Now

Machine learning of cytoskeletal machines

Traditional bottom-up physical-mathematical models have longstanding popularity and success in studying cytoskeleton and mechanochemical machines driving cell movements and division. These models brought and will continue to bring mechanistic insights into cell migration. However, such models are either too simple to embrace the complexity of the multiscale cell processes or are hopelessly cumbersome and unwieldy to be used to nimbly test multiple hypotheses. Machine learning and AI approaches have demonstrated immense strength in identifying statistical patterns in cytoskeletal machines and in predicting cytoskeletal dynamics from microscopy data. However, these data-driven approaches largely neglect the laws of physics and chemistry needed to ground the discoveries in biological mechanisms. These complementary strengths and weaknesses between the traditional modeling and modern data-scientific approaches suggest a promising avenue forward: augmenting traditional models with data-scientific and AI methods for the sake of building more complex traditional models that can be directly connected with the enormous volumes of biological data of cytoskeletal machines.

This workshop will convene data scientists, experimental biologists, mathematical modelers and biophysicists using or interested in starting to use ML to study cytoskeletal dynamics, cell migration and mitosis. The goal is to foster an exchange of ideas between these research communities. The workshop is structured to help participants identify the most promising opportunities for developing and using ML tools to answer biological questions. The program includes both overview and research talks, poster sessions and lightning talks by poster presenters, and will have ample time for participants to get to know each other, exchange ideas and foster collaborations.

Related Info

Register Now

The ceremony will take place on Saturday, December 13 in Pick-Staiger Concert Hall, 50 Arts Circle Drive.

The Reverse Side of Online Shopping: Examining Sociodemographic and Built-Environment Determinants of Delivery Returns

The rapid growth of e-commerce has created new transportation challenges through increased product returns, yet the behavioral determinants of delivery return patterns remain understudied from a consumer-centric perspective. This research develops a comprehensive econometric framework to analyze online shopping frequency, delivery return rates, and return channel preferences using data from the 2022 National Household Travel Survey (NHTS). We employ a multivariate modeling approach integrating probit ordered-response and probit fractional response models to examine three interconnected outcomes: (1) frequency of online goods purchases, (2) proportion of online purchases returned, and (3) distribution of returns across four channels (home pickup, post office, Amazon drop-off, and physical store). The results reveal significant sociodemographic heterogeneity in online purchasing and return behavior. Built environment factors also significantly influence return behaviors. The findings have important implications for transportation planning and urban logistics, highlighting the need for policies that ensure equitable return access and the importance of integrating e-commerce return trips into travel demand models.

Keywords: E-commerce returns, online shopping behavior, transportation planning, reverse logistics, consumer behavior.

Bio

Dr. Chandra R. Bhat is the Joe J. King Chair in Engineering at The University of Texas at Austin, where he teaches courses in transportation systems analysis and transportation planning. He is also the Director of the USDOT-funded National Center for Understanding Future Travel Behavior and Demand. He also served as the Director of the Data-Supported Transportation Operations and Planning (D-STOP) Tier 1 USDOT University Transportation Center, the Associate Chairman of the Department of Civil, Architectural and Environmental Engineering, and the Director of the Center for Transportation Research.

Dr. Bhat is recognized nationally and internationally as a leading expert in the area of travel demand modeling and travel behavior analysis. His substantive research interests include land-use and travel demand modeling, activity-based travel modeling, policy evaluation of the effect of transportation control and congestion pricing measures on traffic congestion and mobile-source emissions, marketing research of competitive positioning strategies for transportation services, use of non-motorized modes of travel, and physical health and transportation. His methodological research interests and expertise are in the areas of econometric and mathematical modeling of consumer behavior, including discrete choice analysis, discrete-continuous econometric systems, and hazard duration models. His methodological works are widely referenced in the economics, marketing, geography, statistics, and transportation fields, and have been included in econometric textbooks and software packages. Many of these works, published as refereed journal papers, have been listed in journals as highly cited papers, and two of his papers were included in a book compilation of the 46 most influential and innovative scholarly papers in the choice modeling field in the past 60 years (the book title is Choice Modelling: Foundational Contributions, 2011, Edward Elgar Publishing Ltd). He also has authored several book chapters focusing on improved methods for choice modeling in general and land use-travel demand modeling in particular. The number of times his work has been cited, as per the Thomson Reuters Web of Science database, is over the 19,800 mark with an h-index of 72. This citation index places him among the top of transportation professors in citations. The number of his citations in the Google Scholar database is over 44,690, with an h-index of 109. Dr. Bhat's research has been funded by the National Science Foundation, the Environmental Protection Agency, the National Institute of Statistical Sciences, State Departments of Transportation, including TxDOT, the Bureau of Transportation Statistics, and the U.S. Department of Transportation.

