Title:
PRedicting Emergence Of Virulent Entities By Novel Technologies (PREVENT) Symposium - Session 4, Physiological and Environmental Level Theme
PRedicting Emergence Of Virulent Entities By Novel Technologies (PREVENT) Symposium - Session 4, Physiological and Environmental Level Theme
Author(s)
Kirschner, Denise
Kumar, Vipin
Colwell, Rita
Kumar, Vipin
Colwell, Rita
Advisor(s)
Editor(s)
Collections
Supplementary to
Permanent Link
Abstract
Denise Kirschner - Plenary Talk TITLE: "A Multi-Scale Systems Biology Approach Toward Tuberculosis Infection Interventions".
Vipin Kuma - Presentation TITLE: "Physics Guided Machine Learning: A New Framework For Accelerating Scientific Discovery". Process-based models of dynamical systems are often used to study engineering and environmental systems. Despite their extensive use, these models have several well-known limitations due to incomplete or inaccurate representations of the physical processes being modeled. Given rapid data growth due to advances in sensor technologies, there is a tremendous opportunity to systematically advance modeling in these domains by using machine learning (ML) methods. However, capturing this opportunity is contingent on a paradigm shift in data-intensive scientific discovery since the “black box” use of ML often leads to serious false discoveries in scientific applications. Because the hypothesis space of scientific applications is often complex and exponentially large, an uninformed data-driven search can easily select a highly complex model that is neither generalizable nor physically interpretable, resulting in the discovery of spurious relationships, predictors, and patterns. This problem becomes worse when there is a scarcity of labeled samples, which is quite common in science and engineering domains. This talk makes a case that in a real-world systems that are governed by physical processes, there is an opportunity to take advantage of fundamental physical principles to inform the search of a physically meaningful and accurate ML model. Even though this talk will illustrate such potential in the context of environmental problems, the paradigm has the potential to greatly advance the pace of discovery in a diverse set of discipline where mechanistic models are used, e.g., power engineering, climate science, weather forecasting, and pandemic management.
Vipin Kuma - Presentation TITLE: "Physics Guided Machine Learning: A New Framework For Accelerating Scientific Discovery". Process-based models of dynamical systems are often used to study engineering and environmental systems. Despite their extensive use, these models have several well-known limitations due to incomplete or inaccurate representations of the physical processes being modeled. Given rapid data growth due to advances in sensor technologies, there is a tremendous opportunity to systematically advance modeling in these domains by using machine learning (ML) methods. However, capturing this opportunity is contingent on a paradigm shift in data-intensive scientific discovery since the “black box” use of ML often leads to serious false discoveries in scientific applications. Because the hypothesis space of scientific applications is often complex and exponentially large, an uninformed data-driven search can easily select a highly complex model that is neither generalizable nor physically interpretable, resulting in the discovery of spurious relationships, predictors, and patterns. This problem becomes worse when there is a scarcity of labeled samples, which is quite common in science and engineering domains. This talk makes a case that in a real-world systems that are governed by physical processes, there is an opportunity to take advantage of fundamental physical principles to inform the search of a physically meaningful and accurate ML model. Even though this talk will illustrate such potential in the context of environmental problems, the paradigm has the potential to greatly advance the pace of discovery in a diverse set of discipline where mechanistic models are used, e.g., power engineering, climate science, weather forecasting, and pandemic management.
Sponsor
National Science Foundation (U.S.)
Date Issued
2021-02-23
Extent
58:08 minutes
Resource Type
Moving Image
Resource Subtype
Presentation