Flow Prediction Research Articles

Hybrid deep learning model with VMD-BiLSTM-GRU networks for short-term traffic flow prediction

Accelerating urbanization and the rapid development of intelligent transportation systems have rendered short-term traffic flow prediction an important research field. Accurate prediction of traffic flow is beneficial for the optimization of traffic planning, improvement of road utilization, reduction of traffic congestion, and reduction in the incidence of traffic accidents. However, data pertaining to traffic flow are typically influenced by a multitude of factors, resulting in data that exhibit a considerable degree of nonlinearity and complexity. To address the issue of noise in raw traffic flow data, this study proposes a hybrid model that combines variational modal decomposition (VMD), a bidirectional long short-term memory network (BiLSTM), and a gated recurrent unit (GRU) for short-term traffic flow prediction. To validate the effectiveness of the model, an experimental validation was conducted based on traffic flow data from UK highways, and the performance of the model was compared with common benchmark models. The experimental results demonstrate that the proposed method yields superior prediction results in terms of mean absolute error, coefficient of determination, and root-mean-square error compared to existing prediction techniques, thereby substantiating its efficacy in short-term traffic flow prediction.

Metro short-term section passenger flow inherent patterns extraction and prediction: A novel denoising-based method

Metro short-term section passenger flow inherent patterns extraction and prediction: A novel denoising-based method

Enhancing urban flow prediction via mutual reinforcement with multi-scale regional information

Enhancing urban flow prediction via mutual reinforcement with multi-scale regional information

Development of a Generalizable Data-Driven Turbulence Model: Conditioned Field Inversion and Symbolic Regression

This paper addresses the issue of predicting separated flows with Reynolds-averaged Navier–Stokes (RANS) turbulence models, which are essential for many engineering tasks. Traditional RANS models usually struggle with this task, so recent efforts have focused on data-driven methods such as field inversion and machine learning (FIML) to correct this issue by adjusting the baseline equations. However, these FIML methods often reduce accuracy in attached boundary layers. To address this issue, we developed a “conditioned field inversion” technique. This method adjusts the corrective factor β (used by FIML) in the shear-stress transport (SST) model. It multiplies β with a shield function fd that is off in the boundary layer and on elsewhere. This maintains the accuracy of the baseline model for the attached flows. We applied both conditioned and classic field inversion to the NASA hump and a curved backward-facing step, creating two datasets. These datasets were used to train two models: SR-CND (symbolic regression-conditioned, from our new method) and SR-CLS (symbolic regression-classic, from the traditional method). The SR-CND model matches the SR-CLS model in predicting separated flows in various scenarios, such as periodic hills, the NLR7301 airfoil, the 3D SAE (Society of Automotive Engineers) car model, and the 3D Ahmed body, and outperforms the baseline SST model in the cases presented in the paper. Importantly, the SR-CND model maintains accuracy in the attached boundary layers, whereas the SR-CLS model does not. Therefore, the proposed method improves separated flow predictions while maintaining the accuracy of the original model for attached flows, offering a better way to create data-driven turbulence models.

Analysis of tourist flow prediction model of rural tourism on the edge of big cities in China

Introduction: With the adoption of the rural rehabilitation strategy in recent years, China’s rural tourist industry has entered a golden age of growth. Due to the lack of management and decision-support systems, many rural tourist attractions in China experience a “tourist overload” problem during minor holidays or Golden Week, an extended vacation of seven or more consecutive days in mainland China formed by transferring holidays during a specific holiday period. This poses a severe challenge to tourist attractions and relevant management departments. Objective: This study aims to summarize the elements influencing passenger flow by examining the features of rural tourist attractions outside China’s largest cities. Additionally, the study will investigate the variations in the flow of tourists. Method: Grey Model (1,1) is a first-order, single-variable differential equation model used for forecasting trends in data with exponential growth or decline, particularly when dealing with small and incomplete datasets. Four prediction algorithms—the conventional GM(1,1) model, residual time series GM(1,1) model, single-element input BP neural network model, and multi-element input BP network model—were used to anticipate and assess the passenger flow of scenic sites. Result: The multi-input BP neural network model and residual time series GM(1,1) model have significantly higher prediction accuracy than the conventional GM(1,1) model and unit-input BP neural network model. A multi-input BP neural network model and the residual time series GM(1,1) model were used in tandem to develop a short-term passenger flow warning model for rural tourism in China’s outskirts. Conclusion: This model can guide tourists to staggered trips and alleviate the problem of uneven allocation of tourism resources.

