physics.comp-ph

arXiv:2501.06300v1 Announce Type: new Abstract: We present a tensorization algorithm for constructing tensor train representations of functions, drawing on sketching and cross interpolation ideas. The method only requires black-box access to the target function and a small set of sample points defining the domain of interest. Thus, it is particularly well-suited for machine learning models, where the domain of interest is naturally defined by the training dataset. We show that this approach can be used to enhance the privacy and interpretability of neural network models. Specifically, we apply our decomposition to (i) obfuscate neural networks whose parameters encode patterns tied to the training data distribution, and (ii) estimate topological phases of matter that are easily accessible from the tensor train representation. Additionally, we show that this tensorization can serve as an efficient initialization method for optimizing tensor trains in general settings, and that, for model compression, our algorithm achieves a superior trade-off between memory and time complexity compared to conventional tensorization methods of neural networks.

arXiv:2404.19602v2 Announce Type: replace-cross Abstract: In this article, we investigate some issues related to the quantification of uncertainties associated with the electrical properties of graphene nanoribbons. The approach is suited to understand the effects of missing information linked to the difficulty of fixing some material parameters, such as the band gap, and the strength of the applied electric field. In particular, we focus on the extension of particle Galerkin methods for kinetic equations in the case of the semiclassical Boltzmann equation for charge transport in graphene nanoribbons with uncertainties. To this end, we develop an efficient particle scheme which allows us to parallelize the computation and then, after a suitable generalization of the scheme to the case of random inputs, we present a Galerkin reformulation of the particle dynamics, obtained by means of a generalized Polynomial Chaos approach, which allows the reconstruction of the kinetic distribution. As a consequence, the proposed particle-based scheme preserves the physical properties and the positivity of the distribution function also in the presence of a complex scattering in the transport equation of electrons. The impact of the uncertainty of the band gap and applied field on the electrical current is analysed.

arXiv:2501.07373v1 Announce Type: new Abstract: Accurate, interpretable, and real-time modeling of multi-body dynamical systems is essential for predicting behaviors and inferring physical properties in natural and engineered environments. Traditional physics-based models face scalability challenges and are computationally demanding, while data-driven approaches like Graph Neural Networks (GNNs) often lack physical consistency, interpretability, and generalization. In this paper, we propose Dynami-CAL GraphNet, a Physics-Informed Graph Neural Network that integrates the learning capabilities of GNNs with physics-based inductive biases to address these limitations. Dynami-CAL GraphNet enforces pairwise conservation of linear and angular momentum for interacting nodes using edge-local reference frames that are equivariant to rotational symmetries, invariant to translations, and equivariant to node permutations. This design ensures physically consistent predictions of node dynamics while offering interpretable, edge-wise linear and angular impulses resulting from pairwise interactions. Evaluated on a 3D granular system with inelastic collisions, Dynami-CAL GraphNet demonstrates stable error accumulation over extended rollouts, effective extrapolations to unseen configurations, and robust handling of heterogeneous interactions and external forces. Dynami-CAL GraphNet offers significant advantages in fields requiring accurate, interpretable, and real-time modeling of complex multi-body dynamical systems, such as robotics, aerospace engineering, and materials science. By providing physically consistent and scalable predictions that adhere to fundamental conservation laws, it enables the inference of forces and moments while efficiently handling heterogeneous interactions and external forces.

arXiv:2501.06933v1 Announce Type: new Abstract: We introduce Neural Discrete Equilibrium (NeurDE), a machine learning (ML) approach for long-term forecasting of flow phenomena that relies on a "lifting" of physical conservation laws into the framework of kinetic theory. The kinetic formulation provides an excellent structure for ML algorithms by separating nonlinear, non-local physics into a nonlinear but local relaxation to equilibrium and a linear non-local transport. This separation allows the ML to focus on the local nonlinear components while addressing the simpler linear transport with efficient classical numerical algorithms. To accomplish this, we design an operator network that maps macroscopic observables to equilibrium states in a manner that maximizes entropy, yielding expressive BGK-type collisions. By incorporating our surrogate equilibrium into the lattice Boltzmann (LB) algorithm, we achieve accurate flow forecasts for a wide range of challenging flows. We show that NeurDE enables accurate prediction of compressible flows, including supersonic flows, while tracking shocks over hundreds of time steps, using a small velocity lattice-a heretofore unattainable feat without expensive numerical root finding.

