Search

• Explore the Physical Informed Neural Networks (PINN) model to predict fluid flow around sharp obstacles using low-resolution datasets. • The PINN is sensitive to the resolution of datasets, and it also struggles to handle boundary conditions on complex geometries. • Improve the use of PINN model by combining it with a One-hot matrix model to better take into account the boundary conditions on complex geometries. • Use the Q-criterion as a weight to enforce the vortical structure location by the neural network. • Better prediction of our approach of two-dimensional flows around sharp rectangular obstacles using low-resolution datasets. The Physical Informed Neural Networks (PINN) model is one of the emerging and promising Deep Learning approaches to predict physical phenomena governed by PDEs such as fluid flow dynamics. The PINN model is indeed of great importance for improving the accuracy of machine learning methods for predicting mass transfer problems. However, it is sensitive to the accuracy of input datasets, and also struggles to predict phenomena occurring in complex geometries. These two weaknesses could limit the application of the PINN model. In this article, we improve the use of the PINN model by combining it with a One-hot matrix model to better take into account the boundary conditions on complex geometries. The use of the One-hot matrix is also investigated with non-uniform weights from physics. We indeed used the Q-criterion as a non-uniform weight to enforce the vortical structure location by the neural network. The proposed model more accurately predicts the two-dimensional flow around sharp rectangular obstacles from low-resolution datasets. [ABSTRACT FROM AUTHOR]