1
|
Musharaf HM, Roshan U, Mudugamuwa A, Trinh QT, Zhang J, Nguyen NT. Computational Fluid-Structure Interaction in Microfluidics. MICROMACHINES 2024; 15:897. [PMID: 39064408 PMCID: PMC11278627 DOI: 10.3390/mi15070897] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/27/2024] [Revised: 07/02/2024] [Accepted: 07/04/2024] [Indexed: 07/28/2024]
Abstract
Micro elastofluidics is a transformative branch of microfluidics, leveraging the fluid-structure interaction (FSI) at the microscale to enhance the functionality and efficiency of various microdevices. This review paper elucidates the critical role of advanced computational FSI methods in the field of micro elastofluidics. By focusing on the interplay between fluid mechanics and structural responses, these computational methods facilitate the intricate design and optimisation of microdevices such as microvalves, micropumps, and micromixers, which rely on the precise control of fluidic and structural dynamics. In addition, these computational tools extend to the development of biomedical devices, enabling precise particle manipulation and enhancing therapeutic outcomes in cardiovascular applications. Furthermore, this paper addresses the current challenges in computational FSI and highlights the necessity for further development of tools to tackle complex, time-dependent models under microfluidic environments and varying conditions. Our review highlights the expanding potential of FSI in micro elastofluidics, offering a roadmap for future research and development in this promising area.
Collapse
Affiliation(s)
- Hafiz Muhammad Musharaf
- Queensland Micro and Nanotechnology Centre, Griffith University, Brisbane, QLD 4111, Australia; (H.M.M.); (U.R.); (A.M.); (Q.T.T.)
| | - Uditha Roshan
- Queensland Micro and Nanotechnology Centre, Griffith University, Brisbane, QLD 4111, Australia; (H.M.M.); (U.R.); (A.M.); (Q.T.T.)
| | - Amith Mudugamuwa
- Queensland Micro and Nanotechnology Centre, Griffith University, Brisbane, QLD 4111, Australia; (H.M.M.); (U.R.); (A.M.); (Q.T.T.)
| | - Quang Thang Trinh
- Queensland Micro and Nanotechnology Centre, Griffith University, Brisbane, QLD 4111, Australia; (H.M.M.); (U.R.); (A.M.); (Q.T.T.)
| | - Jun Zhang
- Queensland Micro and Nanotechnology Centre, Griffith University, Brisbane, QLD 4111, Australia; (H.M.M.); (U.R.); (A.M.); (Q.T.T.)
- School of Engineering and Built Environment, Griffith University, Brisbane, QLD 4111, Australia
| | - Nam-Trung Nguyen
- Queensland Micro and Nanotechnology Centre, Griffith University, Brisbane, QLD 4111, Australia; (H.M.M.); (U.R.); (A.M.); (Q.T.T.)
| |
Collapse
|
2
|
Park Y, Kim J, Hwang S, Han S. Scalable Parallel Algorithm for Graph Neural Network Interatomic Potentials in Molecular Dynamics Simulations. J Chem Theory Comput 2024; 20:4857-4868. [PMID: 38813770 DOI: 10.1021/acs.jctc.4c00190] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/31/2024]
Abstract
Message-passing graph neural network interatomic potentials (GNN-IPs), particularly those with equivariant representations such as NequIP, are attracting significant attention due to their data efficiency and high accuracy. However, parallelizing GNN-IPs poses challenges because multiple message-passing layers complicate data communication within the spatial decomposition method, which is preferred by many molecular dynamics (MD) packages. In this article, we propose an efficient parallelization scheme compatible with GNN-IPs and develop a package, SevenNet (Scalable EquiVariance-Enabled Neural NETwork), based on the NequIP architecture. For MD simulations, SevenNet interfaces with the LAMMPS package. Through benchmark tests on a 32-GPU cluster with examples of SiO2, SevenNet achieves over 80% parallel efficiency in weak-scaling scenarios and exhibits nearly ideal strong-scaling performance as long as GPUs are fully utilized. However, the strong-scaling performance significantly declines with suboptimal GPU utilization, particularly affecting parallel efficiency in cases involving lightweight models or simulations with small numbers of atoms. We also pretrain SevenNet with a vast data set from the Materials Project (dubbed "SevenNet-0") and assess its performance on generating amorphous Si3N4 containing more than 100,000 atoms. By developing scalable GNN-IPs, this work aims to bridge the gap between advanced machine-learning models and large-scale MD simulations, offering researchers a powerful tool to explore complex material systems with high accuracy and efficiency.
