Weather impact on macroscopic traffic stream variables prediction using recurrent learning approach

Nigam, Archana; Srivastava, Sanjay

doi:10.1080/15472450.2021.1983809

Cited by 10 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traffic situations face different variations along with the presence of multi-source heterogeneous environmental factors, such as points of interest (POIs) [22], social events [23], and weather [21,43,44]. Embedding these factors into the traffic scenarios, the spatiotemporal model driven by environmental factors is more relevant to urban traffic, and at the same time, there is an improvement in stability.…”

Section: Spatio-temporal Traffic Prediction With Embedded Factorsmentioning

confidence: 99%

Weather Interaction-Aware Spatio-Temporal Attention Networks for Urban Traffic Flow Prediction

Zhong,

Wang,

Chen

et al. 2024

Buildings

View full text Add to dashboard Cite

As the cornerstone of intelligent transportation systems, accurate traffic prediction can reduce the pressure of urban traffic, reduce the cost of residents’ travel time, and provide a reference basis for urban construction planning. Existing traffic prediction methods focus on spatio-temporal dependence modeling, ignoring the influence of weather factors on spatio-temporal characteristics, and the prediction task has complexity and an uneven distribution in different spatio-temporal scenarios and weather changes. In view of this, we propose a weather interaction-aware spatio-temporal attention network (WST-ANet), in which we integrate feature models and dynamic graph modules in the encoder and decoder, and use a spatio-temporal weather interaction perception module for prediction. Firstly, the contextual semantics of the traffic flows are fused using a feature embedding module to improve the adaptability to weather drivers; then, an encoder–decoder is constructed by combining the Dynamic Graph Module and the WSTA Block, to extract spatio-temporal aggregated correlations in the roadway network; finally, the feature information of the encoder was weighted and aggregated using the cross-focusing mechanism, and attention was paid to the hidden state of the encoding. Traffic flow was predicted using the PeMS04 and PeMS08 datasets and compared with multiple typical baseline models. It was learned through extensive experiments that the accuracy evaluation result is the smallest in WST-ANet, which demonstrated the superiority of the proposed model. This can more accurately predict future changes in traffic in different weather conditions, providing decision makers with a basis for optimizing scenarios.

show abstract

Section: Spatio-temporal Traffic Prediction With Embedded Factorsmentioning

confidence: 99%

Weather Interaction-Aware Spatio-Temporal Attention Networks for Urban Traffic Flow Prediction

Zhong,

Wang,

Chen

et al. 2024

Buildings

View full text Add to dashboard Cite

show abstract

“…Using a random forest method, an SVR model and a deep belief network, a traffic flow prediction model for bad weather was built [30,31]. Neural networks, such as GRU, RNN, and LSTM [32,33], can take weather parameters as input data. It has been found that the introduction of weather data can improve the accuracy of traffic flow prediction [34].…”

Section: Literature Reviewmentioning

confidence: 99%

Intelligent Short-Term Multiscale Prediction of Parking Space Availability Using an Attention-Enhanced Temporal Convolutional Network

Shang

Wan

Zhang

et al. 2023

IJGI

View full text Add to dashboard Cite

The accurate and rapid prediction of parking availability is helpful for improving parking efficiency and to optimize traffic systems. However, previous studies have suffered from limited training sample sizes and a lack of thorough investigation into the correlations among the factors affecting parking availability. The purpose of this study is to explore a prediction method that can account for multiple factors. Firstly, a dynamic prediction method based on a temporal convolutional network (TCN) model was confirmed to be efficient for ultra-short-term parking availability with an accuracy of 0.96 MSE. Then, an attention-enhanced TCN (A-TCN) model based on spatial attention modules was proposed. This model integrates multiple factors, including related dates, extreme weather, and human control, to predict the daily congestion index of parking lots in the short term, with a prediction period of up to one month. Experimental results on real data demonstrate that the MSE of A-TCN is 0.0061, exhibiting better training efficiency and prediction accuracy than a traditional TCN for the short-term prediction time scale.

show abstract

“…There are also several studies focusing on the impact of weather on traffic, some of which are devoted to investigating the effects of inclement weather on traffic-flow characteristics (Gao et al, 2019; Maze et al, 2006). Some studies mainly analyzed the influences of bad weather on free-flow speed (Agarwal et al, 2005; Ru et al, 2015; Yasanthi and Mehran, 2020), whereas others examined the effects of adverse weather on capacity (Chung et al, 2006; Nigam and Srivastava, 2022). However, there are not enough studies on the impact of weather on accessibility of hospitals including public and private hospitals and clinics.…”

Section: Literature Reviewmentioning

confidence: 99%

Investigating Accessibility of Hospitals in Cold Regions: A Case Study of Harbin in China

Xia

et al. 2022

HERD

View full text Add to dashboard Cite

Objective: The objective of this study is to explore healthcare resource accessibility in Harbin, a typical city in a cold region in China. Background: Recently, investments in the construction of medical resources have been increasing annually in China, and consequently, the allocation of these resources has improved. Snow and ice on surfaces in China’s cold regions have certain effects on the traffic capacity of urban roads, leading to a great difference in the accessibility of medical resources in winter and summer. Methods: The basic spatial data, including spatial road data, medical facility data, and population distribution data, are analyzed using geographic information system. Then, a spatial barrier model is used to measure healthcare accessibility based on geographic and population weighting; we explore the accessibility of hospitals under the influence of weather by defining a novel distance attenuation function. Finally, the accessibility of medical institutions in the study area is explored by analyzing data about the related separation factors. Results: It was found that the spatial distribution of medical resources was not equal, and the dominant resources were concentrated in the city center. Some regions are always in an advantageous position regardless of traffic conditions. In contrast, in areas far from the city center, the accessibility of medical resources significantly decreases in winter. Conclusions: These results will help optimize the layout of medical institutions and improve medical equality and propose strategies for the optimization of the accessibility of urban medical institutions in cold regions of China.

show abstract

Weather impact on macroscopic traffic stream variables prediction using recurrent learning approach

Cited by 10 publications

References 21 publications

Weather Interaction-Aware Spatio-Temporal Attention Networks for Urban Traffic Flow Prediction

Weather Interaction-Aware Spatio-Temporal Attention Networks for Urban Traffic Flow Prediction

Intelligent Short-Term Multiscale Prediction of Parking Space Availability Using an Attention-Enhanced Temporal Convolutional Network

Investigating Accessibility of Hospitals in Cold Regions: A Case Study of Harbin in China

Contact Info

Product

Resources

About