arXiv:2405.18874v2 Announce Type: replace-cross Abstract: The dot product attention mechanism, originally designed for natural language processing tasks, is a cornerstone of modern Transformers. It adeptly captures semantic relationships between word pairs in sentences by computing a similarity overlap between queries and keys. In this work, we explore the suitability of Transformers, focusing on their attention mechanisms, in the specific domain of the parametrization of variational wave functions to approximate ground states of quantum many-body spin Hamiltonians. Specifically, we perform numerical simulations on the two-dimensional $J_1$-$J_2$ Heisenberg model, a common benchmark in the field of quantum many-body systems on lattice. By comparing the performance of standard attention mechanisms with a simplified version that excludes queries and keys, relying solely on positions, we achieve competitive results while reducing computational cost and parameter usage. Furthermore, through the analysis of the attention maps generated by standard attention mechanisms, we show that the attention weights become effectively input-independent at the end of the optimization. We support the numerical results with analytical calculations, providing physical insights of why queries and keys should be, in principle, omitted from the attention mechanism when studying large systems.

arXiv:2501.06388v1 Announce Type: new Abstract: We present a realizability-preserving numerical method for solving a spectral two-moment model to simulate the transport of massless, neutral particles interacting with a steady background material moving with relativistic velocities. The model is obtained as the special relativistic limit of a four-momentum-conservative general relativistic two-moment model. Using a maximum-entropy closure, we solve for the Eulerian-frame energy and momentum. The proposed numerical method is designed to preserve moment realizability, which corresponds to moments defined by a nonnegative phase-space density. The realizability-preserving method is achieved with the following key components: (i) a discontinuous Galerkin (DG) phase-space discretization with specially constructed numerical fluxes in the spatial and energy dimensions; (ii) a strong stability-preserving implicit-explicit (IMEX) time-integration method; (iii) a realizability-preserving conserved to primitive moment solver; (iv) a realizability-preserving implicit collision solver; and (v) a realizability-enforcing limiter. Component (iii) is necessitated by the closure procedure, which closes higher order moments nonlinearly in terms of primitive moments. The nonlinear conserved to primitive and the implicit collision solves are formulated as fixed-point problems, which are solved with custom iterative solvers designed to preserve the realizability of each iterate. With a series of numerical tests, we demonstrate the accuracy and robustness of this DG-IMEX method.

arXiv:2402.10874v2 Announce Type: replace-cross Abstract: Despite extensive research on magnetic skyrmions and antiskyrmions, a significant challenge remains in crafting nontrivial high-order skyrmionic textures with varying, or even tailor-made, topologies. We address this challenge, by focusing on a construction pathway of skyrmionic metamaterials within a monolayer thin film and suggest several skyrmionic metamaterials that are surprisingly stable, i.e., long-lived, due to a self-stabilization mechanism. This makes these new textures promising for applications. Central to our approach is the concept of 'simulated controlled assembly', in short, a protocol inspired by 'click chemistry' that allows for positioning topological magnetic structures where one likes, and then allowing for energy minimization to elucidate the stability. Utilizing high-throughput atomistic-spin-dynamic simulations alongside state-of-the-art AI-driven tools, we have isolated skyrmions (topological charge Q=1), antiskyrmions (Q=-1), and skyrmionium (Q=0). These entities serve as foundational 'skyrmionic building blocks' to form the here reported intricate textures. In this work, two key contributions are introduced to the field of skyrmionic systems. First, we present a a novel combination of atomistic spin dynamics simulations and controlled assembly protocols for the stabilization and investigation of new topological magnets. Second, using the aforementioned methods we report on the discovery of skyrmionic metamaterials.

