arXiv subjects

Ali Kashefi

Publications and source records attributed to Ali Kashefi.

17 recordsLinked to original sources

arXiv2026

Flow Matching and Diffusion Models via PointNet for Generating Fluid Fields on Irregular Geometries

We present two novel generative geometric deep learning frameworks, termed Flow Matching PointNet and Diffusion PointNet, for predicting fluid flow variables on irregular geometries by incorporating PointNet into flow matching and diffusion models, respectively. In these frameworks, a reverse generative process reconstructs physical fields from standard Gaussian noise conditioned on unseen geometries. The proposed approaches operate directly on point-cloud representations of computational domains (e.g., grid vertices of finite-volume meshes) and therefore avoid the limitations of pixelation used to project geometries onto uniform lattices, as is common in U-Net-based flow matching and diffusion models. In contrast to graph neural network-based diffusion models, Flow Matching PointNet and Diffusion PointNet do not exhibit high-frequency noise artifacts in the predicted fields. Moreover, unlike such approaches, which require auxiliary intermediate networks to condition geometry, the proposed frameworks rely solely on PointNet, resulting in a simple and unified architecture. The performance of the proposed frameworks is evaluated on steady incompressible flow past a cylinder, using a geometric dataset constructed by varying the cylinder's cross-sectional shape and orientation across samples. The results demonstrate that Flow Matching PointNet and Diffusion PointNet achieve more accurate predictions of velocity and pressure fields, as well as lift and drag forces, and exhibit greater robustness to incomplete geometries compared to a vanilla PointNet with the same number of trainable parameters.

cs.CV↗

arXiv2025

Vision Mamba for Permeability Prediction of Porous Media

Vision Mamba has recently received attention as an alternative to Vision Transformers (ViTs) for image classification. The network size of Vision Mamba scales linearly with input image resolution, whereas ViTs scale quadratically, a feature that improves computational and memory efficiency. Moreover, Vision Mamba requires a significantly smaller number of trainable parameters than traditional convolutional neural networks (CNNs), and thus, they can be more memory efficient. Because of these features, we introduce, for the first time, a neural network that uses Vision Mamba as its backbone for predicting the permeability of three-dimensional porous media. We compare the performance of Vision Mamba with ViT and CNN models across multiple aspects of permeability prediction and perform an ablation study to assess the effects of its components on accuracy. We demonstrate in practice the aforementioned advantages of Vision Mamba over ViTs and CNNs in the permeability prediction of three-dimensional porous media. We make the source code publicly available to facilitate reproducibility and to enable other researchers to build on and extend this work. We believe the proposed framework has the potential to be integrated into large vision models in which Vision Mamba is used instead of ViTs.

cs.CV↗

arXiv2025

Physics-informed KAN PointNet: Deep learning for simultaneous solutions to inverse problems in incompressible flow on numerous irregular geometries

Kolmogorov-Arnold Networks (KANs) have gained attention as an alternative to traditional multilayer perceptrons (MLPs) for deep learning applications in computational physics, particularly for solving inverse problems with sparse data, as exemplified by the physics-informed Kolmogorov-Arnold network (PIKAN). However, the capability of KANs to simultaneously solve inverse problems over multiple irregular geometries within a single training run remains unexplored. To address this gap, we introduce the physics-informed Kolmogorov-Arnold PointNet (PI-KAN-PointNet), in which shared KANs are integrated into the PointNet architecture to capture the geometric features of computational domains. The loss function comprises the squared residuals of the governing equations, computed via automatic differentiation, along with sparse observations and partially known boundary conditions. We construct shared KANs using Jacobi polynomials and investigate their performance by considering Jacobi polynomials of different degrees and types in terms of both computational cost and prediction accuracy. As a benchmark test case, we consider natural convection in a square enclosure with a cylinder, where the cylinder's shape varies across a dataset of 135 geometries. PI-KAN-PointNet offers two main advantages. First, it overcomes the limitation of current PIKANs, which are restricted to solving only a single computational domain per training run, thereby reducing computational costs. Second, when comparing the performance of PI-KAN-PointNet with that of the physics-informed PointNet using MLPs, we observe that, with approximately the same number of trainable parameters and comparable computational cost in terms of the number of epochs, training time per epoch, and memory usage, PI-KAN-PointNet yields more accurate predictions, particularly for values on unknown boundary conditions involving nonsmooth geometries.

cs.LG↗

arXiv2024

PointNet with KAN versus PointNet with MLP for 3D Classification and Segmentation of Point Sets

