All Posts By

sreelaks

MIDAS announces 2023 Propelling Original Data Science (PODS) Grant awardees

By | News

MICHIGAN INSTITUTE FOR DATA SCIENCE announces 2023 Propelling Original Data Science (PODS) Grant awardees

The Michigan Institute for Data Science (MIDAS) announced the awardees of the 2023 round of Propelling Original Data Science (PODS) Grants. Nine teams will receive funding support for a wide range of exciting projects with data science and Artificial Intelligence (AI) as the common thread, including topics such as multimodal learning for disease prediction, using video data to study political discourse, text analysis to detect and reduce bias in graduate admissions, and explainable AI for building trust in AI-aided decisions. The awarded projects are: 

From ground to air, and the traveler experiences in-between: Human-centered data-driven performance measures for multimodal transportation systems

Atiyya Shaw (Civil and Environmental Engineering) and Max Li (Aerospace Engineering and Industrial and Operations Engineering)

A Data Science Toolkit for Examining Local Governance

Justine Zhang (School of Information) and Yanna Krupnikov (Communications & Media)

Bayesian modeling of multi-source phenology to forecast airborne allergen concentration

Kai Zhu (School for Environment and Sustainability) and Kerby Shedden (Statistics)

Interpretable machine learning to identify tumor spatial features from longitudinal multi-modality images for personalized progression risk prediction of poor prognosis head and neck cancer

Lise Wei (Radiation Oncology) and Liyue Shen (Computer Science and Engineering)

MI-SPACE: Multiplex Imaging based Spatial Analysis for Discovery of Cellular Interactions in the Tumor Microenvironment

Maria Masotti (Biostatistics)

Detecting and Countering Untrustworthy Artificial Intelligence (AI) through AI Literacy

Nikola Banovic (Computer Science and Engineering)

Foundations of Sequence Models for Learning, Estimation, and Control of Dynamical Systems

Samet Oymak (Electrical and Computer Engineering) and Necmiye Ozay (Electrical Engineering and Computer Science & Robotics)

Neural Quantum States at Scale: Applications in Sciences and Engineering

Shravan Veerapaneni and James Stokes (Mathematics)

Machine-Processing of Graduate Student Applications for Diversity, Equity, and Inclusion

Wenhao Sun (Materials Science and Engineering) and Dallas Card (School of Information)

Since 2016, MIDAS has been offering funding to U-M faculty to enable groundbreaking disciplinary and interdisciplinary research through data science and AI, making it possible for research teams to form many new collaborations, formulate groundbreaking ideas, and secure external funding to expand their work. As of 2022, a total of $12M MIDAS funding has jump-started 63 research projects, which expanded into 112 follow-on projects with $114M of external funding. In addition, “year after year, the applicants propose to employ increasingly more sophisticated data science and AI methods to address increasingly more profound research questions,” says Dr. H. V. Jagadish, Director of MIDAS. “This reflects the rapid advancement of data science and AI and their transformation of science and society, and U-M researchers are at the forefront of it.”

The 2023 PODS teams will present their projects at the U-M Annual Data Science and AI Summit to be held November 13-14, 2023. Read more about their projects:

Atiyya Shaw (Civil and Environmental Engineering) and Max Li (Aerospace Engineering and Industrial and Operations Engineering)

From ground to air, and the traveler experiences in-between: Human-centered data-driven performance measures for multimodal transportation systems

Both ground and air transportation systems have traditionally been assessed using system-based metrics that discount human experiences. While there is growing consensus that the management of these systems should integrate human-centered performance metrics, the primary sources of data to obtain these metrics are difficult to obtain, and the challenges are only increasing. This project aims to examine the potential of applying AI-based approaches to integrate passively collected travel data with rich behavioral insights from smaller scale passenger survey datasets, with the goal of linking across transportation modes and advancing multimodal transportation networks to be more equitable, accessible, and efficient.

Justine Zhang (School of Information) and Yanna Krupnikov (Communications & Media)

A Data Science Toolkit for Examining Local Governance

We will collect a novel, large-scale dataset containing transcripts of city council meetings in Michigan. On top of this data, we will combine domain expertise and machine learning pipelines to generate a rich set of annotations that capture key political qualities of the meeting discourse. This dataset will lay the groundwork for new empirical research on local governance, political division, discourse and civic participation.

Kai Zhu (School for Environment and Sustainability) and Kerby Shedden (Statistics)

Bayesian modeling of multi-source phenology to forecast airborne allergen concentration
We aim to improve the short-term and long-term predictions of airborne allergens under climate change, an emerging public health concern. To achieve this, we propose to develop novel data science tools to effectively assimilate multiple data sources and integrate various data-driven and process-based models. Beyond innovative methodology, our project also advances the biological understanding of pollen and fungal spores, and ultimately, our work helps alleviate the impacts of airborne allergens on people’s health.

