Urban Link Travel Time Prediction Based on a Gradient Boosting Method Considering Spatiotemporal Correlations
The prediction of travel times is challenging because of the sparseness of real-time traffic data and the intrinsic uncertainty of travel on congested urban road networks. We propose a new gradient–boosted regression tree method to accurately predict travel times. This model accounts for spatiotempo...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2016-11-01
|
Series: | ISPRS International Journal of Geo-Information |
Subjects: | |
Online Access: | http://www.mdpi.com/2220-9964/5/11/201 |
_version_ | 1811276389567954944 |
---|---|
author | Faming Zhang Xinyan Zhu Tao Hu Wei Guo Chen Chen Lingjia Liu |
author_facet | Faming Zhang Xinyan Zhu Tao Hu Wei Guo Chen Chen Lingjia Liu |
author_sort | Faming Zhang |
collection | DOAJ |
description | The prediction of travel times is challenging because of the sparseness of real-time traffic data and the intrinsic uncertainty of travel on congested urban road networks. We propose a new gradient–boosted regression tree method to accurately predict travel times. This model accounts for spatiotemporal correlations extracted from historical and real-time traffic data for adjacent and target links. This method can deliver high prediction accuracy by combining simple regression trees with poor performance. It corrects the error found in existing models for improved prediction accuracy. Our spatiotemporal gradient–boosted regression tree model was verified in experiments. The training data were obtained from big data reflecting historic traffic conditions collected by probe vehicles in Wuhan from January to May 2014. Real-time data were extracted from 11 weeks of GPS records collected in Wuhan from 5 May 2014 to 20 July 2014. Based on these data, we predicted link travel time for the period from 21 July 2014 to 25 July 2014. Experiments showed that our proposed spatiotemporal gradient–boosted regression tree model obtained better results than gradient boosting, random forest, or autoregressive integrated moving average approaches. Furthermore, these results indicate the advantages of our model for urban link travel time prediction. |
first_indexed | 2024-04-12T23:56:42Z |
format | Article |
id | doaj.art-40b7bef7bad648b2b424fef68ca99f0f |
institution | Directory Open Access Journal |
issn | 2220-9964 |
language | English |
last_indexed | 2024-04-12T23:56:42Z |
publishDate | 2016-11-01 |
publisher | MDPI AG |
record_format | Article |
series | ISPRS International Journal of Geo-Information |
spelling | doaj.art-40b7bef7bad648b2b424fef68ca99f0f2022-12-22T03:11:29ZengMDPI AGISPRS International Journal of Geo-Information2220-99642016-11-0151120110.3390/ijgi5110201ijgi5110201Urban Link Travel Time Prediction Based on a Gradient Boosting Method Considering Spatiotemporal CorrelationsFaming Zhang0Xinyan Zhu1Tao Hu2Wei Guo3Chen Chen4Lingjia Liu5State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, ChinaCollaborative Innovation Center of Geospatial Technology, 129 Luoyu Road, Wuhan 430079, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, ChinaSchool of Geodesy and Geomatics, Wuhan University, 129 Luoyu Road, Wuhan 430079, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, ChinaThe prediction of travel times is challenging because of the sparseness of real-time traffic data and the intrinsic uncertainty of travel on congested urban road networks. We propose a new gradient–boosted regression tree method to accurately predict travel times. This model accounts for spatiotemporal correlations extracted from historical and real-time traffic data for adjacent and target links. This method can deliver high prediction accuracy by combining simple regression trees with poor performance. It corrects the error found in existing models for improved prediction accuracy. Our spatiotemporal gradient–boosted regression tree model was verified in experiments. The training data were obtained from big data reflecting historic traffic conditions collected by probe vehicles in Wuhan from January to May 2014. Real-time data were extracted from 11 weeks of GPS records collected in Wuhan from 5 May 2014 to 20 July 2014. Based on these data, we predicted link travel time for the period from 21 July 2014 to 25 July 2014. Experiments showed that our proposed spatiotemporal gradient–boosted regression tree model obtained better results than gradient boosting, random forest, or autoregressive integrated moving average approaches. Furthermore, these results indicate the advantages of our model for urban link travel time prediction.http://www.mdpi.com/2220-9964/5/11/201urban link travel time predictionspatiotemporal correlationsspatiotemporal gradient–boosted regression tree modelbig data |
spellingShingle | Faming Zhang Xinyan Zhu Tao Hu Wei Guo Chen Chen Lingjia Liu Urban Link Travel Time Prediction Based on a Gradient Boosting Method Considering Spatiotemporal Correlations ISPRS International Journal of Geo-Information urban link travel time prediction spatiotemporal correlations spatiotemporal gradient–boosted regression tree model big data |
title | Urban Link Travel Time Prediction Based on a Gradient Boosting Method Considering Spatiotemporal Correlations |
title_full | Urban Link Travel Time Prediction Based on a Gradient Boosting Method Considering Spatiotemporal Correlations |
title_fullStr | Urban Link Travel Time Prediction Based on a Gradient Boosting Method Considering Spatiotemporal Correlations |
title_full_unstemmed | Urban Link Travel Time Prediction Based on a Gradient Boosting Method Considering Spatiotemporal Correlations |
title_short | Urban Link Travel Time Prediction Based on a Gradient Boosting Method Considering Spatiotemporal Correlations |
title_sort | urban link travel time prediction based on a gradient boosting method considering spatiotemporal correlations |
topic | urban link travel time prediction spatiotemporal correlations spatiotemporal gradient–boosted regression tree model big data |
url | http://www.mdpi.com/2220-9964/5/11/201 |
work_keys_str_mv | AT famingzhang urbanlinktraveltimepredictionbasedonagradientboostingmethodconsideringspatiotemporalcorrelations AT xinyanzhu urbanlinktraveltimepredictionbasedonagradientboostingmethodconsideringspatiotemporalcorrelations AT taohu urbanlinktraveltimepredictionbasedonagradientboostingmethodconsideringspatiotemporalcorrelations AT weiguo urbanlinktraveltimepredictionbasedonagradientboostingmethodconsideringspatiotemporalcorrelations AT chenchen urbanlinktraveltimepredictionbasedonagradientboostingmethodconsideringspatiotemporalcorrelations AT lingjialiu urbanlinktraveltimepredictionbasedonagradientboostingmethodconsideringspatiotemporalcorrelations |