Kolmogorov-Arnold Networks (KANs) have recently gained attention as an alternative to traditional Multilayer Perceptrons (MLPs) in deep learning frameworks. KANs have been integrated into various deep learning architectures such as convolutional neural networks, graph neural networks, and transformers, with their performance evaluated. However, their effectiveness within point-cloud-based neural networks remains unexplored. To address this gap, we incorporate KANs into PointNet for the first time to evaluate their performance on 3D point cloud classification and segmentation tasks. Specifically, we introduce PointNet-KAN, built upon two key components. First, it employs KANs instead of traditional MLPs. Second, it retains the core principle of PointNet by using shared KAN layers and applying symmetric functions for global feature extraction, ensuring permutation invariance with respect to the input features. In traditional MLPs, the goal is to train the weights and biases with fixed activation functions; however, in KANs, the goal is to train the activation functions themselves. We use Jacobi polynomials to construct the KAN layers. We extensively and systematically evaluate PointNet-KAN across various polynomial degrees and special types such as the Lagrange, Chebyshev, and Gegenbauer polynomials. Our results show that PointNet-KAN achieves competitive performance compared to PointNet with MLPs on benchmark datasets for 3D object classification and part and semantic segmentation, despite employing a shallower and simpler network architecture. We also study a hybrid PointNet model incorporating both KAN and MLP layers. We hope this work serves as a foundation and provides guidance for integrating KANs, as an alternative to MLPs, into more advanced point cloud processing architectures.

cs.CV↗

arXiv2024

Kolmogorov-Arnold PointNet: Deep learning for prediction of fluid fields on irregular geometries

Kolmogorov-Arnold Networks (KANs) have emerged as a promising alternative to traditional Multilayer Perceptrons (MLPs) in deep learning. KANs have already been integrated into various architectures, such as convolutional neural networks, graph neural networks, and transformers, and their potential has been assessed for predicting physical quantities. However, the combination of KANs with point-cloud-based neural networks (e.g., PointNet) for computational physics has not yet been explored. To address this, we present Kolmogorov-Arnold PointNet (KA-PointNet) as a novel supervised deep learning framework for the prediction of incompressible steady-state fluid flow fields in irregular domains, where the predicted fields are a function of the geometry of the domains. In KA-PointNet, we implement shared KANs in the segmentation branch of the PointNet architecture. We utilize Jacobi polynomials to construct shared KANs. As a benchmark test case, we consider incompressible laminar steady-state flow over a cylinder, where the geometry of its cross-section varies over the data set. We investigate the performance of Jacobi polynomials with different degrees as well as special cases of Jacobi polynomials such as Legendre polynomials, Chebyshev polynomials of the first and second kinds, and Gegenbauer polynomials, in terms of the computational cost of training and accuracy of prediction of the test set. Additionally, we compare the performance of PointNet with shared KANs (i.e., KA-PointNet) and PointNet with shared MLPs. It is observed that when the number of trainable parameters is approximately equal, PointNet with shared KANs (i.e., KA-PointNet) outperforms PointNet with shared MLPs. Moreover, KA-PointNet predicts the pressure and velocity distributions along the surface of cylinders more accurately, resulting in more precise computations of lift and drag.

cs.LG↗

arXiv2024

A Misleading Gallery of Fluid Motion by Generative Artificial Intelligence

In this technical report, we extensively investigate the accuracy of outputs from well-known generative artificial intelligence (AI) applications in response to prompts describing common fluid motion phenomena familiar to the fluid mechanics community. We examine a range of applications, including Midjourney, Dall-E, Runway ML, Microsoft Designer, Gemini, Meta AI, and Leonardo AI, introduced by prominent companies such as Google, OpenAI, Meta, and Microsoft. Our text prompts for generating images or videos include examples such as "Von Karman vortex street", "flow past an airfoil", "Kelvin-Helmholtz instability", "shock waves on a sharp-nosed supersonic body", etc. We compare the images generated by these applications with real images from laboratory experiments and numerical software. Our findings indicate that these generative AI models are not adequately trained in fluid dynamics imagery, leading to potentially misleading outputs. Beyond text-to-image/video generation, we further explore the transition from image/video to text generation using these AI tools, aiming to investigate the accuracy of their descriptions of fluid motion phenomena. This report serves as a cautionary note for educators in academic institutions, highlighting the potential for these tools to mislead students. It also aims to inform researchers at these renowned companies, encouraging them to address this issue. We conjecture that a primary reason for this shortcoming is the limited access to copyright-protected fluid motion images from scientific journals.

