(371o) Integrating Multiscale Modeling and Simulation (MMS) and Machine Learning (ML) for Chemical Engineering Applications

The development of novel technologies, systems, and processes in chemical engineering applications is conventionally complemented by experimental testing. However, experimental tools for testing and examining the results are expensive, and their use is time-consuming. In this context, to accelerate the development, commercialization, utilization, and problem solutions of novel technologies, systems, and processes in chemical engineering related fields, the simultaneous use of computational and experimental tools such as theoretical (multiscale modeling-simulation (MMS), optimization, machine learning (ML), techno-economic analysis, etc.) and experimental approaches is essential. These approaches greatly improve the entire technology development process by reducing cost and time and allow us to tackle problems that cannot be solved using theoretical or experimental methods alone. Among the theoretical methods, MMS and ML are potent methods with many proven applications. ML is a popular method for integrating multimodality and multifidelity data, and revealing correlations between interconnected phenomena presents a unique opportunity in this regard. However, ML typically performs poorly with sparse data, disregards the fundamental laws of physics and can lead to ill-posed problems or non-physical solutions. Classical physics-based simulation appears to be irreplaceable in this discipline. MMS is an effective method for integrating multiscale, multiphysics data and identifying the mechanisms that explain the emergence of function. However, MMS alone frequently fails to effectively combine large datasets from various sources and resolutions. ML and MMS can naturally complement one another to produce robust predictive models that incorporate the underlying physics to manage ill-posed problems and investigate vast design spaces. Thus, this study aims to develop and apply hierarchical integrated MMS-ML and experimental approaches to technology development and problem solutions. The main objectives of this study are: (1) identifying a taxonomy of multiscale modeling-simulation and machine learning paradigms and approaches, as well as a discussion of their strengths and limitations, by categorizing and rating them for the targeted technology applications; (2) developing procedures to integrate MMS and ML, which have been leveraged to facilitate the design and development of novel technologies, systems, and processes; (3) identifying, gathering, and modifying datasets available in the literature for the targeted systems; (4) demonstrating the application of novel hierarchical theoretical (integrated MMS and ML) and experimental approaches to targeted technology development and problem-solving: (5) finally, creating MMS and ML- based designers/deciders/proposers/predictors.