Dr. Bhat received the 2004 Walter L. Huber Award and the 2005 James Laurie Prize from the American Society of Civil Engineers (ASCE) in recognition of his contributions to "innovative methods in transportation systems analysis and modeling." He also received the 2006 Lockheed Martin Aeronautics Company Award for Excellence in Engineering Teaching, awarded by the College of Engineering at UT Austin, and the 2006-2007 Outstanding Graduate Teaching Award, awarded by the UT Graduate School. Dr. Bhat won the 2007 Pyke Johnson Award from the Transportation Research Board (TRB) for the best paper in the area of planning and environment, for a paper he co-authored with two former PhD students. He was selected as the 2008 recipient of the Wilbur S. Smith Distinguished Transportation Educator Award by the Institute of Transportation Engineers (ITE). He also is a 2008 Jefferson Science Fellow Selectee and was conferred the 2008 Outstanding Faculty Advisor Award by the Texas Institute of Transportation Engineers. He was awarded the 2009 S.S. Steinberg Award by the American Road & Transportation Builders Association (ARTBA), the 2010 Most Outstanding Faculty Award for Civil Engineering by the Student Engineering Council in the Cockrell School of Engineering, and selected as one of seven new 2010 members of the Academy of Distinguished Teachers at UT Austin. In 2013, he receive the 2013-14 Billy and Claude R. Hocott Distinguished Centennial Engineering Research Award by the Cockrell School of Engineering, a Humboldt Research Award from the Alexander von Humboldt Foundation, the 2013 Pyke Johnson Awardfrom the Transportation Research Board (TRB) for the best paper in the area of planning and environment, and was featured as a transportation leader in the PROFILES section of the November-December 2013 issue of Transportation News, the bimonthly magazine of the Transportation Research Board of the National Academies. In 2014, he was named as a distinguished scientist and visiting professor as part of the Highly Cited (HiCi) Researcher Program of King Abdulaziz University in Saudi Arabia. At the University level, Dr. Bhat was named as a 2013-2014 Longhorn Game Changer and featured in promotional videos at UT athletic venues and in the social media. In 2015, he was selected to receive the 2015 Hind Rattan Award from the Government of India, and the 2015 Frank M. Masters Transportation Engineering Award from ASCE "for his pioneering contributions to transportation systems analysis, his international leadership in bridging the gap between the research and practice of transportation planning, and his dedicated efforts to produce a new generation of high quality transportation professionals." In 2016, he was named as a Distinguished Alumnus of the Indian Institute of Technology, Madras in recognition of his seminal contributions to the field of transportation and urban policy, and was listed on the Eno Center for Transportation's Top 10 Transportation Thought Leaders in Academia. The list, put together by Eno and the Council of University Transportation Centers (CUTC), features academics who "work in multi-modal disciplines that vary greatly from computer science, information systems, and engineering to public policy, planning, business and design. In addition to grooming the next transportation workforce, this esteemed group leverages their resources and expertise to help solve real world transportation challenges through ongoing research and thought-leadership." In 2017, he was awarded the Lifetime Achievement in Transportation Research and Education Award (Academic) from the Council of University Transportation Centers (CUTC). This award is to "identify individuals who have had a long history of significant and outstanding contribution to university transportation education and research resulting in a lasting contribution to transportation." His paper with students entitled "Transportation Planning to Accommodate Needs of Wind Energy Projects" received the 2017 Transportation Research Board (TRB) Travel Analysis Methods Section Ryuichi Kitamura Paper Award. This award is for the best paper, authored by a student(s)-mentor combination, submitted to the Travel Analysis Methods Section (ADB00) of TRB, which gets over 500 papers each year. He also received the 2022 Theodore M. Matson Memorial Award from the Institute of Transportation Engineers (ITE) for "...a long and distinguished academic career focused on resolving the critical issues facing the transportation industry." Chandra in 2022 is ranked as one of the top three scientists globally in the subject area of transport and logistics. Along with colleagues and students, he is the recipient of the 2022 Pyke Johnson Award from the Transportation Research Board for the best paper in the area of planning and environment (the paper is entitled "The Influence of Mode Use on Level of Satisfaction with Daily Travel Routine: A Focus on Automobile Driving in the United States"). Recently, he received the 2024 W.N. Carey, Jr. Distinguished Service Award from the Transportation Research Board (TRB) and the 2024 Joe King Professional Service Award from the University of Texas�s Cockrell Engineering School.