physics.flu-dyn↗

arXiv2024

A novel Fourier neural operator framework for classification of multi-sized images: Application to three dimensional digital porous media

Fourier neural operators (FNOs) are invariant with respect to the size of input images, and thus images with any size can be fed into FNO-based frameworks without any modification of network architectures, in contrast to traditional convolutional neural networks (CNNs). Leveraging the advantage of FNOs, we propose a novel deep-learning framework for classifying images with varying sizes. Particularly, we simultaneously train the proposed network on multi-sized images. As a practical application, we consider the problem of predicting the label (e.g., permeability) of three-dimensional digital porous media. To construct the framework, an intuitive approach is to connect FNO layers to a classifier using adaptive max pooling. First, we show that this approach is only effective for porous media with fixed sizes, whereas it fails for porous media of varying sizes. To overcome this limitation, we introduce our approach: instead of using adaptive max pooling, we use static max pooling with the size of channel width of FNO layers. Since the channel width of the FNO layers is independent of input image size, the introduced framework can handle multi-sized images during training. We show the effectiveness of the introduced framework and compare its performance with the intuitive approach through the example of the classification of three-dimensional digital porous media of varying sizes.

cs.CV↗

arXiv2023

Physics-informed PointNet: On how many irregular geometries can it solve an inverse problem simultaneously? Application to linear elasticity

Regular physics-informed neural networks (PINNs) predict the solution of partial differential equations using sparse labeled data but only over a single domain. On the other hand, fully supervised learning models are first trained usually over a few thousand domains with known solutions (i.e., labeled data) and then predict the solution over a few hundred unseen domains. Physics-informed PointNet (PIPN) is primarily designed to fill this gap between PINNs (as weakly supervised learning models) and fully supervised learning models. In this article, we demonstrate that PIPN predicts the solution of desired partial differential equations over a few hundred domains simultaneously, while it only uses sparse labeled data. This framework benefits fast geometric designs in the industry when only sparse labeled data are available. Particularly, we show that PIPN predicts the solution of a plane stress problem over more than 500 domains with different geometries, simultaneously. Moreover, we pioneer implementing the concept of remarkable batch size (i.e., the number of geometries fed into PIPN at each sub-epoch) into PIPN. Specifically, we try batch sizes of 7, 14, 19, 38, 76, and 133. Additionally, the effect of the PIPN size, symmetric function in the PIPN architecture, and static and dynamic weights for the component of the sparse labeled data in the loss function are investigated.

cs.LG↗

arXiv2023

Prediction of fluid flow in porous media by sparse observations and physics-informed PointNet

We predict steady-state Stokes flow of fluids within porous media at pore scales using sparse point observations and a novel class of physics-informed neural networks, called "physics-informed PointNet" (PIPN). Taking the advantages of PIPN into account, three new features become available compared to physics-informed convolutional neural networks for porous medium applications. First, the input of PIPN is exclusively the pore spaces of porous media (rather than both the pore and grain spaces). This feature diminishes required computer memory. Second, PIPN represents the boundary of pore spaces smoothly and realistically (rather than pixel-wise representations). Third, spatial resolution can vary over the physical domain (rather than equally spaced resolutions). This feature enables users to reach an optimal resolution with a minimum computational cost. The performance of our framework is evaluated by the study of the influence of noisy sensor data, pressure observations, and spatial correlation length.

physics.flu-dyn↗

arXiv2023

ChatGPT for Programming Numerical Methods

ChatGPT is a large language model recently released by the OpenAI company. In this technical report, we explore for the first time the capability of ChatGPT for programming numerical algorithms. Specifically, we examine the capability of GhatGPT for generating codes for numerical algorithms in different programming languages, for debugging and improving written codes by users, for completing missed parts of numerical codes, rewriting available codes in other programming languages, and for parallelizing serial codes. Additionally, we assess if ChatGPT can recognize if given codes are written by humans or machines. To reach this goal, we consider a variety of mathematical problems such as the Poisson equation, the diffusion equation, the incompressible Navier-Stokes equations, compressible inviscid flow, eigenvalue problems, solving linear systems of equations, storing sparse matrices, etc. Furthermore, we exemplify scientific machine learning such as physics-informed neural networks and convolutional neural networks with applications to computational physics. Through these examples, we investigate the successes, failures, and challenges of ChatGPT. Examples of failures are producing singular matrices, operations on arrays with incompatible sizes, programming interruption for relatively long codes, etc. Our outcomes suggest that ChatGPT can successfully program numerical algorithms in different programming languages, but certain limitations and challenges exist that require further improvement of this machine learning model.

