Hybrid Deep Spatio-Temporal Models for Traffic Flow Prediction on Holidays and Under Adverse Weather
Three hybrid deep spatio-temporal models are proposed to accurately predict traffic flow under normal conditions, on holidays and under adverse weather. Each of the proposed models consists of the global and target parts, and fuses the weather and traffic flow data obtained from the target and upstr...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9612205/ |
| _version_ | 1819200320224362496 |
|---|---|
| author | Wensong Zhang Ronghan Yao Xiaojing Du Jinsong Ye |
| author_facet | Wensong Zhang Ronghan Yao Xiaojing Du Jinsong Ye |
| author_sort | Wensong Zhang |
| collection | DOAJ |
| description | Three hybrid deep spatio-temporal models are proposed to accurately predict traffic flow under normal conditions, on holidays and under adverse weather. Each of the proposed models consists of the global and target parts, and fuses the weather and traffic flow data obtained from the target and upstream sections. The convolutional neural network (CNN), and the gated recurrent unit (GRU) and convolutional long short-term memory (ConvLSTM) neural networks are selected to analyze the spatio-temporal characteristics of traffic flow data. Then, the three proposed models are verified using three actual cases, including traffic flow prediction under normal conditions, on holidays and under adverse weather. Moreover, the characteristics of traffic flow data on the Independence Day and Thanksgiving Day are discussed, as do the patterns of traffic flow data under heavy rain and strong wind. The experimental results show that: the three new models usually perform better than the existing models under all the situations; different holidays and different types of adverse weather have various impacts on the characteristics of traffic volume and speed data. |
| first_indexed | 2024-12-23T03:30:21Z |
| format | Article |
| id | doaj.art-de72da522d1c45ee95aba4884296acc4 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-23T03:30:21Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-de72da522d1c45ee95aba4884296acc42022-12-21T18:01:44ZengIEEEIEEE Access2169-35362021-01-01915716515718110.1109/ACCESS.2021.31275849612205Hybrid Deep Spatio-Temporal Models for Traffic Flow Prediction on Holidays and Under Adverse WeatherWensong Zhang0https://orcid.org/0000-0002-7894-9289Ronghan Yao1https://orcid.org/0000-0002-6614-1960Xiaojing Du2https://orcid.org/0000-0002-5329-8344Jinsong Ye3School of Transportation and Logistics, Dalian University of Technology, Dalian, ChinaSchool of Transportation and Logistics, Dalian University of Technology, Dalian, ChinaSchool of Transportation and Logistics, Dalian University of Technology, Dalian, ChinaKey Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport, China Academy of Transportation Sciences, Beijing, ChinaThree hybrid deep spatio-temporal models are proposed to accurately predict traffic flow under normal conditions, on holidays and under adverse weather. Each of the proposed models consists of the global and target parts, and fuses the weather and traffic flow data obtained from the target and upstream sections. The convolutional neural network (CNN), and the gated recurrent unit (GRU) and convolutional long short-term memory (ConvLSTM) neural networks are selected to analyze the spatio-temporal characteristics of traffic flow data. Then, the three proposed models are verified using three actual cases, including traffic flow prediction under normal conditions, on holidays and under adverse weather. Moreover, the characteristics of traffic flow data on the Independence Day and Thanksgiving Day are discussed, as do the patterns of traffic flow data under heavy rain and strong wind. The experimental results show that: the three new models usually perform better than the existing models under all the situations; different holidays and different types of adverse weather have various impacts on the characteristics of traffic volume and speed data.https://ieeexplore.ieee.org/document/9612205/Traffic flow predictionholidaysadverse weatherhybrid deep spatio-temporal modelconvolutional long short-term memory (ConvLSTM) |
| spellingShingle | Wensong Zhang Ronghan Yao Xiaojing Du Jinsong Ye Hybrid Deep Spatio-Temporal Models for Traffic Flow Prediction on Holidays and Under Adverse Weather IEEE Access Traffic flow prediction holidays adverse weather hybrid deep spatio-temporal model convolutional long short-term memory (ConvLSTM) |
| title | Hybrid Deep Spatio-Temporal Models for Traffic Flow Prediction on Holidays and Under Adverse Weather |
| title_full | Hybrid Deep Spatio-Temporal Models for Traffic Flow Prediction on Holidays and Under Adverse Weather |
| title_fullStr | Hybrid Deep Spatio-Temporal Models for Traffic Flow Prediction on Holidays and Under Adverse Weather |
| title_full_unstemmed | Hybrid Deep Spatio-Temporal Models for Traffic Flow Prediction on Holidays and Under Adverse Weather |
| title_short | Hybrid Deep Spatio-Temporal Models for Traffic Flow Prediction on Holidays and Under Adverse Weather |
| title_sort | hybrid deep spatio temporal models for traffic flow prediction on holidays and under adverse weather |
| topic | Traffic flow prediction holidays adverse weather hybrid deep spatio-temporal model convolutional long short-term memory (ConvLSTM) |
| url | https://ieeexplore.ieee.org/document/9612205/ |
| work_keys_str_mv | AT wensongzhang hybriddeepspatiotemporalmodelsfortrafficflowpredictiononholidaysandunderadverseweather AT ronghanyao hybriddeepspatiotemporalmodelsfortrafficflowpredictiononholidaysandunderadverseweather AT xiaojingdu hybriddeepspatiotemporalmodelsfortrafficflowpredictiononholidaysandunderadverseweather AT jinsongye hybriddeepspatiotemporalmodelsfortrafficflowpredictiononholidaysandunderadverseweather |