Collapse
Affiliation(s)
- Yutack Park
- Department of Materials Science and Engineering and Research Institute of Advanced Materials, Seoul National University, Seoul 08826, Korea
| | - Jaesun Kim
- Department of Materials Science and Engineering and Research Institute of Advanced Materials, Seoul National University, Seoul 08826, Korea
| | - Seungwoo Hwang
- Department of Materials Science and Engineering and Research Institute of Advanced Materials, Seoul National University, Seoul 08826, Korea
| | - Seungwu Han
- Department of Materials Science and Engineering and Research Institute of Advanced Materials, Seoul National University, Seoul 08826, Korea
- Korea Institute for Advanced Study, Seoul 02455, Korea
| |
Collapse
|
3
|
Cao Z, Wang Y, Lorsung C, Barati Farimani A. Neural network predicts ion concentration profiles under nanoconfinement. J Chem Phys 2023; 159:094702. [PMID: 37655768 DOI: 10.1063/5.0147119] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/19/2023] [Accepted: 06/23/2023] [Indexed: 09/02/2023] Open
Abstract
Modeling the ion concentration profile in nanochannel plays an important role in understanding the electrical double layer and electro-osmotic flow. Due to the non-negligible surface interaction and the effect of discrete solvent molecules, molecular dynamics (MD) simulation is often used as an essential tool to study the behavior of ions under nanoconfinement. Despite the accuracy of MD simulation in modeling nanoconfinement systems, it is computationally expensive. In this work, we propose neural network to predict ion concentration profiles in nanochannels with different configurations, including channel widths, ion molarity, and ion types. By modeling the ion concentration profile as a probability distribution, our neural network can serve as a much faster surrogate model for MD simulation with high accuracy. We further demonstrate the superior prediction accuracy of neural network over XGBoost. Finally, we demonstrated that neural network is flexible in predicting ion concentration profiles with different bin sizes. Overall, our deep learning model is a fast, flexible, and accurate surrogate model to predict ion concentration profiles in nanoconfinement.
Collapse
Affiliation(s)
- Zhonglin Cao
- Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, USA
| | - Yuyang Wang
- Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, USA
| | - Cooper Lorsung
- Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, USA
| | - Amir Barati Farimani
- Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, USA
- Department of Chemical Engineering, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, USA
- Machine Learning Department, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, USA
| |
Collapse
|
4
|
Wang Y, Xu C, Li Z, Barati Farimani A. Denoise Pretraining on Nonequilibrium Molecules for Accurate and Transferable Neural Potentials. J Chem Theory Comput 2023; 19:5077-5087. [PMID: 37390120 PMCID: PMC10413865 DOI: 10.1021/acs.jctc.3c00289] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/13/2023] [Indexed: 07/02/2023]
Abstract
Recent advances in equivariant graph neural networks (GNNs) have made deep learning amenable to developing fast surrogate models to expensive ab initio quantum mechanics (QM) approaches for molecular potential predictions. However, building accurate and transferable potential models using GNNs remains challenging, as the data are greatly limited by the expensive computational costs and level of theory of QM methods, especially for large and complex molecular systems. In this work, we propose denoise pretraining on nonequilibrium molecular conformations to achieve more accurate and transferable GNN potential predictions. Specifically, atomic coordinates of sampled nonequilibrium conformations are perturbed by random noises, and GNNs are pretrained to denoise the perturbed molecular conformations which recovers the original coordinates. Rigorous experiments on multiple benchmarks reveal that pretraining significantly improves the accuracy of neural potentials. Furthermore, we show that the proposed pretraining approach is model-agnostic, as it improves the performance of different invariant and equivariant GNNs. Notably, our models pretrained on small molecules demonstrate remarkable transferability, improving performance when fine-tuned on diverse molecular systems, including different elements, charged molecules, biomolecules, and larger systems. These results highlight the potential for leveraging denoise pretraining approaches to build more generalizable neural potentials for complex molecular systems.