Collision energy dependence of elliptic flow of identified hadrons in heavy-ion collisions using the PHSD model

We report the first predictions of elliptic flow (v2) of identified hadrons at mid-rapidity (|y|< 1.0) in Au+Au collisions at Elab=6.7,8,11,and 25 A GeV using the Parton Hadron String Dynamics (PHSD) model. The transverse momentum (pT) dependence of identified hadron v2 in different centrality intervals (0-10%, 10-40%, and 40-80%) is shown. A clear centrality dependence of v2(pT) is observed for particles at Elab=6.7,8,11,and 25 A GeV. Within the PHSD model, the number of constituent quark (NCQ) scaling of v2 approximately follows in Au+Au collisions at all beam energies. A collision energy (sNN) dependence of π, K, and pv2 is studied in comparison with available published experimental data in the beam energy range of 6-25 A GeV. These predictions will help in interpreting the data from the forthcoming Compressed Baryonic Matter (CBM) experiment at the Facility for Antiproton and Ion Research (FAIR) and Multi-Purpose Detector (MPD) at the Nuclotron-based Ion Collider facility (NICA).

Leveraging synthetic aperture radar (SAR) with the National Water Model (NWM) to improve above-normal flow prediction in ungauged basins

Abstract Effective flood prediction supports developing proactive risk management strategies, but its application in ungauged basins faces tremendous challenges due to limited/no streamflow record. This study investigates the potential for integrating streamflow derived from synthetic aperture radar (SAR) data and U.S. National Water Model (NWM) reanalysis estimates to develop improved predictions of above-normal flow (ANF) over the coterminous US. Leveraging the SAR data from the Global Flood Detection System to estimate the antecedent conditions using principal component regression, we apply the spatial-temporal hierarchical model (STHM) using NWM outputs for improving ANF prediction. Our evaluation shows promising results with the integrated model, STHM-SAR, significantly improving NWE, especially in 60% of the sites in the coastal region. Spatial and temporal validations underscore the model’s robustness, with SAR data contributing to explained variance by 24% on average. This approach not only improves NWM prediction, but also uniquely combines existing remote sensing data with national-scale predictions, showcasing its potential to improve hydrological modeling, particularly in regions with limited stream gauges.

Short-Term Passenger Flow Prediction Based on a Hybrid Model of Support Vector Machine and Long Short-Term Memory Network

Short-Term Passenger Flow Prediction Based on a Hybrid Model of Support Vector Machine and Long Short-Term Memory Network

Tennis Player Momentum Analysis and Match Flow Prediction Model Based on PCA

Momentum is a fluctuating phenomenon that occurs during the course of a game when the seemingly dominant side scores consecutive points or influences the course of the entire game. And as tennis is a popular sport all over the world, exploring the effects and mechanisms of athletes' momentum on match changes and outcomes in tennis matches can provide reasonable match advice to athletes. To this end, this paper systematically establishes a prediction model based on tennis players' momentum analysis and match direction. In this paper, this text first cleaned the data for the 2023 Wimbledon tennis tournament obtained from the American Collegiate Mathematical Modeling Contest website and supplemented the missing values using cubic Hermite interpolation. The processed data is then analyzed using principal component analysis, where a linear combination of each principal component is defined as a momentum value, thus quantifying the momentum and creating a mathematical model between the indicator and the momentum. Finally, a momentum plot of the player is created to visualize the relationship between the player's momentum and the outcome of the race.

Long-Term Passenger Flow Forecasting for Rail Transit Based on Complex Networks and Informer.

With the continuous growth of urbanization, passenger flow in urban rail transit systems is steadily increasing, making accurate long-term forecasting essential for optimizing operational scheduling and enhancing service quality. However, passenger flow forecasting becomes increasingly complex due to the intricate structure of rail transit networks and external factors such as seasonal variations. To address these challenges, this paper introduces an optimized Informer model for long-term forecasting that incorporates the influences of other stations based on complex network theory. Compared to the ARIMA, LSTM, and Transformer models, this optimized Informer model excels in processing large-scale complex transit data, particularly in terms of long-term forecasting accuracy and capturing network dependencies. The results demonstrate that this forecasting approach, which integrates complex network theory with the Informer model, significantly improves the accuracy and efficiency of long-term passenger flow predictions, providing robust decision support for urban rail transit planning and management.