arXiv:2501.07547v1 Announce Type: new Abstract: We propose a high-order spacetime wavelet method for the solution of nonlinear partial differential equations with a user-prescribed accuracy. The technique utilizes wavelet theory with a priori error estimates to discretize the problem in both the spatial and temporal dimensions simultaneously. We also propose a novel wavelet-based recursive algorithm to reduce the system sensitivity stemming from steep initial and/or boundary conditions. The resulting nonlinear equations are solved using the Newton-Raphson method. We parallelize the construction of the tangent operator along with the solution of the system of algebraic equations. We perform rigorous verification studies using the nonlinear Burgers' equation. The application of the method is demonstrated solving Sod shock tube problem using the Navier-Stokes equations. The numerical results of the method reveal high-order convergence rates for the function as well as its spatial and temporal derivatives. We solve problems with steep gradients in both the spatial and temporal directions with a priori error estimates.

arXiv:2207.04443v3 Announce Type: replace Abstract: The finite element method offers attractive methods for the numerical solution of coupled field problems arising in sensors and actuator simulations of various physical domains, like electrodynamics, mechanics, and thermodynamics. With this application perspective and being open, accessible, and fast implementations are possible, openCFS was launched in 2020. It provides an open-source framework for implementing partial differential equations using the finite element method. In particular, the acoustic module is part of active development, including several key methods. These methods include the perfectly-matched layer technique, non-confirming interface formulations, Lagrangian basis function, Legendre basis functions, spectral element formulations, a nodal element type, edge-based element type (aeroacoustic post-processing), absorbing boundary conditions, frequency dependent-material for time-harmonic and time-dependent simulations. Time-dependent simulations, time-harmonic simulations, and eigenvalue simulations are supported. Several variants of acoustic equations are implemented, including the relevant source terms and wave operators for aeroacoustics. The package includes rotating domains and non-conforming interfaces for fan noise simulations. It also contains an API to the Python3 package pyCFS. This paper presents openCFS with a focus on the acoustic module.

arXiv:2409.12483v2 Announce Type: replace-cross Abstract: Numerical methods of the ADER family, in particular finite-element ADER-DG and finite-volume ADER-WENO methods, are among the most accurate numerical methods for solving quasilinear PDE systems. The internal structure of ADER-DG and ADER-WENO numerical methods contains a large number of basic linear algebra operations related to matrix multiplications. The main interface of software libraries for matrix multiplications for high-performance computing is BLAS. This paper presents an effective method for integration the standard functions of the BLAS interface into the implementation of these numerical methods. The calculated matrices are small matrices; at the same time, the proposed implementation makes it possible to effectively use existing JIT technologies. The proposed approach immediately operates on AoS, which makes it possible to efficiently calculate flux, source and non-conservative terms without need to carry out transposition. The obtained computational costs demonstrated that the effective implementation, based on the use of the JIT functions of the BLAS, outperformed both the implementation based on the general BLAS functions and the vanilla implementations by several orders of magnitude. At the same time, the complexity of developing an implementation based on the approach proposed in this work does not exceed the complexity of developing a vanilla implementation.

arXiv:2501.03383v1 Announce Type: cross Abstract: Increasing HPC cluster sizes and large-scale simulations that produce petabytes of data per run, create massive IO and storage challenges for analysis. Deep learning-based techniques, in particular, make use of these amounts of domain data to extract patterns that help build scientific understanding. Here, we demonstrate a streaming workflow in which simulation data is streamed directly to a machine-learning (ML) framework, circumventing the file system bottleneck. Data is transformed in transit, asynchronously to the simulation and the training of the model. With the presented workflow, data operations can be performed in common and easy-to-use programming languages, freeing the application user from adapting the application output routines. As a proof-of-concept we consider a GPU accelerated particle-in-cell (PIConGPU) simulation of the Kelvin- Helmholtz instability (KHI). We employ experience replay to avoid catastrophic forgetting in learning from this non-steady process in a continual manner. We detail challenges addressed while porting and scaling to Frontier exascale system.

