Institutional Repository of Key Laboratory of Ocean Circulation and Wave Studies, Institute of Oceanology, Chinese Academy of Sciences
| A hybrid integrated deep learning model for the prediction of citywide spatio-temporal flow volumes | |
| Ren, Yibin1,2,3; Chen, Huanfa4; Han, Yong5,6; Cheng, Tao7; Zhang, Yang7; Chen, Ge5,6 | |
| 2019-08-15 | |
| Source Publication | INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE
 |
| ISSN | 1365-8816 |
| Pages | 22 |
| Corresponding Author | Han, Yong(yonghan@ouc.edu.cn) |
| Abstract | The spatio-temporal residual network (ST-ResNet) leverages the power of deep learning (DL) for predicting the volume of citywide spatio-temporal flows. However, this model, neglects the dynamic dependency of the input flows in the temporal dimension, which affects what spatio-temporal features may be captured in the result. This study introduces a long short-term memory (LSTM) neural network into the ST-ResNet to form a hybrid integrated-DL model to predict the volumes of citywide spatio-temporal flows (called HIDLST). The new model can dynamically learn the temporal dependency among flows via the feedback connection in the LSTM to improve accurate captures of spatio-temporal features in the flows. We test the HIDLST model by predicting the volumes of citywide taxi flows in Beijing, China. We tune the hyperparameters of the HIDLST model to optimize the prediction accuracy. A comparative study shows that the proposed model consistently outperforms ST-ResNet and several other typical DL-based models on prediction accuracy. Furthermore, we discuss the distribution of prediction errors and the contributions of the different spatio-temporal patterns. |
| Keyword | Spatio-temporal flow volume prediction deep learning LSTM ResNet |
| DOI | 10.1080/13658816.2019.1652303 |
| Indexed By | SCI |
| Language | 英语 |
| Funding Project | Science and Technology Project of Qingdao[16-6-2-61-NSH] ; China Scholarship Council (CSC) |
| WOS Research Area | Computer Science ; Geography ; Physical Geography ; Information Science & Library Science |
| WOS Subject | Computer Science, Information Systems ; Geography ; Geography, Physical ; Information Science & Library Science |
| WOS ID | WOS:000481199600001 |
| Publisher | TAYLOR & FRANCIS LTD |
| Citation statistics | |
| Document Type | 期刊论文 |
| Identifier | http://ir.qdio.ac.cn/handle/337002/162331 |
| Collection | 海洋环流与波动重点实验室 |
| Corresponding Author | Han, Yong |
| Affiliation | 1.Chinese Acad Sci, CAS Key Lab Ocean Circulat & Waves, Inst Oceanol, Qingdao, Shandong, Peoples R China 2.Chinese Acad Sci, Ctr Ocean Mega Sci, Qingdao, Shandong, Peoples R China 3.Qingdao Natl Lab Marine, Pilot Natl Lab Marine Sci & Technol, Qingdao, Shandong, Peoples R China 4.UCL, Ctr Adv Spatial Anal, London, England 5.Ocean Univ China, Coll Informat Sci & Engn, Qingdao Collaborat Innovat Ctr Marine Sci & Techn, Qingdao, Shandong, Peoples R China 6.Qingdao Natl Lab Marine, Lab Reg Oceanog & Numer Modeling, Qingdao, Shandong, Peoples R China 7.UCL, Dept Civil Environm & Geomat Engn, SpaceTimeLab, London, England |
| First Author Affilication | Institute of Oceanology, Chinese Academy of Sciences |
| Recommended Citation GB/T 7714 | Ren, Yibin,Chen, Huanfa,Han, Yong,et al. A hybrid integrated deep learning model for the prediction of citywide spatio-temporal flow volumes[J]. INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE,2019:22. |
| APA | Ren, Yibin,Chen, Huanfa,Han, Yong,Cheng, Tao,Zhang, Yang,&Chen, Ge.(2019).A hybrid integrated deep learning model for the prediction of citywide spatio-temporal flow volumes.INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE,22. |
| MLA | Ren, Yibin,et al."A hybrid integrated deep learning model for the prediction of citywide spatio-temporal flow volumes".INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE (2019):22. |
| Files in This Item: | ||||||
| File Name/Size | DocType | Version | Access | License | ||
| A hybrid integrated （3526KB） | 期刊论文 | 出版稿 | 开放获取 | CC BY-NC-SA | View Application Full Text | |
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment