The PODS funding strongly encourages works that transform research domains through data science and AI, works that improve the reproducibility of research, and works that promise major impact and potential for significant expansion. “We are thrilled by the many brilliant research ideas in the large number of submitted proposals. Our funding this year focuses on the four current MIDAS research pillars,” says Dr. H. V. Jagadish, MIDAS Director, “These projects will have an immediate impact on responsible research, using new data types to measure society, applying cutting-edge methodology to healthcare intervention, and building strengths to support national priorities.”
Previous MIDAS grants have made it possible for the research teams to form many new collaborations, formulate groundbreaking ideas, and bring more than $124 million of external funding to U-M.
The awarded PODS grants and the (co) Principal Investigators are:
- A Machine-Learning Approach to Reduce Uncertainty in Climate Forcing by Aerosols, Joyce Penner (Climate and Space Sciences and Engineering)
- AI-based author entity disambiguation for promoting fair evaluation of women in science, Jinseok Kim (Institute for Social Research)
- Building a genomic literature knowledgebase, Jie Liu (Computational Medicine and Bioinformatics)
- Combating and predicting drug resistance using a hybrid mechanistic machine learning model, Sriram Chandrasekaran (Biomedical Engineering), Rudy Richardson (Toxicology)
- Developing a large-scale dataset to track romantic relationship formation and maintenance, Amie Gordon (Psychology), Elizabeth Bruch (Sociology)
- Developing Language-based Tools For Real-Time Counseling Feedback, Veronica Perez-Rosas (Computer Science and Engineering), Kenneth Resnicow (Health Behavior and Health Education), Rada Mihalcea (Computer Science and Engineering)
- Improving Cardiovascular Disease Detection with a Novel Multi-label Classifier for Electrocardiograms: Capturing Label Uncertainty and Complex Hierarchical Relationships between Output Classes, Negar Farzaneh (Emergency Medicine), Hamid Ghanbari (Internal Medicine)
- Machine Learning Guided Co-design for Reconstructive Spectroscopy, Qing Qu (Electrical and Computer Engineering), Pei-Cheng Ku (Electrical and Computer Engineering)
- Sustainability outcomes of restrictions on human actions: COVID-19 mobility changes, forest fires and air pollution across land regimes, Arun Agrawal (Schooll for Environment and Sustainability), Ines Ibanez (School for Environment and Sustainability), Yang Chen (Statistics)
- Unlocking the vault: machine learning methods for the mobilization of data from millions of plant images, Stephen Smith (Ecology and Evolutionary Biology)