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.


This content will become publicly available on October 27, 2026

Title: Accelerating multi-species field-theoretic simulations using Bayesian optimization
Field-based simulations can be challenging in multi-component polymer systems and are highly sensitive to the choice of relaxation coefficients (λ) used in the field update algorithms. Judiciously chosen relaxation coefficients are critical for both the stability and convergence of field-based simulations, yet their selection is challenging when the number of unique chemical species in the system is large. In this work, we develop a new method to automatically and efficiently locate optimal relaxation coefficients in systems with large numbers of species. We begin by analyzing the effects of relaxation coefficients in two- and three-species systems and demonstrate that regions of high-performance are both narrow and system-specific. Based on these findings, we next develop a method based on Bayesian optimization that automatically locates relaxation coefficients that are stable and exhibit good performance. We demonstrate that our method is considerably faster than naive search methods and becomes particularly efficient as the system complexity increases. This work demonstrates that Bayesian optimization can be used to stabilize and accelerate field-based simulations that contain many different chemical species.  more » « less
Award ID(s):
2337554
PAR ID:
10657596
Author(s) / Creator(s):
 ;  ;  
Publisher / Repository:
Mol. Syst. Des. Eng.
Date Published:
Journal Name:
Molecular Systems Design & Engineering
Volume:
10
Issue:
11
ISSN:
2058-9689
Page Range / eLocation ID:
982 to 996
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; (, Proceedings of Machine Learning Research)
    Camps-Valls, Gustau; Ruiz, Francisco J.; Valera, Isabel (Ed.)
    Traditionally, Bayesian network structure learning is often carried out at a central site, in which all data is gathered. However, in practice, data may be distributed across different parties (e.g., companies, devices) who intend to collectively learn a Bayesian network, but are not willing to disclose information related to their data owing to privacy or security concerns. In this work, we present a federated learning approach to estimate the structure of Bayesian network from data that is horizontally partitioned across different parties. We develop a distributed structure learning method based on continuous optimization, using the alternating direction method of multipliers (ADMM), such that only the model parameters have to be exchanged during the optimization process. We demonstrate the flexibility of our approach by adopting it for both linear and nonlinear cases. Experimental results on synthetic and real datasets show that it achieves an improved performance over the other methods, especially when there is a relatively large number of clients and each has a limited sample size. 
    more » « less
  2. ; (, Energies)
    Voltage control in modern electric power distribution systems has become challenging due to the increasing penetration of distributed energy resources (DER). The current state-of-the-art voltage control is based on static/pre-determined DER volt-var curves. Static volt-var curves do not provide sufficient flexibility to address the temporal and spatial aspects of the voltage control problem in a power system with a large number of DER. This paper presents a simple, scalable, and robust distributed optimization framework (DOF) for optimizing voltage control. The proposed framework allows for data-driven distributed voltage optimization in a power distribution system. This method enhances voltage control by optimizing volt-var curve parameters of inverters in a distributed manner based on a cellular computational network (CCN) representation of the power distribution system. The cellular optimization approach enables the system-wide optimization. The cells to be optimized may be prioritized and two methods namely, graph and impact-based methods, are studied. The impact-based method requires extra initial computational efforts but thereafter provides better computational throughput than the graph-based method. The DOF is illustrated on a modified standard distribution test case with several DERs. The results from the test case demonstrate that the DOF based volt-var optimization results in consistently better performance than the state-of-the-art volt-var control. 
    more » « less
  3. ; ; ; ; (, Proceedings of the ACM on Management of Data)
    Supporting the interactive exploration of large datasets is a popular and challenging use case for data management systems. Traditionally, the interface and the back-end system are built and optimized separately, and interface design and system optimization require different skill sets that are difficult for one person to master. To enable analysts to focus on visualization design, we contribute VegaPlus, a system that automatically optimizes interactive dashboards to support large datasets. To achieve this, VegaPlus leverages two core ideas. First, we introduce an optimizer that can reason about execution plans in Vega, a back-end DBMS, or a mix of both environments. The optimizer also considers how user interactions may alter execution plan performance, and can partially or fully rewrite the plans when needed. Through a series of benchmark experiments on seven different dashboard designs, our results show that VegaPlus provides superior performance and versatility compared to standard dashboard optimization techniques. 
    more » « less
  4. ; ; ; ; ; ; (, ACM transactions on design automation of electronic systems)
    Analog IC performance has a strong dependence on interconnect RC parasitics, which are significantly affected by wire sizes in recent technologies, where minimum-width wires have high resistance. However, performance-driven wire sizing for analog ICs has received very little research attention. In order to fill this void, we develop several techniques to facilitate an end-to-end automatic wire sizing approach. They include a circuit performance model based on customized graph neural network (GNN) and two optimization techniques: one using Bayesian optimization accelerated by the GNN model, and the other based on TensorFlow training. Experimental results show that our technique can achieve 11% circuit performance improvement or 8.7× speedup compared to a conventional Bayesian optimization method. 
    more » « less
  5. ; ; ; (, Digital Discovery)
    Autonomous chemical process development and optimization methods use algorithms to explore the operating parameter space based on feedback from experimentally determined exit stream compositions. Measuring the compositions of multicomponent streams is challenging, requiring multiple analytical techniques to differentiate between similar chemical components in the mixture and determine their concentration. Herein, we describe a universal analytical methodology based on multitarget regression machine learning (ML) models to rapidly determine chemical mixtures' compositions from Fourier transform infrared (FTIR) absorption spectra. Specifically, we used simulated FTIR spectra for up to 6 components in water and tested seven different ML algorithms to develop the methodology. All algorithms resulted in regression models with mean absolute errors (MAE) between 0–0.27 wt%. We validated the methodology with experimental data obtained on mixtures prepared using a network of programmable pumps in line with an FTIR transmission flow cell. ML models were trained using experimental data and evaluated for mixtures of up to 4-components with similar chemical structures, including alcohols ( i.e. , glycerol, isopropanol, and 1-butanol) and nitriles ( i.e. , acrylonitrile, adiponitrile, and propionitrile). Linear regression models predicted concentrations with coefficients of determination, R 2 , between 0.955 and 0.986, while artificial neural network models showed a slightly lower accuracy, with R 2 between 0.854 and 0.977. These R 2 correspond to MAEs of 0.28–0.52 wt% for mixtures with component concentrations between 4–10 wt%. Thus, we demonstrate that ML models can accurately determine the compositions of multicomponent mixtures of similar species, enhancing spectroscopic chemical quantification for use in autonomous, fast process development and optimization. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email