EAGER: Collaborative Research: III: Exploring Physics Guided Machine Learning for Accelerating Sensing and Physical Sciences

Ohio State University, The, Columbus OH

Investigators

Abstract

As machine learning (ML) continues to revolutionize the commercial space including vision, speech, and text recognition, there is great anticipation in the scientific community to unlock the power of ML for accelerating scientific discovery. However, black-box ML models, which rely solely on training data and ignore existing scientific knowledge have met with limited success in scientific problems, particularly when labeled data is limited, sometimes even leading to spectacular failures. This is because the black box ML models are susceptible to learning spurious relationships that do not generalize well outside the data they are trained for. The emerging paradigm of physics-guided machine learning (PGML), which leverages the unique ability of ML algorithms to automatically extract patterns and models from data with guidance of the knowledge accumulated in physics (or scientific theories), aims to address the challenges faced by black box ML in scientific applications. Significant exploratory efforts are needed to formulate and assess sound PGML approaches for particular scientific problems. For data science, PGML has the potential to transform ML beyond black-box applications by enabling solutions that generalize well even on unseen input-output distributions that are different from those encountered during training, by anchoring ML methods with the scientific body of knowledge. PGML makes a distinct departure from the conventional view that physics-based models and ML models are developed in isolation but seldom mixed together. The proposed project is fundamentally different from existing body of research that attempts to combine ML and domain sciences, e.g., by making use of domain-specific knowledge in ML algorithms in simplistic ways, or making use of data in the physics-based modeling process albeit without allowing data to change the functional forms of existing physics-based models. The tight interplay between data science and the domains of physics and sensing in the project lends itself naturally to diverse education activities that complement the research tasks outlined by our team. Over the duration of this one-year project, the team will develop an integrative course at the graduate level on "ML meets Physics", which explores topical, emerging themes in this interdisciplinary area. Offerings of the course will draw upon course modules shared between the four universities, such as shared guest videos and case studies. The physics department at BU has a well-developed "Physics Outreach Project" that annually performs science exhibitions for elementary schools in Binghamton metropolitan area, for which the team will create a new exhibition about neural networks and ML. In follow-on work, similar outreach events will be replicated at schools (Robinson Middle School in Lowell and Metro STEM Middle School in Columbus). The PIs are committed to increasing the diversity of involvement at various levels of the training ecosystem impacted by this project, and have planned various coordinated broader impact activities for inclusion of female and underrepresented minority students as well as faculty. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.