Federated Learning-Based Traffic Flow Prediction Model in Intelligent Transportation Systems

The existing Intelligent Transportation System (ITS) achieves high success. As an essential component of ITS, Traffic Flow Prediction (TFP) has attracted tremendous attention. It is a critical but challenging task to improve the robust convergence and high accuracy of TFP in real-world scenarios. This study presents an optimized Federated Learning (FL)-based ChebNet model, FedproxChebNet, to realize the highly effective and accurate TFP. By selecting the best penalty constant in the proximal term to optimize the objective function, this model can achieve fast and stable convergence. Using the ChebNet model to aggregate neighbor nodes’ characteristics, more hidden information underlying the spatio-temporal traffic data can be taken into consideration for training the global and local models. All the superiority of the FedproxChebNet model makes it outperform other FL models with the Graph Convolutional Network (GCN), Graph Attention Network (GAT) and Spatio-Temporal Graph Convolutional Network (STGCN). We designed a series of experiments on various FL-based GNN model comparisons, parameter sensitivity tests, and on verifying the performance of FedproxChebNet with different heterogeneous systems with [Formula: see text], [Formula: see text] and [Formula: see text]. Based on four real-world data sets from the cognitive network, the experimental results demonstrate that the presented FedproxChebNet provides the best convergence and the highest accuracy in TFP, and achieves the best performance in a highly heterogeneous system ([Formula: see text]). Specifically, the accuracy of FedproxChebNet is at least improved by [Formula: see text] on PeMS07 than other FL-based GNN models. This proposed FedproxChebNet model may be preferable for different scenarios in ITS such as route planning, traffic congestion control and reversible lanes.

An Artificial Neural Network Model for Short-Term Traffic Flow Prediction in Two Lane Highway in Khulna Metropolitan City, Bangladesh

Short-term traffic flow prediction is one of the most significant research topics in traffic engineering. It is instrumental in designing a more modern transport network to manage traffic signals and reduce congestion. Short-term traffic flow is a challenge that a third-world country like Bangladesh is all too familiar with. Like the other cities of Bangladesh, Khulna Metropolitan City is gradually becoming more aware of this situation. The Khulna-Jashore National Highway (N-7), which runs through the city and provides a linear shape, serves as the backbone of the Khulna Metropolitan City traffic flow. This study developed an Artificial Neural Network (ANN) model for the short-term Traffic Flow Prediction on Two-Lane Highway in Khulna Metropolitan City, Bangladesh. Data was collected from March 1, 2021, through June 30, 2021, during 600–900 hours and 1200–1500 hours. Good-quality electronic cameras recorded the vehicles at the full designated length. The regression graphs displayed the network outputs with targets for the training, validation, and test sets. The various speed level parameters for which the fit is reasonable for all data sets, with R values of 0.98426 in each case. The various traffic volume parameters for which the fit is reasonable for all data sets, with R values of 0.96758 in each case. The model's superiority is indicated by its low mean squared error values. This study demonstrated that the neural network has a good prediction effect on specific road traffic flow, which can achieve the goal of short-term prediction and has improved practicability through testing on real traffic data. This study provides an opportunity to provide a suitable alternative for short-term traffic flow forecasting in Khulna Metropolitan City with traffic flow conditions for two-lane undivided highways.

Neural differentiable modeling with diffusion-based super-resolution for two-dimensional spatiotemporal turbulence

Simulating spatiotemporal turbulence with high fidelity remains a cornerstone challenge in computational fluid dynamics (CFD) due to its intricate multiscale nature and prohibitive computational demands. Traditional approaches typically employ closure models, which attempt to represent small-scale features in an unresolved manner. However, these methods often sacrifice accuracy and lose high-frequency/wavenumber information, especially in scenarios involving complex flow physics. In this paper, we introduce an innovative neural differentiable modeling framework designed to enhance the predictability and efficiency of spatiotemporal turbulence simulations. Our approach features differentiable hybrid modeling techniques that seamlessly integrate deep neural networks with numerical PDE solvers within a differentiable programming framework, synergizing deep learning with physics-based CFD modeling. Specifically, a hybrid differentiable neural solver is constructed on a coarser grid to capture large-scale turbulent phenomena, followed by the application of a Bayesian conditional diffusion model that generates small-scale turbulence conditioned on large-scale flow predictions. Two innovative hybrid architecture designs are studied, and their performance is evaluated through comparative analysis against conventional large eddy simulation techniques with physics-based subgrid-scale closures and purely data-driven neural solvers. The findings underscore the potential of the neural differentiable modeling framework to significantly enhance the accuracy and computational efficiency of turbulence simulations. This study not only demonstrates the efficacy of merging deep learning with physics-based numerical solvers but also sets a new precedent for advanced CFD modeling techniques, highlighting the transformative impact of differentiable programming in scientific computing.

LES and RANS Modeling of an 84-Pin Hexagonal Rod Bundle with Spacer Grid and Experimental Validation

As part of an ongoing integrated research project (IRP), detailed investigations of the flow characteristics of an 84-pin hexagonal rod bundle representing a potential modular gas-cooled fast reactor design have been performed. The rod bundle features a pitch-to-diameter ratio of 1.5 and a large central guide tube, along with simple spacer grids and an outer enclosure. The primary focus of the current work is modeling and simulation of this geometry using multiple computational techniques. These include high-fidelity large eddy simulation (LES) and advanced Reynolds-averaged Navier-Stokes (RANS) approaches. The flow predictions are validated at a Reynolds number of 12 000 using matched index of refraction particle image velocimetry experimental data that were also generated by Texas A&M University as part of the IRP. The comparison data include velocity magnitude and turbulent kinetic energy (TKE) at different lateral locations and at multiple distances downstream of the spacer grid. Many characteristics of the experimental flow are replicated in the LES and RANS runs, and a general agreement between simulation and experiment is shown. Except for the immediate vicinity of the grid, LES is able to capture the velocity magnitude within a 10% error and the TKE to within the experimental uncertainty. The LES shows notably better agreement with the experimental data than RANS, particularly regarding the TKE decay behavior downstream of the grid. Both methods show significant departures from the experiment in their predictions close to the central guide tube. The experimental and high-fidelity data will be used to inform closures for novel multiscale methodologies. The long-term goal of the work is to use the high-fidelity data to yield improved multiscale thermal analysis techniques for solving fuel performance problems of direct relevance to industry.

MSA-GCN: Multistage Spatio-Temporal Aggregation Graph Convolutional Networks for Traffic Flow Prediction

Timely and accurate traffic flow prediction is crucial for stabilizing road conditions, reducing environmental pollution, and mitigating economic losses. While current graph convolution methods have achieved certain results, they do not fully leverage the true advantages of graph convolution. There is still room for improvement in simultaneously addressing multi-graph convolution, optimizing graphs, and simulating road conditions. Based on this, this paper proposes MSA-GCN: Multistage Spatio-Temporal Aggregation Graph Convolutional Networks for Traffic Flow Prediction. This method overcomes the aforementioned issues by dividing the process into different stages and achieves promising prediction results. In the first stage, we construct a latent similarity adjacency matrix and address the randomness interference features in similarity features through two optimizations using the proposed ConvGRU Attention Layer (CGAL module) and the Causal Similarity Capture Module (CSC module), which includes Granger causality tests. In the second stage, we mine the potential correlation between roads using the Correlation Completion Module (CC module) to create a global correlation adjacency matrix as a complement for potential correlations. In the third stage, we utilize the proposed Auto-LRU autoencoder to pre-train various weather features, encoding them into the model’s prediction process to enhance its ability to simulate the real world and improve interpretability. Finally, in the fourth stage, we fuse these features and use a Bidirectional Gated Recurrent Unit (BiGRU) to model time dependencies, outputting the prediction results through a linear layer. Our model demonstrates a performance improvement of 29.33%, 27.03%, and 23.07% on three real-world datasets (PEMSD8, LOSLOOP, and SZAREA) compared to advanced baseline methods, and various ablation experiments validate the effectiveness of each stage and module.

SPFDNet: Water Extraction Method Based on Spatial Partition and Feature Decoupling

Extracting water information from remote-sensing images is of great research significance for applications such as water resource protection and flood monitoring. Current water extraction methods aggregated richer multi-level features to enhance the output results. In fact, there is a difference in the requirements for the water body and the water boundary. Indiscriminate multi-feature fusion can lead to perturbation and competition of information between these two types of features during the optimization. Consequently, models cannot accurately locate the internal vacancies within the water body with the external boundary. Therefore, this paper proposes a water feature extraction network with spatial partitioning and feature decoupling. To ensure that the water features are extracted with deep semantic features and stable spatial information before decoupling, we first design a chunked multi-scale feature aggregation module (CMFAM) to construct a context path for obtaining deep semantic information. Then, an information interaction module (IIM) is designed to exchange information between two spatial paths with two fixed resolution intervals and the two paths through. During decoding, a feature decoupling module (FDM) is developed to utilize internal flow prediction to acquire the main body features, and erasing techniques are employed to obtain boundary features. Therefore, the deep features of the water body and the detailed boundary information are supplemented, strengthening the decoupled body and boundary features. Furthermore, the integrated expansion recoupling module (IERM) module is designed for the recoupling stage. The IERM expands the water body and boundary features using expansion and adaptively compensates the transition region between the water body and boundary through information guidance. Finally, multi-level constraints are combined to realize the supervision of the decoupled features. Thus, the water body and boundaries can be extracted more accurately. A comparative validation analysis is conducted on the public datasets, including the gaofen image dataset (GID) and the gaofen2020 challenge dataset (GF2020). By comparing with seven SOTAs, the results show that the proposed method achieves the best results, with IOUs of 91.22 and 78.93, especially in the localization of water bodies and boundaries. By applying the proposed method in different scenarios, the results show the stable capability of the proposed method for extracting water with various shapes and areas.