Dr. Bhat has also made significant educational and scientific impacts on the transportation planning field by nurturing and producing a new generation of very high quality researchers. The results of his pedagogical efforts are evident in the quality of his graduate students. In each of the years 2000, 2001, 2013, 2018, and 2025, one of his MS students was awarded the prestigious Milton Pikarsky Memorial Award for the best North America thesis in the transportation science and technology area, and in 2013, one of his PhD students won the Milton Pikarsky Memorial Award for the best North American dissertation in the transportation science and technology area. In 2004, and again in 2008, one of his PhD students received the Charley V. Wootan Memorial Award for the best North American dissertation in the transportation policy and planning area, and in 2009, 2011, 2013, and again in 2024, one of his MS students won the Charley V. Wootan Memorial Award for the best North American thesis in the transportation policy and planning area. In 2009 and 2012, a PhD student received an honorable mention in the international Eric Pas Prize Competition for one of the top two dissertations in the travel behavior field. His students have been selected for the Eno Leadership Program, the International Road Federation (IRF) Leadership Program, the Eisenhower Graduate Fellowship, the Wanda Schafer Scholarship of the Women's Transportation Society, and the Herman Award, among other awards. Overall, since 2000, his students have received over 45 external (non-UT) awards for their scholarly research and leadership contributions.

Dr. Bhat has been invited and/or elected to serve on several international and national transportation committees, including the International Association for Travel Behavior Research and eleven Transportation Research Board (TRB) committees/task forces. He served as the President of the International Association for Travel Behavior Research, and was a member of the Board of Directors of this association. He is a current member of the TRB Committee on Statistical Methods (AED60), and served as the Co-Chair of the TRB Transportation Planning and Analysis Section (AEP00), Chair of the TRB Travel Analysis Methods Section (ADB00), Co-Chair of the TRB Committee on Transportation Education and Training (ABG20), and Chair of the Committee on Transportation Demand Forecasting (ADB40). He is also the Editor-in-Chief of Transportation Research-Part B, an Associate Editor of Analytic Methods in Accident Research, Transportation Research Record: Journal of the Transportation Research Board (TRR), and Transportation Research Interdisciplinary Perspectives (TRIP), a consulting editor of Travel Behaviour and Society, and serves on the editorial boards of the Journal of Choice Modelling, Transportation Letters: The International Journal of Transportation Research, EURO Journal on Transport and Logistics, and Transportation in Developing Economies, A Journal of the Transportation Research Group of India (TRG). Dr. Bhat is on the Board of Directors of the Research and Education Division of the American Road and Transportation Builders Association (ARTBA) and was a member of the Executive Committee of the Council of University Transportation Centers (CUTC).

Dr. Bhat has been a consultant for activity-based travel modeling for MPOs, has conducted research for the Boston MPO in the past on improvements to travel demand modeling, and is currently working with the North Central Texas Council of Governments (NCTCOG) on an ongoing activity-based travel modeling project. He has worked with Parsons Brinckerhoff and Cambridge Systematics as a consultant for developing and implementing integrated land-use, transportation, and air quality models. He was on a National Academy of Sciences (NAS) Panel to review the travel demand modeling procedures of the Metropolitan Washington Council of Governments (MWCOG) in Washington D.C. He has served as a Peer Review Panelist for several MPOS, including those in the San Francisco, San Diego, Seattle, Los Angeles, New Jersey, Calgary, and St. Louis areas. Locally, he was the technical advisor to a Blue Ribbon Task Force constituted by the Greater Austin Chamber of Commerce to review and assess Capital Metro's light rail proposal for Austin.

