检索结果-内蒙古大学图书馆

DEEP LEARNING OF FREE BOUNDARY AND STEFAN PROBLEMS

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wang, Sifan Perdikaris, Paris Graduate Group in Applied Mathematics and Computational Science University of Pennsylvania PhiladelphiaPA19104 United States Department of Mechanichal Engineering and Applied Mechanics University of Pennsylvania PhiladelphiaPA19104 United States

Free boundary problems appear naturally in numerous areas of mathematics, science and engineering. These problems present a great computational challenge because they necessitate numerical methods that can yield an accurate approximation of free boundaries and complex dynamic interfaces. In this work, we propose a multi-network model based on physics-informed neural networks to tackle a general class of forward and inverse free boundary problems called Stefan problems. Specifically, we approximate the unknown solution as well as any moving boundaries by two deep neural networks. Besides, we formulate a new type of inverse Stefan problems that aim to reconstruct the solution and free boundaries directly from sparse and noisy measurements. We demonstrate the effectiveness of our approach in a series of benchmarks spanning different types of Stefan problems, and illustrate how the proposed framework can accurately recover solutions of partial differential equations with moving boundaries and dynamic interfaces. All code and data accompanying this manuscript are publicly available at https://***/PredictiveIntelligenceLab/DeepStefan. Copyright © 2020, The Authors. All rights reserved.

关键词： Numerical methods

On the eigenvector bias of Fourier feature networks: From regression to solving multi-scale PDEs with physics-informed neural networks

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wang, Sifan Wang, Hanwen Perdikaris, Paris Graduate Group in Applied Mathematics and Computational Science University of Pennsylvania PhiladelphiaPA19104 United States Department of Mechanichal Engineering and Applied Mechanics University of Pennsylvania PhiladelphiaPA19104 United States

Physics-informed neural networks (PINNs) are demonstrating remarkable promise in integrating physical models with gappy and noisy observational data, but they still struggle in cases where the target functions to be approximated exhibit high-frequency or multi-scale features. In this work we investigate this limitation through the lens of Neural Tangent Kernel (NTK) theory and elucidate how PINNs are biased towards learning functions along the dominant eigen-directions of their limiting NTK. Using this observation, we construct novel architectures that employ spatio-temporal and multi-scale random Fourier features, and justify how such coordinate embedding layers can lead to robust and accurate PINN models. Numerical examples are presented for several challenging cases where conventional PINN models fail, including wave propagation and reaction-diffusion dynamics, illustrating how the proposed methods can be used to effectively tackle both forward and inverse problems involving partial differential equations with multi-scale behavior. All code an data accompanying this manuscript will be made publicly available at https://***/PredictiveIntelligenceLab/MultiscalePINNs. Copyright © 2020, The Authors. All rights reserved.

关键词： Partial differential equations

Threshold and decay properties of transient isolated turbulent band in plane Couette flow

学校读者我要写书评

暂无评论

applied mathematics and Mechanics(English Edition) 2019年第10期40卷 1449-1456页

作者： Jianzhou LU Jianjun TAO Weitao ZHOU Xiangming XIONG CAPT-HEDPS SKLTCS Collaborative Innovation Center of IFSA Department of Mechanics and Engineering Science College of Engineering Peking University Beijing 100871 China The Program in Applied and Computational Mathematics Princeton University Princeton NJ 08544 U. S.A.

By direct numerical simulations of the plane Couette flow (PCF) in a large computational domain, it is shown that an isolated turbulent band decays monotonically at low Reynolds numbers but experiences transient growth before the eventual relaminarization at moderate Reynolds numbers. The lower bound Reynolds number of the transient-growth regime is determined as 286. The width, length, and tilt angle of the iso- lated band structure are defined based on the disturbance kinetic energy in the mid-plane, and the geometric characteristics of the band can be described with a tilted rectangle. It is illustrated that before its eventual fragmentation, the isolated turbulent band decays in a style of longitudinal contraction, where the center, width, and tilt angle of the band keep almost constant but the band length contracts with a statistically constant velocity.

关键词： plane Couette flow (PCF) subcritical transition turbulent band

More Optimal Fractional-Order Stochastic Gradient Descent for Non-Convex Optimization Problems

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Partohaghighi, Mohammad Marcia, Roummel Chen, YangQuan Electrical Engineering and Computer Science Graduate Program University of California Merced United States Department of Applied Mathematics University of California Merced MercedCA United States Lab Department of Mechanical Engineering School of Engineering University of California MercedCA95343 United States

Fractional-order stochastic gradient descent (FOSGD) leverages fractional exponents to capture long-memory effects in optimization. However, its utility is often limited by the difficulty of tuning and stabilizing these exponents. We propose 2SED Fractional-Order Stochastic Gradient Descent (2SEDFOSGD), which integrates the Two-Scale Effective Dimension (2SED) algorithm with FOSGD to adapt the fractional exponent in a data-driven manner. By tracking model sensitivity and effective dimensionality, 2SEDFOSGD dynamically modulates the exponent to mitigate oscillations and hasten convergence. Theoretically, for onoconvex optimization problems, this approach preserves the advantages of fractional memory without the sluggish or unstable behavior observed in naïve fractional SGD. Empirical evaluations in Gaussian and α-stable noise scenarios using an autoregressive (AR) model highlight faster convergence and more robust parameter estimates compared to baseline methods, underscoring the potential of dimension-aware fractional techniques for advanced modeling and estimation tasks. © 2025, CC BY.

