Fast Prediction of Solute Concentration Field in Rotationally Influenced Fluids Using a Parameter-Based Field Reconstruction Convolutional Neural Network

Many high-performance fluid dynamic models do not consider fluids in a rotating environment and often require significant amount of computational time. The current study proposes novel parameter-based field reconstruction convolutional neural network (PFR-CNN) approach to model the solute concentration rotationally influenced fluids. A new three-dimensional (3D) numerical solver, TwoLiquidMixingCoriolisFoam, was implemented within framework OpenFOAM simulate effluents subjected influence rotation. Subsequently, developed solver employed conduct experiments generate data. PFR-CNN designed predict fields neutrally buoyant water bodies based on Froude number (Fr) Rossby (Ro). proposed trained validated with train-validation dataset. predicted for two additional tests demonstrated good performance approach, algorithm performed better than traditional approaches. This offers 3D can transport effects rotation few seconds, significantly reduce costs. advance ability flow processes, CNN-based potentially be spatial distribution any physical variable lentic, ocean, earth system.