Lise Wei (Radiation Oncology) and Liyue Shen (Computer Science and Engineering)

Interpretable machine learning to identify tumor spatial features from longitudinal multi-modality images for personalized progression risk prediction of poor prognosis head and neck cancer
Our research project focuses on the development of an interpretable machine learning model designed to efficiently integrate multimodal data, including images and biological information. Our model also identifies crucial tumor changes over time, enabling personalized progression risk prediction for patients with poor prognosis head and neck cancer. This innovative approach aims to enhance the efficacy and precision of radiation therapy for high-risk patients, ultimately resulting in improved treatment outcomes and quality of life.

Maria Masotti (Biostatistics) 

MI-SPACE: Multiplex Imaging based Spatial Analysis for Discovery of Cellular Interactions in the Tumor Microenvironment
The tumor microenvironment is emerging as the next frontier in cancer research, where scientists are working to understand how the spatial interplay of multiple cell types surrounding the tumor affects immune response, tumor development, response to treatment, and more. Existing methods to quantify cellular interactions in the tumor microenvironment do not scale to the rapidly evolving technical landscape where researchers are now able to map over fifty cellular markers at the single cell resolution with thousands of cells per image. We will develop a statistically-oriented, scalable framework and software toolkit to help researchers discover novel associations between cellular cross-talk in the tumor microenvironment and patient-level outcomes such as response to treatment or survival.

Nikola Banovic (Computer Science and Engineering)

Detecting and Countering Untrustworthy Artificial Intelligence (AI) through AI Literacy

Distinguishing trustworthy from untrustworthy Artificial Intelligence (AI) is of critical importance to broader societal adoption of AI, as AI gets deployed into high-stakes decision-making scenarios. However, end-users who are not computer-science savvy and who lack AI literacy fail to detect untrustworthy AI, despite existing approaches that attempt to promote AI trustworthiness by explaining and justifying AI decisions. Here, we propose to design and evaluate novel explanation mechanisms to help such end-users develop AI literacy they require to detect and counter untrustworthy AI, and in turn reduce their undue reliance on such AI.

Samet Oymak (Electrical and Computer Engineering) and Necmiye Ozay (Electrical Engineering and Computer Science & Robotics)

Foundations of Sequence Models for Learning, Estimation, and Control of Dynamical Systems

Powerful sequence models such as transformers have revolutionized natural language processing however their use in dynamic decision making remains unproven and unsafe. This project will unlock the potential of sequence models in data-driven control and enable their safe and robust use through innovative theory and algorithms.

Shravan Veerapaneni and James Stokes (Mathematics)

Neural Quantum States at Scale: Applications in Sciences and Engineering

Neural networks have achieved unparalleled performance on a diversity of tasks ranging from image processing to natural language generation. This project will leverage these successes to unravel the mysteries of quantum many-body physics. The project hinges on the idea that the quantum many-body problem can be posed as a machine learning problem for a quantum many-body wave function. By drawing upon state-of-art machine learning techniques, this project will make possible the application of neural-network techniques to quantum many-body problems of unprecedented scale, thereby unlocking a spectrum of applications in physics, chemistry and materials science.

Wenhao Sun (Materials Science and Engineering) and Dallas Card (School of Information)

Machine-Processing of Graduate Student Applications for Diversity, Equity, and Inclusion
Every year the UM College of Engineering receives tens of thousands of graduate applications, which faculty reviewers initially down-select using numerical indicators of merit such as GPA, test scores, and undergraduate school prestige. Unless an applicant meets a predefined numerical threshold, richer portions of an application—such as letters of recommendation and statement of purposes—may remain overlooked. This project aims to use Natural Language Processing methods to process graduate student applications and identify ‘hidden gem’ applicants, who are exceptional students from underrepresented or less-privileged backgrounds but have a strong propensity for PhD research.

Announcing the 2023 cohort of postdoctoral fellows

By | News

Michigan Institute for Data Science announces 2023 fellows

Written by Jennifer Lewis

The Michigan Institute for Data Science (MIDAS) announces two new cohorts of postdoctoral fellows. Eleven new fellows will join the Eric and Wendy Schmidt AI in Science Fellowship program in the fall and two new fellows will join the Michigan Data Science Fellowship program.

The AI in Science Fellows will not only work on their individual research projects but will also collaborate on initiatives to support the adoption of AI methods in science and engineering research in the U-M research community. The Data Science Fellows will work at the boundaries of data science methods and domain sciences in an intellectually vibrant environment, and develop collaborative relationships with the U-M data science community. Both Fellowship programs are components of MIDAS’ effort to catalyze the transformative use of Data Science in a wide range of disciplines to achieve lasting societal impact, through research, training, outreach and partnership. The new Fellows will join a close-knit postdoc community with collocated work space at MIDAS and a variety of structured collaborative learning activities. 

“I am constantly amazed by their fantastic research, their enthusiasm to learn new skills together, and their effort to strengthen the data science and AI campus research community.” says Dr. H. V. Jagadish, Director of MIDAS. “In the past few years, our postdocs have collaborated with researchers from more than 30 U-M departments. They have also been developing research incubation activities and technical workshops for the campus community.”

The postdocs will offer an annual AI in Science and Engineering symposium in the spring. They will also offer summer academies on AI methods to enable science and engineering research. Researchers who would like to discuss their ideas with the postdocs at their regular meetings can contact Jen Lewis, postdoc program manager (jlolewis@umich.edu).