关键词： Convex optimization

computational Design of Anisotropic Stealthy Hyperuniform Composites with Engineered Directional Scattering Properties

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Shi, Wenlong Keeney, David Chen, Duyu Jiao, Yang Torquato, Salvatore Materials Science and Engineering Arizona State University TempeAZ85287 United States Materials Research Laboratory University of California Santa BarbaraCA93106 United States Department of Physics Arizona State University TempeAZ85287 United States Department of Chemistry Princeton University PrincetonNJ08544 United States Department of Physics Princeton University PrincetonNJ08544 United States Princeton Institute of Materials Princeton University PrincetonNJ08544 United States Program in Applied and Computational Mathematics Princeton University PrincetonNJ08544 United States

Disordered hyperuniform materials are an emerging class of exotic amorphous states of matter that endow them with singular physical properties, including large isotropic photonic band gaps, superior resistance to fracture, and nearly optimal electrical and thermal transport properties, to name but a few. Here, we generalize the Fourier-space based numerical construction procedure for designing and generating digital realizations of isotropic disordered hyperuniform two-phase heterogeneous materials (i.e., composites) developed by Chen and Torquato [Acta Mater. 142, 152 (2018)] to anisotropic microstructures with targeted spectral densities. Our generalized construction procedure explicitly incorporates the vector-dependent spectral density function χ˜V (k) of arbitrary form that is realizable. We demonstrate the utility of the procedure by generating a wide spectrum of anisotropic stealthy hyperuniform (SHU) microstructures with χ˜V (k) = 0 for k ∈ Ω, i.e., complete suppression of scattering in an "exclusion" region Ω around the origin in the Fourier space. We show how different exclusion-region shapes with various discrete symmetries, including circular-disk, elliptical-disk, square, rectangular, butterfly-shaped and lemniscate-shaped regions of varying size, affect the resulting statistically anisotropic microstructures as a function of the and phase volume fraction. The latter two cases of Ω lead to directionally hyperuniform composites, which are stealthy hyperuniform only along certain directions, and are non-hyperuniform along others. We find that, while the circular-disk exclusion regions give rise to isotropic hyperuniform composite microstructures, the directional hyperuniform behaviors imposed by the shape asymmetry (or anisotropy) of certain exclusion regions give rise to distinct anisotropic structures and degree of uniformity in the distribution of the phases on intermediate and large length scales along different directions. Moreover, while the anisotr

关键词： Volume fraction

Measuring the Substructure Mass Power Spectrum of 23 SLACS Strong Galaxy-Galaxy Lenses with Convolutional Neural Networks

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Fagin, Joshua Vernardos, Georgios Tsagkatakis, Grigorios Pantazis, Yannis Shajib, Anowar J. O’Dowd, Matthew The Graduate Center The City University of New York 365 Fifth Avenue New YorkNY10016 United States Department of Astrophysics American Museum of Natural History Central Park West and 79th Street NY10024-5192 United States Department of Physics and Astronomy Lehman College The CUNY BronxNY10468 United States Institute of Computer Science FORTH HeraklionGR-70013 Greece Institute of Applied and Computational Mathematics FORTH HeraklionGR-70013 Greece Department of Astronomy & Astrophysics University of Chicago ChicagoIL606374 United States Kavli Institute for Cosmological Physics University of Chicago ChicagoIL60637 United States

Strong gravitational lensing can be used as a tool for constraining the substructure in the mass distribution of galaxies. In this study we investigate the power spectrum of dark matter perturbations in a population of 23 Hubble Space Telescope images of strong galaxy-galaxy lenses selected from The Sloan Lens ACS (SLACS) survey. We model the dark matter substructure as a Gaussian Random Field perturbation on a smooth lens mass potential, characterized by power-law statistics. We expand upon the previously developed machine learning framework to predict the power-law statistics by using a convolutional neural network (CNN) that accounts for both epistemic and aleatoric uncertainties. For the training sets, we use the smooth lens mass potentials and reconstructed source galaxies that have been previously modelled through traditional fits of analytical and shapelet profiles as a starting point. We train three CNNs with different training set: the first using standard data augmentation on the best-fitting reconstructed sources, the second using different reconstructed sources spaced throughout the posterior distribution, and the third using a combination of the two data sets. We apply the trained CNNs to the SLACS data and find agreement in their predictions. Our results suggest a significant substructure perturbation favoring a high frequency power spectrum across our lens population. © 2024, CC BY.

关键词： Convolutional neural networks

Inventory of fungi from termite nests at Gunung Leuser National Park, northern Sumatra 2

学校读者我要写书评

暂无评论

Inventory of fungi from termite nests at Gunung Leuser Natio...