Evolutionary game theory (EGT) offers a powerful modeling framework for analyzing frequency-dependent interactions in biological, social, and artificial systems. Originally adapted from economic models and applied to animal behavior, EGT has become a foundational tool for studying phenomena ranging from microbial competition and tumor progression to cultural dynamics and cooperative AI. The field's mathematical foundations have expanded over the years, incorporating tools from dynamical systems, probability theory, partial differential equations, and network science. This diverse modeling toolkit has enabled researchers to examine how social behaviors evolve in structured populations, how empirical data can inform game parameters, and how environmental feedbacks shape evolutionary dynamics.

This workshop will bring together an interdisciplinary community of EGT researchers to chart new directions for theory and applications. Through presentations and discussions, participants will identify mismatches between current models and observed systems, explore strategies for integrating empirical data into theoretical work, and formulate open problems that resonate across applied mathematics, biology, physics, and computer science. A primary aim of the workshop is to stimulate interdisciplinary collaboration and expand the methodological scope of EGT to frequency-dependent problems across scales.

Related Info

Register Now

Evolutionary game theory (EGT) offers a powerful modeling framework for analyzing frequency-dependent interactions in biological, social, and artificial systems. Originally adapted from economic models and applied to animal behavior, EGT has become a foundational tool for studying phenomena ranging from microbial competition and tumor progression to cultural dynamics and cooperative AI. The field's mathematical foundations have expanded over the years, incorporating tools from dynamical systems, probability theory, partial differential equations, and network science. This diverse modeling toolkit has enabled researchers to examine how social behaviors evolve in structured populations, how empirical data can inform game parameters, and how environmental feedbacks shape evolutionary dynamics.

This workshop will bring together an interdisciplinary community of EGT researchers to chart new directions for theory and applications. Through presentations and discussions, participants will identify mismatches between current models and observed systems, explore strategies for integrating empirical data into theoretical work, and formulate open problems that resonate across applied mathematics, biology, physics, and computer science. A primary aim of the workshop is to stimulate interdisciplinary collaboration and expand the methodological scope of EGT to frequency-dependent problems across scales.

Related Info

Register Now

Evolutionary game theory (EGT) offers a powerful modeling framework for analyzing frequency-dependent interactions in biological, social, and artificial systems. Originally adapted from economic models and applied to animal behavior, EGT has become a foundational tool for studying phenomena ranging from microbial competition and tumor progression to cultural dynamics and cooperative AI. The field's mathematical foundations have expanded over the years, incorporating tools from dynamical systems, probability theory, partial differential equations, and network science. This diverse modeling toolkit has enabled researchers to examine how social behaviors evolve in structured populations, how empirical data can inform game parameters, and how environmental feedbacks shape evolutionary dynamics.

This workshop will bring together an interdisciplinary community of EGT researchers to chart new directions for theory and applications. Through presentations and discussions, participants will identify mismatches between current models and observed systems, explore strategies for integrating empirical data into theoretical work, and formulate open problems that resonate across applied mathematics, biology, physics, and computer science. A primary aim of the workshop is to stimulate interdisciplinary collaboration and expand the methodological scope of EGT to frequency-dependent problems across scales.

Related Info

Register Now

Evolutionary game theory (EGT) offers a powerful modeling framework for analyzing frequency-dependent interactions in biological, social, and artificial systems. Originally adapted from economic models and applied to animal behavior, EGT has become a foundational tool for studying phenomena ranging from microbial competition and tumor progression to cultural dynamics and cooperative AI. The field's mathematical foundations have expanded over the years, incorporating tools from dynamical systems, probability theory, partial differential equations, and network science. This diverse modeling toolkit has enabled researchers to examine how social behaviors evolve in structured populations, how empirical data can inform game parameters, and how environmental feedbacks shape evolutionary dynamics.

This workshop will bring together an interdisciplinary community of EGT researchers to chart new directions for theory and applications. Through presentations and discussions, participants will identify mismatches between current models and observed systems, explore strategies for integrating empirical data into theoretical work, and formulate open problems that resonate across applied mathematics, biology, physics, and computer science. A primary aim of the workshop is to stimulate interdisciplinary collaboration and expand the methodological scope of EGT to frequency-dependent problems across scales.

Related Info

Register Now