Accurately measuring blood flow is critical to the fundamental understanding of cardiovascular disease and clinical decision making. Although researchers have made great strides in computational and experimental blood flow modeling, reliable data is still difficult to generate in large quantities.

Bioengineer Amir Arzani, an assistant professor at Northern Arizona University's Department of Mechanical Engineering, recently received a $507,642 grant from the National Science Foundation (NSF). The award will support Arzani's research aimed at developing scientific machine learning models to improve the accuracy and fidelity of current cardiovascular flow models.

Arzani, director of NAU's Cardiovascular Biomechanics Lab, studies the mechanisms behind initiation and progression of different cardiovascular diseases, developing computational models that can capture the multiscale and multiphysics nature of cardiovascular disease.

In my lab, we routinely use a 3D computer modeling technique called computational fluid dynamics (CFD) to study complex fluid flow processes and blood flow in diseased arteries. We use numerical modeling and high-performance computing to solve the fundamental mathematical equations that govern fluid flow."

Amir Arzani, Bioengineer, Assistant Professor, Department of Mechanical Engineering, Cardiovascular Biomechanics, Lab, Northern Arizona University

 

"Data science and machine learning are influencing our daily lives," Arzani said, "from our interactions with Google services and social media to movie suggestions in Netflix. These models use massive amounts of data. However, in engineering modeling, we do not have the luxury of large data. Scientific machine learning allows us to tackle data-driven modeling in engineering. This project will develop software that synergistically integrates novel deep learning and traditional physics-based modeling to address fundamental issues in high-fidelity blood flow and cardiovascular disease modeling. The software will promote the progress of scientific cardiovascular disease and fluid flow modeling research and ultimately advance national health."

The team, which will consist of Ph.D. students in Arzani's lab as well as several collaborators at other universities, including Purdue University, The University of Toledo, Auburn University, the University of Wisconsin and McMaster University, will integrate imperfect experimental data with uncertain physics-based models to overcome the limitations of each approach, testing the methods in different cardiovascular disease applications.

Award to fund development of new program to promote STEM education

The award was made to Arzani through the NSF's prestigious Faculty Early Career Development (CAREER) Program "in support of early-career faculty who have the potential to serve as academic role models in research and education and to lead advances in the mission of their department or organization. Activities pursued by early-career faculty should build a firm foundation for a lifetime of leadership in integrating education and research."

The award will also support the development of a new educational program called FAST (Fluids, Art, and StoryTelling) to generate interest for integrated computer modeling and engineering education.

"As part of the project, we will create new education programs integrated with research to promote fluid flow computer modeling education by blending data analysis, visualization and computer modeling," Arzani said.

"Fluid mechanics is generally considered a math-heavy and conceptually difficult class. I will integrate artistic fluid flow visualization with storytelling to help explain difficult concepts in simple and exciting language. The goal is to leverage the art of visualization and storytelling to show the hidden beauty in fluid mechanics computer modeling."

The grant will support Ph.D. students as they conduct high quality, state-of-the-art research in Arzani's lab, and the education program will be integrated with regional initiatives to promote STEM participation in underrepresented groups.