A neural accelerated surface-roughness-based Discrete Element Method (SR-DEM) for modeling granular systems

Xiwei Pan; Liuchi Li

Home/Archive/arXiv

arXiv · 2610.33363

A neural accelerated surface-roughness-based Discrete Element Method (SR-DEM) for modeling granular systems

Xiwei Pan·Liuchi Li

View original source ↗Read source document ↗Export metadata ↓

Abstract

The Discrete Element Method (DEM) is an indispensable tool for modeling and understanding the basic mechanical behaviors of (dry) granular media, a class of disordered material systems of significant interest to multiple scientific domains from (geo-)physics to (chemical) engineering. At the core of all present DEM frameworks is a phenomenological friction law--commonly chosen to be of the Amontons-Coulomb type--that models the frictional interaction among constituent grains. Here, inspired by research in the tribology community, we present an alternative, fundamentally different framework, termed surface-roughness-based DEM (SR-DEM), in which contact friction is handled in a more physics-based manner. In this framework, instead of using a friction law, we explicitly resolve the surface topography of each grain and let friction emerge from collective frictionless interactions of surface asperities. In essence, we trade phenomenology for physics at the cost of an increased computational demand. To mitigate the cost, we introduce an FE$^2$-like algorithm and a feature-wise linear modulation (FiLM)-based neural network surrogate, both of which are parallelized on GPU to accelerate contact computation. Crucially, using this framework in 2D, we (1) demonstrate the possibility of recovering a two-body-based Amontons-Coulomb-type friction behavior using a simple representation of surface topography, and (2) identify many-body-based frictional behaviors--more specifically, the angle of repose values--that cannot always be captured by current DEM frameworks under the same level of model complexity. We conclude by discussing future directions for SR-DEM, as well as exciting new opportunities it could unlock for a wide range of emerging applications, including (designing) suspension rheology and metamaterial mechanics.

Explore related subjects

physics.comp-ph cond-mat.soft

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Xiwei Pan, Liuchi Li. 2026-10-23. A neural accelerated surface-roughness-based Discrete Element Method (SR-DEM) for modeling granular systems. https://arxiv.org/abs/2610.33363

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Physics-Informed Neural Networks for coupled stiff transport systems

Physics-Informed Neural Networks (PINN) struggle with stiff, regime-changing transport equations due to instability, loss imbalance, and violations of physical consistency. This paper investigates these failures through the Marshak wave equations, a canonical benchmark from radiative transport, where initial and boundary conditions differ by up to 12 orders of magnitude, and proposes modifications to the standard PINN framework to overcome them. Three modifications are introduced: a ScaledSigmoid final activation enforcing physical bounds and positivity of the unknowns; a logarithmic MSE loss replacing the standard quadratic loss for initial and boundary conditions, enabling training across extreme scale disparities; and explicit enforcement of global conservation laws as an additional physics loss term. Monte Carlo sampling with exponential time weighting is used throughout. The proposed framework recovers the Marshak wave dynamics - including the hot, cold, and wave-front regions - in good agreement with a reference Implicit Monte Carlo solution (sub-millimeter absolute error on the front position, although the relative error remains substantial at early times), with run times under 5 minutes. Ablation studies confirm that each ingredient is essential: linear activation, absence of the logarithmic loss, or removal of the PDE term each independently cause the method to fail qualitatively. This work identifies and resolves three concrete failure modes of standard PINN on stiff hyperbolic systems with nonlinear coupling. The combination of bounded activations, scale-aware loss functions, and conservation law enforcement constitutes a framework validated on the present one-dimensional Marshak wave problem, with potential extension to other coupled stiff transport systems in engineering.

physics.comp-ph↗

arXiv2026

Towards Exact Multidimensional Fluxes: A Structure-Preserving Data-Informed Framework for Riemann Solvers

Finite-volume and discontinuous Galerkin methods update cells using the space-time flux integral over their faces, which typically depends on the solutions to local Riemann problems. In the multidimensional Riemann problem setting, this integral is difficult to evaluate exactly because of complex wave interactions. In this work, we show that the exact space-time flux integral is a polynomial in the time step and face dimensions. This motivates a learning-based approach, as only the mapping from the initial states to the polynomial coefficients needs to be learned. We propose a structure-preserving, data-informed Riemann solver framework that uses a neural network trained on high-resolution simulation data to learn this mapping. Key structural properties, including consistency and symmetry, are enforced by construction. Provided that the high-resolution simulations converge to the exact flux integrals and the network accurately predicts the coefficients, this framework yields near-exact flux integrals for use in numerical simulations. We demonstrate the framework using classical implosion and explosion problems for the two-dimensional Euler equations. In an unsplit MUSCL-Hancock scheme, the learned Riemann solver remains stable at a CFL number of 0.9, whereas the same scheme using the exact one-dimensional Riemann solver fails. Compared with the latter scheme at CFL=0.45, the learned scheme is slightly more accurate and requires approximately 30% less computational time.

physics.comp-ph↗

arXiv2026

Machine learning kinetics from molecular dynamics data

Most molecular transitions occur on time scales far beyond direct molecular dynamics simulations. The committor, the probability that a configuration reaches a product state before a reactant state, is a central kinetic statistic, providing a mechanism-independent reaction coordinate and a foundation for transition path theory and the calculation of rates. This review surveys modern approaches for estimating the committor and related kinetic statistics from molecular simulations, with an emphasis on self-supervised methods that learn solutions of their defining dynamical equations rather than relying on labeled shooting data. We develop a common operator viewpoint connecting generator-based partial differential equations, variational principles, Markov state models, dynamical Galerkin approximation, and neural networks. Empirical and theoretical evidence points to the efficiency of these methods. We provide theoretical and practical guidance for realizing their full potential in applications, including strategies for treating non-Markovian effects and for sampling. We conclude by identifying opportunities for further research, including connections to reinforcement learning and generative modeling.

physics.comp-ph↗