中文
相关论文

相关论文: Modeling of Coupled Turbulent Channel Porous Media…

200 篇论文

Identifying the heterogeneous conductivity field and reconstructing the contaminant release history are key aspects of subsurface remediation. Achieving these two goals with limited and noisy hydraulic head and concentration measurements is…

机器学习 · 计算机科学 2022-09-29 Zitong Zhou , Nicholas Zabaras , Daniel M. Tartakovsky

Motor Imagery (MI) Electroencephalography (EEG) signals contain two crucial and complementary types of information: state information, which captures the global context of the task, and flow information, which captures fine-grained temporal…

人机交互 · 计算机科学 2026-04-10 Guoqing Cai , Shoulin Huang , Ting Ma

Autoencoders and generative neural network models have recently gained popularity in fluid mechanics due to their spontaneity and low processing time instead of high fidelity CFD simulations. Auto encoders are used as model order reduction…

流体动力学 · 物理学 2022-03-04 Kanishk , Tanishk Nandal , Prince Tyagi , Raj Kumar Singh

Liquid dropout and retention in gas-condensate reservoirs, specially in the near wellbore region, obstruct gas flowing paths and impact negatively the produced fluid volume and composition. Yet, condensate banking forecasting is commonly…

流体动力学 · 物理学 2020-11-18 Paula Reis , Marcio Carvalho

Understanding the process of multiphase fluid flow through porous media is crucial for many climate change mitigation technologies, including CO$_2$ geological storage, hydrogen storage, and fuel cells. However, current numerical models are…

流体动力学 · 物理学 2024-11-22 Yuxuan Gu , Catherine Spurin , Gege Wen

Neuro-inspired recurrent neural network algorithms, such as echo state networks, are computationally lightweight and thereby map well onto untethered devices. The baseline echo state network algorithms are shown to be efficient in solving…

机器学习 · 计算机科学 2019-03-27 Zachariah Carmichael , Humza Syed , Stuart Burtner , Dhireesha Kudithipudi

Physics-based models often involve large systems of parametrized partial differential equations, where design parameters control various properties. However, high-fidelity simulations of such systems on large domains or with high grid…

计算物理 · 物理学 2025-05-15 Diba Behnoudfar

A physics-informed convolutional neural network is proposed to simulate two phase flow in porous media with time-varying well controls. While most of PICNNs in existing literatures worked on parameter-to-state mapping, our proposed network…

机器学习 · 计算机科学 2024-10-24 Jungang Chen , Eduardo Gildin , John E. Killough

The continuum approach employing porous media models is a robust and efficient solution method in the area of the simulation of fixed-bed reactors. This paper applies the double-averaging methodology to refine the continuum approach,…

流体动力学 · 物理学 2023-05-11 W. Sadowski , M. Sayyari , F. di Mare , H. Marschall

We propose a deep probabilistic-neural-network architecture for learning a minimal and near-orthogonal set of non-linear modes from high-fidelity turbulent-flow-field data useful for flow analysis, reduced-order modeling, and flow control.…

流体动力学 · 物理学 2021-09-06 Hamidreza Eivazi , Soledad Le Clainche , Sergio Hoyas , Ricardo Vinuesa

Prediction of future states of the environment and interacting agents is a key competence required for autonomous agents to operate successfully in the real world. Prior work for structured sequence prediction based on latent variable…

计算机视觉与模式识别 · 计算机科学 2020-08-19 Apratim Bhattacharyya , Michael Hanselmann , Mario Fritz , Bernt Schiele , Christoph-Nikolas Straehle

Machine learning methods have shown promise in learning chaotic dynamical systems, enabling model-free short-term prediction and attractor reconstruction. However, when applied to large-scale, spatiotemporally chaotic systems, purely…

混沌动力学 · 物理学 2026-01-09 Kuei-Jan Chu , Nozomi Akashi , Akihiro Yamamoto

Fast and robust dynamic state estimation (DSE) is essential for accurately capturing the internal dynamic processes of power systems, and it serves as the foundation for reliably implementing real-time dynamic modeling, monitoring, and…

系统与控制 · 电气工程与系统科学 2025-01-07 Jianhua Pei , Ping Wang , Jingyu Wang , Dongyuan Shi

With their motion-responsive nature, event-based cameras offer significant advantages over traditional cameras for optical flow estimation. While deep learning has improved upon traditional methods, current neural networks adopted for…

计算机视觉与模式识别 · 计算机科学 2025-04-16 Gokul Raju Govinda Raju , Nikola Zubić , Marco Cannici , Davide Scaramuzza

We present DC-AE 1.5, a new family of deep compression autoencoders for high-resolution diffusion models. Increasing the autoencoder's latent channel number is a highly effective approach for improving its reconstruction quality. However,…

计算机视觉与模式识别 · 计算机科学 2025-08-04 Junyu Chen , Dongyun Zou , Wenkun He , Junsong Chen , Enze Xie , Song Han , Han Cai

A novel strategy is proposed to improve the accuracy of state estimation and reconstruction from low-fidelity models and sparse data from sensors. This strategy combines ensemble Data Assimilation (DA) and Machine Learning (ML) tools,…

流体动力学 · 物理学 2025-01-31 Miguel M. Valero , Marcello Meldi

Simulation of multiphase flow in porous media is crucial for the effective management of subsurface energy and environment related activities. The numerical simulators used for modeling such processes rely on spatial and temporal…

计算物理 · 物理学 2022-05-25 Bicheng Yan , Dylan Robert Harp , Rajesh J. Pawar

We present a simple model for the development of shear layers between parallel flows in confining channels. Such flows are important across a wide range of topics from diffusers, nozzles and ducts to urban air flow and geophysical fluid…

流体动力学 · 物理学 2018-04-09 GP Benham , AA Castrejon-Pita , IJ Hewitt , CP Please , RW Style , P Bird

Numerical modeling and simulation of two-phase flow in porous media is challenging due to the uncertainties in key parameters, such as permeability. To address these challenges, we propose a computational framework by utilizing the novel…

数值分析 · 数学 2025-05-13 Ruoyu Hu , Sanjeeb Poudel , Feng Bao , Sanghyun Lee

We present efficient deep learning techniques for approximating flow and transport equations for both single phase and two-phase flow problems. The proposed methods take advantages of the sparsity structures in the underlying discrete…

数值分析 · 数学 2020-01-08 Yating Wang , Guang Lin