Dynamic multi-scale spatial-temporal graph convolutional network for traffic flow prediction

This paper proposes a dynamic multi-scale spatial-temporal graph convolutional network (DS-STGCN) for traffic flow prediction. The network aims to comprehensively extract global and local dependencies in dynamic spatial-temporal data by inputting traffic network flow data to construct node feature graphs, topology graphs, and time slot feature graphs, capturing the complexity and dynamics of traffic flow. DS-STGCN interprets feature information of the traffic network from both spatial and temporal dimensions through dynamic multi-scale graph convolutional blocks. In the spatial dimension, these blocks use constraints at different levels to balance fine-grained local features and extensive global features, revealing the intrinsic structure of traffic flow data. In the temporal dimension, these blocks jointly learn with temporal convolutional blocks to capture multi-frequency time patterns and handle long sequence data, effectively extracting potential dependencies of time series. Furthermore, DS-STGCN effectively models the changing spatial-temporal relationships in road network flow by constructing dynamically adaptive updated adjacency tensors, generating dynamic graph structures to address the challenge of changing spatial-temporal relationships in the transportation system. Experimental results show that our method significantly outperforms other competing methods on five real traffic datasets (PEMS03, PEMS04, PEMS07, PEMS08 and METR-LA).

Retraction Note: Machine learning and IoTs for forecasting prediction of smart road traffic flow

Retraction Note: Machine learning and IoTs for forecasting prediction of smart road traffic flow

Data-Guided Low-Reynolds-Number Corrections for Two-Equation Models

Abstract The baseline Launder–Spalding k−ε model cannot be integrated to the wall. This paper seeks to incorporate the entire law of the wall into the model while preserving the original k−ε framework structure. Our approach involves modifying the unclosed dissipation terms in the k and ε equations specifically within the wall layer according to direct numerical simulation (DNS) data. The resulting model effectively captures the mean flow characteristics in both the buffer layer and the logarithmic layer, resulting in robust predictions of skin friction for zero-pressure-gradient (ZPG) flat-plate boundary layers and plane channels. To further validate our formulation, we apply our model to boundary layers under varying pressure gradients, channels experiencing sudden deceleration, and flow over periodic hills, with highly favorable results. Although not the focus of this study, the methodology here applies equally to the k–ω formulation and yields improved predictions of the mean flow in the viscous sublayer and buffer layer.

MGHCN: Multi-graph structures and hypergraph convolutional networks for traffic flow prediction

Accurate and timely traffic flow predictions are essential for effective traffic management and congestion reduction. However, most traditional prediction methods often fail to capture the complex dynamics and correlations within traffic flows due to insufficient processing of spatiotemporal data. Specifically, these methods struggle to integrate and analyze the multi-layered spatial and temporal interactions inherent in traffic data, leading to suboptimal prediction accuracy and robustness. To address this limitation, this paper presents a Multi-Graph Structures and Hypergraph Convolutional Network (MGHCN) that combines diverse graphs and hypergraphs. The MGHCN simplifies the predictive framework by integrating key components that improve its robustness and accuracy. One of the most critical components is the dual hypergraph structure, which captures edge correlations by converting traditional graph edges into hypergraph nodes. To better capture the spatiotemporal correlation of traffic data, a Graph Convolutional Network (GCN) is employed to analyze these hypergraphs in depth. Finally, a novel adjacency matrix and a dynamic graph module are used to accurately simulate interactions between spatiotemporal features, thereby enhancing the accuracy and robustness of predictions. Experimental validation on four distinct real-world traffic datasets shows that MGHCN outperforms existing state-of-the-art traffic prediction methods.