arXiv:2311.10872v3 Announce Type: replace-cross Abstract: Since viscoelastic two-phase flows arise in various industrial and natural processes, developing accurate and efficient software for their detailed numerical simulation is a highly relevant and challenging research task. We present a geometrical unstructured Volume-of-Fluid (VOF) method for handling two-phase flows with viscoelastic liquid phase, where the latter is modeled via generic rate-type constitutive equations and a one-field description is derived by conditional volume averaging of the local instantaneous bulk equations and interface jump conditions. The method builds on the plicRDF-isoAdvector geometrical VOF solver that is extended and combined with the modular framework DeboRheo for viscoelastic computational fluid dynamics (CFD). A piecewise-linear geometrical interface reconstruction technique on general unstructured meshes is employed for discretizing the viscoelastic stresses across the fluid interface. DeboRheo facilitates a flexible combination of different rheological models with appropriate stabilization methods to address the high Weissenberg number problem.

arXiv:2501.01859v1 Announce Type: new Abstract: The modeling of deposition rates in Thermal Laser Epitaxy (TLE) is essential for the accurate prediction of the evaporation process and for improved dynamic process control. We demonstrate excellent agreement between experimental data and a model based on a finite element simulation that describes the temperature distribution of an elemental source when irradiated with continuous wave laser radiation. The simulation strongly depends on the thermophysical constants of the material, data of which is lacking for many elements. Effective values for the parameters may be determined with precision by means of an unambiguous reference provided by the melting point of the material, which is directly observed during the experiments. TLE may therefore be used to study the high temperature thermophysical and optical properties of the elements.

arXiv:2501.01811v1 Announce Type: cross Abstract: Accurate prediction of protein-ligand binding affinities is crucial in drug discovery, particularly during hit-to-lead and lead optimization phases, however, limitations in ligand force fields continue to impact prediction accuracy. In this work, we validate relative binding free energy (RBFE) accuracy using neural network potentials (NNPs) for the ligands. We utilize a novel NNP model, AceForce 1.0, based on the TensorNet architecture for small molecules that broadens the applicability to diverse drug-like compounds, including all important chemical elements and supporting charged molecules. Using established benchmarks, we show overall improved accuracy and correlation in binding affinity predictions compared with GAFF2 for molecular mechanics and ANI2-x for NNPs. Slightly less accuracy but comparable correlations with OPLS4. We also show that we can run the NNP simulations at 2 fs timestep, at least two times larger than previous NNP models, providing significant speed gains. The results show promise for further evolutions of free energy calculations using NNPs while demonstrating its practical use already with the current generation. The code and NNP model are publicly available for research use.

arXiv:2501.01621v1 Announce Type: new Abstract: We introduce a hyperreduced reduced basis element method for model reduction of parameterized, component-based systems in continuum mechanics governed by nonlinear partial differential equations. In the offline phase, the method constructs, through a component-wise empirical training, a library of archetype components defined by a component-wise reduced basis and hyperreduced quadrature rules with varying hyperreduction fidelities. In the online phase, the method applies an online adaptive scheme informed by the Brezzi-Rappaz-Raviart theorem to select an appropriate hyperreduction fidelity for each component to meet the user-prescribed error tolerance at the system level. The method accommodates the rapid construction of hyperreduced models for large-scale component-based nonlinear systems and enables model reduction of problems with many continuous and topology-varying parameters. The efficacy of the method is demonstrated on a two-dimensional nonlinear thermal fin system that comprises up to 225 components and 68 independent parameters.

arXiv:2501.00738v1 Announce Type: cross Abstract: The multiscale and turbulent nature of Earth's atmosphere has historically rendered accurate weather modeling a hard problem. Recently, there has been an explosion of interest surrounding data-driven approaches to weather modeling, which in many cases show improved forecasting accuracy and computational efficiency when compared to traditional methods. However, many of the current data-driven approaches employ highly parameterized neural networks, often resulting in uninterpretable models and limited gains in scientific understanding. In this work, we address the interpretability problem by explicitly discovering partial differential equations governing various weather phenomena, identifying symbolic mathematical models with direct physical interpretations. The purpose of this paper is to demonstrate that, in particular, the Weak form Sparse Identification of Nonlinear Dynamics (WSINDy) algorithm can learn effective weather models from both simulated and assimilated data. Our approach adapts the standard WSINDy algorithm to work with high-dimensional fluid data of arbitrary spatial dimension. Moreover, we develop an approach for handling terms that are not integrable-by-parts, such as advection operators.

