Pozzi Receives NSF CAREER Award for Infrastructure Management Research
From roads and bridges to water pipes and wind turbines, maintaining safe and functional infrastructure is no easy task. Rarely do managers have all the information needed to assess the current state, evolution, or performance of the various components that form the country’s aging infrastructure systems.
Through his research, CEE Assistant Professor Matteo Pozzi aims to develop algorithms that help infrastructure managers make smarter decisions and ultimately reduce uncertainty, risk, and management cost. To help him address this challenge, The National Science Foundation has selected Pozzi for the National Science Foundation Faculty Early Career Development (CAREER) Award, a prestigious five-year grant given to junior faculty for research and education.
In his research, Pozzi is focusing on the potential of sensors and robotic technology to collect data that can inform decision making. Through integrating models and probabilistic computational approaches, Pozzi hopes to not only optimize infrastructure operation and maintenance, but also the continued collection of information.
“Because we are managing such limited resources, data collection, this process of learning about the infrastructure, must be optimized,” he explains, proposing that algorithms could offer guidance on where and when to add more sensors, schedule inspections, or conduct strategic testing.
“Managers also have to compare the benefits of collecting information with the benefits of repairing various components, where each choice is expensive,” he adds. “This is what I am trying to develop—approaches and algorithms to make these comparisons and to suggest strategies that are optimal both for collecting information and for taking actions to benefit a component.”
Optimizing large infrastructure systems can be particularly complex but deliver a high impact. Often, individual components experience similar environmental conditions and other stressors due to proximity, so that information from one component can be used to infer the conditions of others, ultimately informing the strategic allocation of resources across an entire system.
As Pozzi establishes and refines his algorithms, he will also develop methods to teach infrastructure planning and analysis. Partnering with CMU’s Summer Engineering Experience for Girls program, Pozzi plans to build a simulation game in which students act as virtual infrastructure managers who must develop, test, and revise decision-making strategies in the face of persistent risk and uncertainty.
As Pozzi’s project gets underway, he’s enthusiastic about what’s ahead. “I'm excited because it's an expansive, long-term project that allows me to investigate topics I am passionate about, to educate students, and to form a path in the direction in which I want to research and teach.”