cs.LG↗

arXiv2022

Physics-informed PointNet: A deep learning solver for steady-state incompressible flows and thermal fields on multiple sets of irregular geometries

We present a novel physics-informed deep learning framework for solving steady-state incompressible flow on multiple sets of irregular geometries by incorporating two main elements: using a point-cloud based neural network to capture geometric features of computational domains, and using the mean squared residuals of the governing partial differential equations, boundary conditions, and sparse observations as the loss function of the network to capture the physics. While the solution of the continuity and Navier-Stokes equations is a function of the geometry of the computational domain, current versions of physics-informed neural networks have no mechanism to express this functionally in their outputs, and thus are restricted to obtain the solutions only for one computational domain with each training procedure. Using the proposed framework, three new facilities become available. First, the governing equations are solvable on a set of computational domains containing irregular geometries with high variations with respect to each other but requiring training only once. Second, after training the introduced framework on the set, it is now able to predict the solutions on domains with unseen geometries from seen and unseen categories as well. The former and the latter both lead to savings in computational costs. Finally, all the advantages of the point-cloud based neural network for irregular geometries, already used for supervised learning, are transferred to the proposed physics-informed framework. The effectiveness of our framework is shown through the method of manufactured solutions and thermally-driven flow for forward and inverse problems.

physics.flu-dyn↗

arXiv2021

A Point-Cloud Deep Learning Framework for Prediction of Fluid Flow Fields on Irregular Geometries

We present a novel deep learning framework for flow field predictions in irregular domains when the solution is a function of the geometry of either the domain or objects inside the domain. Grid vertices in a computational fluid dynamics (CFD) domain are viewed as point clouds and used as inputs to a neural network based on the PointNet architecture, which learns an end-to-end mapping between spatial positions and CFD quantities. Using our approach, (i) the network inherits desirable features of unstructured meshes (e.g., fine and coarse point spacing near the object surface and in the far field, respectively), which minimizes network training cost; (ii) object geometry is accurately represented through vertices located on object boundaries, which maintains boundary smoothness and allows the network to detect small changes between geometries; and (iii) no data interpolation is utilized for creating training data; thus accuracy of the CFD data is preserved. None of these features are achievable by extant methods based on projecting scattered CFD data into Cartesian grids and then using regular convolutional neural networks. Incompressible laminar steady flow past a cylinder with various shapes for its cross section is considered. The mass and momentum of predicted fields are conserved. We test the generalizability of our network by predicting the flow around multiple objects as well as an airfoil, even though only single objects and no airfoils are observed during training. The network predicts the flow fields hundreds of times faster than our conventional CFD solver, while maintaining excellent to reasonable accuracy.

cs.LG↗

arXiv2021

Point-Cloud Deep Learning of Porous Media for Permeability Prediction

We propose a novel deep learning framework for predicting permeability of porous media from their digital images. Unlike convolutional neural networks, instead of feeding the whole image volume as inputs to the network, we model the boundary between solid matrix and pore spaces as point clouds and feed them as inputs to a neural network based on the PointNet architecture. This approach overcomes the challenge of memory restriction of graphics processing units and its consequences on the choice of batch size, and convergence. Compared to convolutional neural networks, the proposed deep learning methodology provides freedom to select larger batch sizes, due to reducing significantly the size of network inputs. Specifically, we use the classification branch of PointNet and adjust it for a regression task. As a test case, two and three dimensional synthetic digital rock images are considered. We investigate the effect of different components of our neural network on its performance. We compare our deep learning strategy with a convolutional neural network from various perspectives, specifically for maximum possible batch size. We inspect the generalizability of our network by predicting the permeability of real-world rock samples as well as synthetic digital rocks that are statistically different from the samples used during training. The network predicts the permeability of digital rocks a few thousand times faster than a Lattice Boltzmann solver with a high level of prediction accuracy.

eess.IV↗

arXiv2020

A coarse-grid projection method for accelerating incompressible MHD flow simulations

Coarse grid projection (CGP) is a multiresolution technique for accelerating numerical calculations associated with a set of nonlinear evolutionary equations along with the stiff Poisson equations. In this article we use CGP for the first time to speed up incompressible magnetohydrodynamics (MHD) flow simulations. Accordingly, we solve the nonlinear advection-diffusion equation on a fine mesh, while we execute the electric potential Poisson equation on the corresponding coarsened mesh. Mapping operators connect two grids together. A pressure correction scheme is used to enforce the incompressibility constrain. The study of incompressible flow past a circular cylinder in the presence of Lorentz force is selected as a benchmark problem with a fixed Reynolds number but various Stuart numbers. We consider two different situations. First, we only apply CGP to the electric potential Poisson equation. Second, we apply CGP to the pressure Poisson equation as well. The maximum speedup factors achieved here are approximately 3 and 23 respectively for the first and second situations. For the both situations we examine the accuracy of velocity and vorticity fields as well as the lift and drag coefficients. In general, the results obtained by CGP are in an excellent to reasonable range of accuracy and are significantly consistently more accurate than when we use coarse grids for the discretization of both the advection-diffusion and electric potential Poisson equations.

