Juner Zhu

Research Overview

AI-driven discovery and characterization of complex multifield materials systems such as electro-chemo-mechanical coupling in batteries, for sustainability, reliability, and security

Modern engineered systems are becoming increasingly complex, presenting new challenges and opportunities for engineers. These systems inherently involve the deep coupling of multiple physical fields—mechanics, chemical reactions, mass transport, and biophysics—to achieve desired functions in various environments. Advanced manufacturing now enables such couplings across multiple length scales, from the nanoscale to the macroscale. Moreover, many systems involve heterogeneous materials and multiphase interactions, adding further layers of complexity. As a result, designing, assessing, and controlling these systems, as well as refurbishing, reusing, and recycling them at their end-of-life, demand new approaches that can interpret and manage their intricate multi-field behaviors.

Our research group advances multi-field science to develop new methods and technologies that decode system complexity for sustainability, reliability, and security. Under this broad vision, we pursue diverse topics including mechano-electrochemical analytics, automated characterization of materials and structures, and AI-driven discovery in mechanical sciences and engineering.

The group’s Principal Investigator, Juner Zhu, has a strong record of industrial collaboration addressing real-world challenges such as sheet metal forming, crashworthiness of EV batteries, battery swelling and degradation, and non-destructive assessment of energy storage systems. Over the past years, these efforts have been supported by leading companies including Apple, AVL, Hyundai, John Deere, Ford, Glimpse, LG Energy Solution, Murata, Saint-Gobain, SES.AI, Shell, Tesla, Toyota, and VW/Audi/Porsche. Building on this foundation, we are now transforming these research successes into commercial products and standardized techniques through spin-out ventures.

Currently, our group is interested in the multi-field science of coupled systems—exploring how one physical field can be modeled, inferred, and controlled through the measurement and interpretation of another, by integrating physics-based theory with data-driven learning.