Granular materials play a crucial role in various industries, sparking a growing interest in the development of digital twins to replicate industrial scenarios. However, these materials show complex behaviours that challenge traditional simulation methods. While the discrete particle method (DPM) offers a promising solution by accurately capturing key physics, it solves Newton’s laws per particle and is computationally too expensive for large-scale industrial applications. To address this limitation, we propose a novel approach that combines two open-source software frameworks, namely pyMOR and MercuryDPM. The goal is to enhance the efficiency of DPM simulations using model order reduction (MOR) techniques. The approach involves reducing the complexity of DPM simulations by approximating particle behaviour with a lower-dimensional model. We aim to develop efficient MOR methods tailored for granular material simulations. Additionally, we explore a neural network trained to predict system states on the reduced subspace in a non-intrusive manner. This hybrid strategy reduces the simulation runtime from days to seconds, enabling us to create highly-efficient reduced models suitable for virtual prototyping and digital twin applications in industry. A significant challenge in applying MOR to particle methods lies in the inherently complex, random and high dimensional dynamics of individual particles, which disrupts traditional low-rank structures in state-space solution manifolds. To overcome this obstacle, we introduce MercuryCG, a popular homogenisation tool developed by our team. MercuryCG extracts continuum fields from discrete particle data while conserving local mass and momentum. By integrating MercuryCG with MOR techniques, we aim to mitigate the stochastic nature of particle simulations and establish a physics-informed surrogate model that preserves the structure of its underlying DPM model. Our approach represents a significant advancement in the simulation of granular materials, bridging the gap between computational efficiency and physical accuracy. Through the synergy of expertise and software resources from multiple institutions, we showcase a novel approach with the potential to transform the simulation of granular materials, offering unprecedented speed and reliability for process optimisation and design.