skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Challenges and Opportunities for Machine Learning in Multiscale Computational Modeling
Abstract Many mechanical engineering applications call for multiscale computational modeling and simulation. However, solving for complex multiscale systems remains computationally onerous due to the high dimensionality of the solution space. Recently, machine learning (ML) has emerged as a promising solution that can either serve as a surrogate for, accelerate or augment traditional numerical methods. Pioneering work has demonstrated that ML provides solutions to governing systems of equations with comparable accuracy to those obtained using direct numerical methods, but with significantly faster computational speed. These high-speed, high-fidelity estimations can facilitate the solving of complex multiscale systems by providing a better initial solution to traditional solvers. This paper provides a perspective on the opportunities and challenges of using ML for complex multiscale modeling and simulation. We first outline the current state-of-the-art ML approaches for simulating multiscale systems and highlight some of the landmark developments. Next, we discuss current challenges for ML in multiscale computational modeling, such as the data and discretization dependence, interpretability, and data sharing and collaborative platform development. Finally, we suggest several potential research directions for the future.  more » « less
Award ID(s):
2203580
PAR ID:
10442448
Author(s) / Creator(s):
; ; ;
Date Published:
Journal Name:
Journal of Computing and Information Science in Engineering
Volume:
23
Issue:
6
ISSN:
1530-9827
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; (, Electronics)
    The integration of machine learning in power systems, particularly in stability and dynamics, addresses the challenges brought by the integration of renewable energies and distributed energy resources (DERs). Traditional methods for power system transient stability, involving solving differential equations with computational techniques, face limitations due to their time-consuming and computationally demanding nature. This paper introduces physics-informed Neural Networks (PINNs) as a promising solution for these challenges, especially in scenarios with limited data availability and the need for high computational speed. PINNs offer a novel approach for complex power systems by incorporating additional equations and adapting to various system scales, from a single bus to multi-bus networks. Our study presents the first comprehensive evaluation of physics-informed Neural Networks (PINNs) in the context of power system transient stability, addressing various grid complexities. Additionally, we introduce a novel approach for adjusting loss weights to improve the adaptability of PINNs to diverse systems. Our experimental findings reveal that PINNs can be efficiently scaled while maintaining high accuracy. Furthermore, these results suggest that PINNs significantly outperform the traditional ode45 method in terms of efficiency, especially as the system size increases, showcasing a progressive speed advantage over ode45. 
    more » « less
  2. ; ; ; (, Intelligent Computing)
    Computational fluid dynamics (CFD) simulations are broadly used in many engineering and physics fields. CFD requires the solution of the Navier–Stokes (N-S) equations under complex flow and boundary conditions. However, applications of CFD simulations are computationally limited by the availability, speed, and parallelism of high-performance computing. To address this, machine learning techniques have been employed to create data-driven approximations for CFD to accelerate computational efficiency. Unfortunately, these methods predominantly depend on large labeled CFD datasets, which are costly to procure at the scale required for robust model development. In response, we introduce a weakly supervised approach that, through a multichannel input capturing boundary and geometric conditions, solves steady-state N-S equations. Our method achieves state-of-the-art results without relying on labeled simulation data, instead using a custom data-driven and physics-informed loss function and small-scale solutions to prime the model for solving the N-S equations. By training stacked models, we enhance resolution and predictability, yielding high-quality numerical solutions to N-S equations without hefty computational demands. Remarkably, our model, being highly adaptable, produces solutions on a 512 × 512 domain in a swift 7 ms, outpacing traditional CFD solvers by a factor of 1,000. This paves the way for real-time predictions on consumer hardware and Internet of Things devices, thereby boosting the scope, speed, and cost-efficiency of solving boundary-value fluid problems. 
    more » « less
  3. ; ; (, Proceedings of the 2nd ACM SIGSPATIAL International Workshop on Animal Movement Ecology and Human Mobility)
    Ossi, Federico; Hachem, Fatima; Robira, Benjamin; Ellis Soto, Diego; Rutz, Christian; Dodge, Somayeh; Cagnacci, Francesca; Damiani, Maria Luisa (Ed.)
    Data collected about routine human activity and mobility is used in diverse applications to improve our society. Robust models are needed to address the challenges of our increasingly interconnected world. Methods capable of portraying the dynamic properties of complex human systems, such as simulation modeling, must comply to rigorous data requirements. Modern data sources, like SafeGraph, provide aggregate data collected from location aware technologies. Opportunities and challenges arise to incorporate the new data into existing analysis and modeling methods. Our research employs a multiscale spatial similarity index to compare diverse origin-destination mobility datasets. Established distance ranges accommodate spatial variability in the model’s datasets. This paper explores how similarity scores change with different aggregations to address discrepancies in the source data’s temporal granularity. We suggest possible explanations for variations in the similarity scores and extract characteristics of human mobility for the study area. The multiscale spatial similarity index may be integrated into a vast array of analysis and modeling workflows, either during preliminary analysis or later evaluation phases as a method of data validation (e.g., agent-based models). We propose that the demonstrated tool has potential to enhance mobility modeling methods in the context of complex human systems. 
    more » « less
  4. ; ; (, Science Advances)
    Cardiac dynamics modeling has been useful for studying and treating arrhythmias. However, it is a multiscale problem requiring the solution of billions of differential equations describing the complex electrophysiology of interconnected cells. Therefore, large-scale cardiac modeling has been limited to groups with access to supercomputers and clusters. Many areas of computational science face similar problems where computational costs are too high for personal computers so that supercomputers or clusters currently are necessary. Here, we introduce a new approach that makes high-performance simulation of cardiac dynamics and other large-scale systems like fluid flow and crystal growth accessible to virtually anyone with a modest computer. For cardiac dynamics, this approach will allow not only scientists and students but also physicians to use physiologically accurate modeling and simulation tools that are interactive in real time, thereby making diagnostics, research, and education available to a broader audience and pushing the boundaries of cardiac science. 
    more » « less
  5. ; ; ; (, The Journal of Chemical Physics)
    Complex fluids in confined geometries are found in numerous applications, including membranes, lubricants, and microelectronics. However, current computational approaches for studying these systems have a variety of shortcomings. Particle-based simulations are limited in accessible length and time scales, while the interaction parameters in field-theoretic approaches have no direct connections to specific chemistries. Here, we extend a multiscale framework that we earlier developed for bulk systems to address these challenges in confined polymer formulations. The methodology uses atomistic molecular dynamics simulations to parameterize coarse-grained field-theoretic models of confined fluids, which subsequently enable fast equilibration and the ability to surmount length scales inaccessible to particle-based simulation methods. We first use this workflow to study a model system consisting of a confined Gaussian fluid to validate and determine best practices for the coarse-graining methodology. Next, we demonstrate this methodology by applying it to an alkyl acrylic diblock copolymer and dodecane solution confined between α-iron oxide surfaces and examining the effect of diblock concentration and length on the structure of the adsorbed film. This approach has the potential to expedite the study of complex fluids in confined environments, bridging atomistic detail and mesoscale modeling with broad implications for materials design. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email