physics.comp-ph↗

arXiv2020

Spring-Slider and Finite Element Modeling of Microseismic Events and Fault Slip during Hydraulic Fracturing

Hydraulic fracturing increases reservoir permeability by opening fractures and triggering slip on natural fractures and faults. While seismic slip of small faults or fault patches is detectable as microseismic events, the role of aseismic slip is poorly understood. From a modeling standpoint, geomechanical analysis using the Coulomb criterion can determine if faults slip but not whether slip is seismic or aseismic. Here we propose a computational methodology to predict fault slip, and whether slip is seismic or aseismic, using rate-and-state friction. To avoid computational costs associated with resolving small faults, we use the spring-slider idealization that treats faults as points. Interaction between faults is neglected. The method is applied to study fault slip from a hydraulic fracture that grows past a fault, without intersecting it. We represent the hydraulic fracture stressing using an asymptotic expansion of stresses around the tip of a tensile crack. We investigate the effect of fault length, orientation, and distance from the hydraulic fracture. For velocity-weakening faults with stiffness smaller than a critical stiffness, slip is seismic, whereas faults with stiffness greater than the critical stiffness slip aseismically. Furthermore, we compare the spring-slider idealization with a finite element analysis that resolves spatially variable slip. The spring-slider idealization provides reasonably accurate predictions of moment and even moment-rate history, especially for faults having stiffness close to or larger than the critical stiffness. Differences appear for large faults where rupture propagation is important, though differences might still be negligible for many applications.

physics.geo-ph↗

arXiv2019

A coarse grid projection method for accelerating heat transfer computations

Coarse Grid Projection (CGP) methodology is used to accelerate the computations of sets of decoupled nonlinear evolutionary and linear static equations. In CGP, the linear equations are solved on a coarsened mesh compared to the nonlinear equations, leading to a reduction in central processing unit (CPU) time. The accuracy of the CGP scheme has been assessed for the advection-diffusion equation along with the pressure Poisson equation. Here we add another decoupled equation to this set: the energy equation. In this article, we examine the influence of CGP methodology for the first time on thermal fields. To this purpose, a semi-implicit-time-integration unstructured-triangular-finite-element CGP version is selected. The CGP platform is validated with two different test cases: first, natural convection induced by a hot circular cylinder located in the center of a cold square cylinder, and second, the flow over a circular cylinder with the condition of constant cylinder temperature. Regarding the first test case, the CGP and non-CGP simulations are carried out for different Rayleigh numbers. The velocity and temperature fields as well as the local Nusselt number on the surface of the inner hot cylinder calculated by CGP reveal good agreement with the non-CGP data. Concerning the second test case, the temperature variable is used as the passive scalar. For different Prandtl numbers, we compare the CGP and non-CGP configurations according to the Nusselt number and the spatial structure of the scalar field obtained. The phase lag between the standard and CGP approaches is transmitted from the velocity field into the temperature filed, and thus into the local transient Nusselt number. For one and two levels of coarsening, the numerical predictions by CGP for the unsteady local heat transfer coefficients agree well with available data in the literature.

physics.comp-ph↗

arXiv2018

Coarse grid projection methodology: A partial mesh refinement tool for incompressible flow simulations

We discuss Coarse Grid Projection (CGP) methodology as a guide for partial mesh refinement of incompressible flow computations for the first time. Based on it, if for a given spatial resolution the numerical simulation diverges or the velocity outputs are not accurate enough, instead of refining both the advection-diffusion and the Poisson grids, the CGP mesh refinement suggests to only refine the advection-diffusion grid and keep the Poisson grid resolution unchanged. The application of the novel mesh refinement tool is shown in the cases of flow over a backward-facing step and flow past a cylinder. For the backward facing step flow, a three-level partial mesh refinement makes a previously diverging computation numerically stable. For the flow past a cylinder, the error of the viscous lift force is reduced from 31.501% to 7.191% (with reference to the standard mesh refinement results) by the one-level partial mesh refinement technique.

physics.comp-ph↗