Collapse
Affiliation(s)
- Yuyang Wang
- Department
of Mechanical Engineering, Carnegie Mellon
University, Pittsburgh, Pennsylvania 15213, United States
- Machine
Learning Department, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, United States
| | - Changwen Xu
- Department
of Mechanical Engineering, Carnegie Mellon
University, Pittsburgh, Pennsylvania 15213, United States
| | - Zijie Li
- Department
of Mechanical Engineering, Carnegie Mellon
University, Pittsburgh, Pennsylvania 15213, United States
| | - Amir Barati Farimani
- Department
of Mechanical Engineering, Carnegie Mellon
University, Pittsburgh, Pennsylvania 15213, United States
- Machine
Learning Department, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, United States
- Department
of Materials Science and Engineering, Carnegie
Mellon University, Pittsburgh, Pennsylvania 15213, United States
- Department
of Chemical Engineering, Carnegie Mellon
University, Pittsburgh, Pennsylvania 15213, United States
| |
Collapse
|
5
|
Kubečka J, Knattrup Y, Engsvang M, Jensen AB, Ayoubi D, Wu H, Christiansen O, Elm J. Current and future machine learning approaches for modeling atmospheric cluster formation. NATURE COMPUTATIONAL SCIENCE 2023; 3:495-503. [PMID: 38177415 DOI: 10.1038/s43588-023-00435-0] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/21/2022] [Accepted: 03/16/2023] [Indexed: 01/06/2024]
Abstract
The formation of strongly bound atmospheric molecular clusters is the first step towards forming new aerosol particles. Recent advances in the application of machine learning models open an enormous opportunity for complementing expensive quantum chemical calculations with efficient machine learning predictions. In this Perspective, we present how data-driven approaches can be applied to accelerate cluster configurational sampling, thereby greatly increasing the number of chemically relevant systems that can be covered.
Collapse
Affiliation(s)
- Jakub Kubečka
- Department of Chemistry, Aarhus University, Aarhus, Denmark
| | - Yosef Knattrup
- Department of Chemistry, Aarhus University, Aarhus, Denmark
| | | | | | - Daniel Ayoubi
- Department of Chemistry, Aarhus University, Aarhus, Denmark
| | - Haide Wu
- Department of Chemistry, Aarhus University, Aarhus, Denmark
| | | | - Jonas Elm
- Department of Chemistry, Aarhus University, Aarhus, Denmark.
- iCLIMATE Aarhus University Interdisciplinary Centre for Climate Change, Aarhus, Denmark.
| |
Collapse
|
6
|
Han Z, Kammer DS, Fink O. Learning physics-consistent particle interactions. PNAS NEXUS 2022; 1:pgac264. [PMID: 36712322 PMCID: PMC9802333 DOI: 10.1093/pnasnexus/pgac264] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 10/31/2022] [Accepted: 11/15/2022] [Indexed: 11/19/2022]
Abstract
Interacting particle systems play a key role in science and engineering. Access to the governing particle interaction law is fundamental for a complete understanding of such systems. However, the inherent system complexity keeps the particle interaction hidden in many cases. Machine learning methods have the potential to learn the behavior of interacting particle systems by combining experiments with data analysis methods. However, most existing algorithms focus on learning the kinetics at the particle level. Learning pairwise interaction, e.g., pairwise force or pairwise potential energy, remains an open challenge. Here, we propose an algorithm that adapts the Graph Networks framework, which contains an edge part to learn the pairwise interaction and a node part to model the dynamics at particle level. Different from existing approaches that use neural networks in both parts, we design a deterministic operator in the node part that allows to precisely infer the pairwise interactions that are consistent with underlying physical laws by only being trained to predict the particle acceleration. We test the proposed methodology on multiple datasets and demonstrate that it achieves superior performance in inferring correctly the pairwise interactions while also being consistent with the underlying physics on all the datasets. While the previously proposed approaches are able to be applied as simulators, they fail to infer physically consistent particle interactions that satisfy Newton's laws. Moreover, the proposed physics-induced graph network for particle interaction also outperforms the other baseline models in terms of generalization ability to larger systems and robustness to significant levels of noise. The developed methodology can support a better understanding and discovery of the underlying particle interaction laws, and hence, guide the design of materials with targeted properties.
Collapse
Affiliation(s)
- Zhichao Han
- Institute for Building Materials, ETH Zürich, 8093 Zürich, Switzerland
| | - David S Kammer
- Institute for Building Materials, ETH Zürich, 8093 Zürich, Switzerland
| | - Olga Fink
- To whom correspondence should be addressed:
| |
Collapse
|
7
|
Ess DH, Jelfs KE, Kulik HJ. Chemical design by artificial intelligence. J Chem Phys 2022; 157:120401. [PMID: 36182437 DOI: 10.1063/5.0123281] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/14/2022] Open
Affiliation(s)
- Daniel H Ess
- Department of Chemistry and Biochemistry, Brigham Young University, Provo, Utah 84604, USA
| | - Kim E Jelfs
- Department of Chemistry, Molecular Sciences Research Hub, 82 Wood Lane, White City Campus, Imperial College London, London W12 0BZ, United Kingdom
| | - Heather J Kulik
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, USA
| |
Collapse
|