A physics-informed neural network coupling framework for predicting heat and mass transfer characteristics of grains

Puntos clave

• Predictive modeling shows improved accuracy in heat and mass transfer characteristics in grains, enhancing understanding of these processes.
• Key metrics include the coupling of physics-informed neural networks that optimally simulate grain behavior under varying conditions.
• Analysis incorporates state-of-the-art predictive modeling techniques through a neural network framework for heat and mass transfer.
• Findings may enable more efficient agricultural processing and storage practices by optimizing grain heat and mass transfer characteristics.