Region-aware graph neural networks for real-time drying simulations of unsaturated porous media - Food drying digital twin framework

Real-time simulation and the integration of digital twins necessitate the development of computationally efficient surrogate models for contemporary food drying systems, in which complex physical processes must interact dynamically with virtual representations. Traditional modeling approaches for food drying are subject to notable limitations: empirical models often lack physical fidelity, whereas high-fidelity computational fluid dynamics (CFD) simulations require the resolution of tightly coupled heat and mass transfer processes among vapor, liquid water, and air phases within unsaturated porous media, rendering them computationally prohibitive for real-time applications. This work proposes a region-aware graph neural network (GNN) surrogate model for food drying simulation by leveraging mesh-based and region-specific representations of the drying process. The proposed GNN architecture, inspired by MeshGraphNet with specialized masked message passing, handles the heterogeneous domains and sharp discontinuities characteristic of coupled heat and mass transfer in food drying. The GNN model was trained on a limited dataset comprising 28 CFD simulations of hot-air drying of a potato slice under varying ambient conditions, generated using a CFD framework validated against numerical results from the literature and laboratory-scale experimental data. Despite this small training set, the model delivers predictive performance for operating conditions beyond those seen during training. Single-step predictions achieved RMSE values of 0.17 °C for temperature ( T ), 0.26% for relative humidity ( RH ), and 0.0028 for liquid saturation ( S w ). Comparative analysis with standard message passing revealed a threefold reduction in interfacial absolute error (0.003 vs. 0.008) and elimination of nonphysical field propagation across domain boundaries. The model maintained performance on the training domain edges, with moisture ratio curves achieving R 2 > 0.97 for 10-step rollouts (R 2 = 0.989 interior domain; R 2 = 0.979 edge domain) while preserving the characteristic S-shaped drying curves in longer autonomous simulations (R 2 = 0.784 and 0.873 for full rollouts of the interior and edge-of-domain test cases, respectively). This framework is applicable to real-time process control, design optimization, and digital twin implementations in food manufacturing. • Integrated a region-aware GNN into a digital twin for potato drying. • Achieved high accuracy with minimal data in heat and mass transfer prediction. • Region-aware message passing ensured physical consistency across domains. • Model adapted to changes in temperature and geometry with low prediction error. • Fast predictions enable real-time control and food process optimization