arXiv subjects

Xuebo Li

Publications and source records attributed to Xuebo Li.

3 recordsLinked to original sources

arXiv2026

Error Analysis of Tr-PINNs Algorithm for 2D Incompressible Navier-Stokes Equations with Non-Homogeneous Boundary Conditions

Physics-informed neural networks (PINNs) have been widely applied to solve Navier-Stokes equations by enforcing outputs and gradients of deep models to satisfy target equations. However, conventional PINNs only constrain the boundary terms by means of the $L^2$-norm when addressing the equations with non-homogeneous boundary conditions. This single constraint strategy may cause inaccurate boundary simulation, further resulting in the decline of prediction accuracy. To resolve this critical issue, this paper proposes an improved physics-informed neural network by correcting the error of the boundary value, which is called Tr-PINNs. Based on the results of nonhomogeneous Stokes problem, the algorithm error analysis of Tr-PINNs is established. The efficacy of the Tr-PINNs algorithm is demonstrated via numerical experiments, which further demonstrate that the Tr-PINNs algorithm achieves a remarkable improvement in computational accuracy.

math.NA↗

arXiv2021

Scale-dependent inclination angle of turbulent structures in stratified atmospheric surface layers

A large-scale spanwise and wall-normal array of sonic anemometers in the atmospheric surface layer is used to acquire all three components of instantaneous fluctuating velocity as well as temperature in a range of stability conditions. These data permit investigation of the three-dimensional statistical structure of turbulence structures. The present work extends the view of a self-similar range of wall-attached turbulence structures to the atmospheric surface layer under unstable and near-neutral stability conditions, and includes the statistical structure in both the wall-normal and spanwise directions in relation to the streamwise wavelength. Results suggest that the self-similar wall-attached structures have similar aspect ratios between streamwise/wall-normal scales and streamwise/spanwise scales such that $λ_x/Δz : λ_x/Δy \approx 1$ for both near-neutral and unstable conditions. By analysing the phase shift between synchronized measurements, in the spectral domain, it is quantified how the structure inclination angle varies with stability. Under the most unstable conditions, coherent structures of $λ_x/δ= 1$ are inclined at angles as high as $65^\circ$ relative to the solid boundary, while larger scales of $λ_x/δ= 6$ exhibit inclination angles of approximately $35^\circ$. For near-neutral stability conditions, the angle tends towards $12^\circ$ for all scales. It is noted that in the near-neutral condition, the structure inclination angle and the aspect ratio -- and thus the statistical modeling of coherent structures in the ASL -- are highly sensitive to the value of the stability parameter.

physics.flu-dyn↗

arXiv2021

COVID-19 Fake News Detection Using Bidirectional Encoder Representations from Transformers Based Models

Nowadays, the development of social media allows people to access the latest news easily. During the COVID-19 pandemic, it is important for people to access the news so that they can take corresponding protective measures. However, the fake news is flooding and is a serious issue especially under the global pandemic. The misleading fake news can cause significant loss in terms of the individuals and the society. COVID-19 fake news detection has become a novel and important task in the NLP field. However, fake news always contain the correct portion and the incorrect portion. This fact increases the difficulty of the classification task. In this paper, we fine tune the pre-trained Bidirectional Encoder Representations from Transformers (BERT) model as our base model. We add BiLSTM layers and CNN layers on the top of the finetuned BERT model with frozen parameters or not frozen parameters methods respectively. The model performance evaluation results showcase that our best model (BERT finetuned model with frozen parameters plus BiLSTM layers) achieves state-of-the-art results towards COVID-19 fake news detection task. We also explore keywords evaluation methods using our best model and evaluate the model performance after removing keywords.

cs.CL↗