2nd International Conference on Agriculture and Bioindustry, ICAGRI 2020

作者： Hanum, S. Fitri, L. Lisa, O. Samingan, S. Alfizar, A. Sutekad, D. Novita, N. Muarrif, S. Syaukani, S. Master Program in Biological Science Faculty of Mathematic and Natural Sciences Universitas Syiah Kuala Darussalam Banda Aceh23111 Indonesia Biology Department Faculty of Mathematic and Natural Sciences Universitas Syiah Kuala Darussalam Banda Aceh23111 Indonesia Faculty of Teacher Training and Education Universitas Syiah Kuala Darussalam Banda Aceh23111 Indonesia Plant Protection Department Faculty of Agriculture Universitas Syiah Kuala Darussalam Banda Aceh23111 Indonesia Graduate School of Mathematics and Applied Science Universitas Syiah Kuala Darussalam Banda Aceh23111 Indonesia

Fungi and termite coexisted each other and have diverse symbiotic relationship in tropical forest. This research aims to determine the fungus found on termite nests in Suaq Balimbing Research Station so it can be used that as initial information in developing environmentally friendly termite control. The method used for collecting samples of fungus is a Standarized Sampling Protocol and for identification used slide culture method. The results showed that 5 of 12 termites nest are invaded by fungi. Based on macroscopic and microscopic observation, fungus species that obtained from termite nests are 2 species, namely: Penicillium sp.1, Trichoderma sp. 1 © Published under licence by IOP Publishing Ltd.

关键词： Fungi

DeePN2: A deep learning-based non-Newtonian hydrodynamic model

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Fang, Lidong Ge, Pei Zhang, Lei Weinan, E. Lei, Huan Department of Computational Mathematics Science and Engineering Michigan State University MI48824 United States School of Mathematical Sciences Institute of Natural Sciences and MOE-LSC Shanghai Jiao Tong University 800 Dongchuan Road Shanghai200240 China Center for Machine Learning Research School of Mathematical Sciences Peking University Beijing100871 China AI for Science Institute Beijing100080 China Department of Mathematics and Program in Applied and Computational Mathematics Princeton University NJ08544 United States Department of Statistics and Probability Michigan State University MI48824 United States

A long standing problem in the modeling of non-Newtonian hydrodynamics of polymeric flows is the availability of reliable and interpretable hydrodynamic models that faithfully encode the underlying micro-scale polymer dynamics. The main complication arises from the long polymer relaxation time, the complex molecular structure and heterogeneous interaction. DeePN2, a deep learning-based non-Newtonian hydrodynamic model, has been proposed and has shown some success in systematically passing the micro-scale structural mechanics information to the macro-scale hydrodynamics for suspensions with simple polymer conformation and bond potential. The model retains a multi-scaled nature by mapping the polymer configurations into a set of symmetry-preserving macro-scale features. The extended constitutive laws for these macro-scale features can be directly learned from the kinetics of their micro-scale counterparts. In this paper, we develop DeePN2 using more complex micro-structural models. We show that DeePN2 can faithfully capture the broadly overlooked viscoelastic differences arising from the specific molecular structural mechanics without human intervention. © 2021, CC BY.

关键词： Non Newtonian flow

Isotope effects in molecular structures and electronic properties of liquid water via deep potential molecular dynamics based on the SCAN functional

学校读者我要写书评

暂无评论

Physical Review B 2020年第21期102卷 214113-214113页

作者： Jianhang Xu Chunyi Zhang Linfeng Zhang Mohan Chen Biswajit Santra Xifan Wu Department of Physics Temple University Philadelphia Pennsylvania 19122 USA Program in Applied and Computational Mathematics Princeton University Princeton New Jersey 08544 USA CAPT HEDPS College of Engineering Peking University Beijing 100871 China Institute for Computational Molecular Science Temple University Philadelphia Pennsylvania 19122 USA

Feynman path-integral deep potential molecular dynamics (PI-DPMD) calculations have been employed to study both light (H2O) and heavy water (D2O) within the isothermalisobaric ensemble. In particular, the deep neural network is trained based on ab initio data obtained from the strongly constrained and appropriately normed (SCAN) exchange-correlation functional. Because of the lighter mass of hydrogen than deuteron, the properties of light water are more influenced by nuclear quantum effect than those of heavy water. Clear isotope effects are observed and analyzed in terms of hydrogen-bond structure and electronic properties of water that are closely associated with experimental observables. The molecular structures of both liquid H2O and D2O agree well with the data extracted from scattering experiments. The delicate isotope effects on radial distribution functions and angular distribution functions are well reproduced as well. Our approach demonstrates that deep neural network combined with SCAN functional based ab initio molecular dynamics provides an accurate theoretical tool for modeling water and its isotope effects.

关键词： Atomic & molecular structure Electronic structure Isotope effect Water Ab initio calculations Density functional theory Machine learning Molecular dynamics Path-integral methods