arXiv:2501.00016v1 Announce Type: cross Abstract: Phase-field modeling reformulates fracture problems as energy minimization problems and enables a comprehensive characterization of the fracture process, including crack nucleation, propagation, merging, and branching, without relying on ad-hoc assumptions. However, the numerical solution of phase-field fracture problems is characterized by a high computational cost. To address this challenge, in this paper, we employ a deep neural operator (DeepONet) consisting of a branch network and a trunk network to solve brittle fracture problems. We explore three distinct approaches that vary in their trunk network configurations. In the first approach, we demonstrate the effectiveness of a two-step DeepONet, which results in a simplification of the learning task. In the second approach, we employ a physics-informed DeepONet, whereby the mathematical expression of the energy is integrated into the trunk network's loss to enforce physical consistency. The integration of physics also results in a substantially smaller data size needed for training. In the third approach, we replace the neural network in the trunk with a Kolmogorov-Arnold Network and train it without the physics loss. Using these methods, we model crack nucleation in a one-dimensional homogeneous bar under prescribed end displacements, as well as crack propagation and branching in single edge-notched specimens with varying notch lengths subjected to tensile and shear loading. We show that the networks predict the solution fields accurately, and the error in the predicted fields is localized near the crack.

arXiv:2409.19838v2 Announce Type: replace Abstract: Identifying informative low-dimensional features that characterize dynamics in molecular simulations remains a challenge, often requiring extensive manual tuning and system-specific knowledge. Here, we introduce geom2vec, in which pretrained graph neural networks (GNNs) are used as universal geometric featurizers. By pretraining equivariant GNNs on a large dataset of molecular conformations with a self-supervised denoising objective, we obtain transferable structural representations that are useful for learning conformational dynamics without further fine-tuning. We show how the learned GNN representations can capture interpretable relationships between structural units (tokens) by combining them with expressive token mixers. Importantly, decoupling training the GNNs from training for downstream tasks enables analysis of larger molecular graphs (such as small proteins at all-atom resolution) with limited computational resources. In these ways, geom2vec eliminates the need for manual feature selection and increases the robustness of simulation analyses.

arXiv:2501.00015v1 Announce Type: cross Abstract: (Pseudo)random sampling, a costly yet widely used method in (probabilistic) machine learning and Markov Chain Monte Carlo algorithms, remains unfeasible on a truly large scale due to unmet computational requirements. We introduce an energy-efficient algorithm for uniform Float16 sampling, utilizing a room-temperature stochastic magnetic tunnel junction device to generate truly random floating-point numbers. By avoiding expensive symbolic computation and mapping physical phenomena directly to the statistical properties of the floating-point format and uniform distribution, our approach achieves a higher level of energy efficiency than the state-of-the-art Mersenne-Twister algorithm by a minimum factor of 9721 and an improvement factor of 5649 compared to the more energy-efficient PCG algorithm. Building on this sampling technique and hardware framework, we decompose arbitrary distributions into many non-overlapping approximative uniform distributions along with convolution and prior-likelihood operations, which allows us to sample from any 1D distribution without closed-form solutions. We provide measurements of the potential accumulated approximation errors, demonstrating the effectiveness of our method.

arXiv:2501.00011v1 Announce Type: cross Abstract: Atmospheric models demand a lot of computational power and solving the chemical processes is one of its most computationally intensive components. This work shows how to improve the computational performance of the Multiscale Online Nonhydrostatic AtmospheRe CHemistry model (MONARCH), a chemical weather prediction system developed by the Barcelona Supercomputing Center. The model implements the new flexible external package Chemistry Across Multiple Phases (CAMP) for the solving of gas- and aerosol-phase chemical processes, that allows multiple chemical processes to be solved simultaneously as a single system. We introduce a novel strategy to simultaneously solve multiple instances of a chemical mechanism, represented in the model as grid-cells, obtaining a speedup up to 9x using thousands of cells. In addition, we present a GPU strategy for the most time-consuming function of CAMP. The GPU version achieves up to 1.2x speedup compared to CPU. Also, we optimize the memory access in the GPU to increase its speedup up to 1.7x.