The 2023 postdoctoral fellows, with their discipline, affiliated department, faculty mentors, and their degree-granting institution are:

Kamal Abdulraheem

Kamal Abdulraheem

Ph.D., Nuclear Engineering
Schmidt AI in Science Fellow
AI Mentor: Majdi Radaideh, Alex Gorodetsky, Aerospace Engineering
Science Mentor: Brendan Kochunas, Nuclear Engineering and Radiological Science
Research Theme: AI management of nuclear reactors

Jacob Berv

Jacob Berv

PhD., Ecology and Evolutionary Biology
Schmidt AI in Science Fellow
AI Mentor: David Fouhey, Computer Science and Engineering
Science Mentor: Brian Weeks, Environment and Sustainability
Research Theme: ML models for avian evolution

Vital Fernández

Vital Fernández

Ph.D., Fluid Mechanics; Ph.D., Astrophysics
Schmidt AI in Science Fellow
AI Mentor: Xun Huan, Mechanical Engineering
Science Mentor: Sally Oey, Astronomy
Research Theme: Deep Learning for spectral analysis for distant galaxies

Matthew Andres Moreno

Dual Ph.D., Computer Science and Engineering and Ecology and Evolutionary Biology
Schmidt AI in Science Fellow
AI Mentor: Kevin Wood, Biophysics
Science Mentor: Luis Zaman, Complex Systems; Ecology and Evolutionary Biology
Research Theme: Digital Evolution

Amirhossein Moosavi

Ph.D., Management
Data Science Fellow
Science Mentor: Mariel Lavieri, Industrial and Operations Engineering
Research Theme: Using AI methods to improve optimization algorithms and incorporating personal and organizational constraints for healthcare management decision making

Kevin Napier

Kevin Napier

Ph.D., Physics
Schmidt AI in Science Fellow
AI Mentor: Camille Avestruz, Physics
Science Mentor: Hsing-Wen Lin, Physics
Research Theme: Computer Vision Detecting the faintest objects in the Solar System

Christin Salley

Christin Salley

Ph.D., Civil Engineering
Schmidt AI in Science Fellow
AI Mentor: Lu Wang, Computer Science and Engineering
Science Mentor: Sabine Loos, Civil and Environmental Engineering
Research Theme: Analysis of city planning and infrastructure. Impact of and recovery from natural hazards

Alyssa Schubert

Alyssa Schubert

Ph.D., Environmental Engineering
Schmidt AI in Science Fellow
AI Mentor: Bryan Goldsmith, Chemical Engineering
Science Mentor: Mark Burns, Chemical Engineering
Research Theme: AI for sensor data analysis for water quality monitoring

Jeremy Seeman

Ph.D., Statistics and Social Data Analytics
Data Science Fellow
Science Mentor: Yajuan Si, Institute for Social Research
Research Theme: Refining formal privacy methods and applying them to survey data.

Elena Shresta

Ph.D., Aerospace Engineering
Schmidt AI in Science Fellow
AI Mentor: Katie Skinner, Robotics
Science Mentor: Dimitra Panagou, Aerospace Engineering
Research Theme: Intelligent visual and flow-based navigation for autonomous underwater vehicles

Yiluan Song

Ph.D., Environmental Studies
Shmidt AI in Science Fellow
AI Mentor: Yang Chen, Statistics
Science Mentor: Kai Zhu, Environment and Sustainability
Research Theme: Projecting nature’s calendar under climate change

Nanata Sophonrat

Ph.D., Materials Science and Engineering
Schmidt AI in Science Fellow
AI Mentor: Ambuj Tewari, Statistics
Science Mentor: Anne McNeil, Chemistry
Research Theme: Chemist in the loop ML for plastics recycling

Weichi Yao

Ph.D., Statistics
Shmidt AI in Science Fellow
AI Mentor: Yixin Wang, Statistics
Science Mentor: Bryan Goldsmith, Chemical Engineering
Research Theme: Causal reasoning in materials science

AI in Science Fellows appointed in 2022 who will continue fellowships include: James Boyko, Computational Methods, Microevolutionary Biology; Yossi Cohen, Responsible AI, Industrial Decision-Making; Nathan Fox, Crowdsourced data ML, Human Nature Interactions; Jennifer Li, AI, Transient Sky; Andreas Rauch, Data-Driven Modeling, Computational Fluid Dynamics; Soumi Tribedi, AI methods, Electronic Structure Issues in Chemistry; Anastasia Visheratina, AI, Advanced Functional Materials & Devices; Yutong Wang, Developing Machine Learning Theory, Scientific Engineering Applications;  Xin Xie, AI in Topological Photonics. 

Data Science Fellows appointed in 2022 who will continue fellowships are Bernardo Modenesi, Data Science and Elyse Thulin, Computational Methods to Better Understand Human Behaviors.

Fellowships are made possible by generous gifts from Schmidt Futures and the Rocket Companies. The call for applications for the 2024 cohort will be published in August, 2023.

For more information about the AI in Science Fellowship, please visit our program page

For more information about the Data Science Fellowship, please visit our training page.