A fusion model of temporal graph attention network and machine learning for inferring commuting flow from human activity intensity dynamics
Accurately estimating commuting flow is essential for optimizing urban planning and traffic design. The latest graph neural network (GNN) model with the encoder-decoder-predictor components has several limitations. First, it ignores the temporal dependency of node features for node embedding. Second...
| Hoofdauteurs: | , , , |
|---|---|
| Formaat: | Artikel |
| Taal: | English |
| Gepubliceerd in: |
Elsevier
2024-02-01
|
| Reeks: | International Journal of Applied Earth Observations and Geoinformation |
| Onderwerpen: | |
| Online toegang: | http://www.sciencedirect.com/science/article/pii/S156984322300434X |
| _version_ | 1827384127639257088 |
|---|---|
| author | Qingli Shi Li Zhuo Haiyan Tao Junying Yang |
| author_facet | Qingli Shi Li Zhuo Haiyan Tao Junying Yang |
| author_sort | Qingli Shi |
| collection | DOAJ |
| description | Accurately estimating commuting flow is essential for optimizing urban planning and traffic design. The latest graph neural network (GNN) model with the encoder-decoder-predictor components has several limitations. First, it ignores the temporal dependency of node features for node embedding. Second, different estimation methods used in the decoder and predictor make it difficult to distinguish the contribution of node embedding or estimation method to flow estimation. Third, finer-grained socio-economic features of nodes are difficult to obtain due to low data availability. To address these problems, this study proposes a fusion model of temporal graph attention network and machine learning (TGAT-ML) to infer commuting flow from dynamic human activity intensity distribution. The model first constructs a commuting network with temporal human activity intensity as node features. A temporal graph attention network is then developed to capture the spatiotemporal dependency. The learned node embedding is generated by using a machine learning method in the decoder. Finally, based on learned node embedding and machine learning method used in the decoder, the commuting flow intensity is estimated. Results from an empirical study using the Baidu heat map data of Guangzhou city indicate that the proposed fusion model TGAT-ML outperforms all other baseline models. This study proves that the model performance can be significantly enhanced by determining the edge existence through commuting time-based approach, integrating temporal convolution with graph convolution, and unifying flow estimation method in both decoder and predictor. This work enables commuting flow estimation from dynamic human activity intensity and broadens existing flow generation research in terms of data and methodology. |
| first_indexed | 2024-03-08T14:50:12Z |
| format | Article |
| id | doaj.art-7d557ccfcf284cf0927a6180eb6b7fee |
| institution | Directory Open Access Journal |
| issn | 1569-8432 |
| language | English |
| last_indexed | 2024-03-08T14:50:12Z |
| publishDate | 2024-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Applied Earth Observations and Geoinformation |
| spelling | doaj.art-7d557ccfcf284cf0927a6180eb6b7fee2024-01-11T04:30:26ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322024-02-01126103610A fusion model of temporal graph attention network and machine learning for inferring commuting flow from human activity intensity dynamicsQingli Shi0Li Zhuo1Haiyan Tao2Junying Yang3Guangdong Provincial Engineering Research Center for Public Security and Disaster, School of Geography and Planning, Sun Yat-sen University, Guangzhou 510006, ChinaGuangdong Provincial Engineering Research Center for Public Security and Disaster, School of Geography and Planning, Sun Yat-sen University, Guangzhou 510006, China; Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai), Zhuhai 519082, China; Corresponding author at: Guangdong Provincial Engineering Research Center for Public Security and Disaster, School of Geography and Planning, Sun Yat-sen University, Guangzhou 510006, China.Guangdong Provincial Engineering Research Center for Public Security and Disaster, School of Geography and Planning, Sun Yat-sen University, Guangzhou 510006, ChinaGuangdong Provincial Engineering Research Center for Public Security and Disaster, School of Geography and Planning, Sun Yat-sen University, Guangzhou 510006, ChinaAccurately estimating commuting flow is essential for optimizing urban planning and traffic design. The latest graph neural network (GNN) model with the encoder-decoder-predictor components has several limitations. First, it ignores the temporal dependency of node features for node embedding. Second, different estimation methods used in the decoder and predictor make it difficult to distinguish the contribution of node embedding or estimation method to flow estimation. Third, finer-grained socio-economic features of nodes are difficult to obtain due to low data availability. To address these problems, this study proposes a fusion model of temporal graph attention network and machine learning (TGAT-ML) to infer commuting flow from dynamic human activity intensity distribution. The model first constructs a commuting network with temporal human activity intensity as node features. A temporal graph attention network is then developed to capture the spatiotemporal dependency. The learned node embedding is generated by using a machine learning method in the decoder. Finally, based on learned node embedding and machine learning method used in the decoder, the commuting flow intensity is estimated. Results from an empirical study using the Baidu heat map data of Guangzhou city indicate that the proposed fusion model TGAT-ML outperforms all other baseline models. This study proves that the model performance can be significantly enhanced by determining the edge existence through commuting time-based approach, integrating temporal convolution with graph convolution, and unifying flow estimation method in both decoder and predictor. This work enables commuting flow estimation from dynamic human activity intensity and broadens existing flow generation research in terms of data and methodology.http://www.sciencedirect.com/science/article/pii/S156984322300434XTemporal convolution networkGraph attention networkHuman activity intensity dynamicsCommuting flow |
| spellingShingle | Qingli Shi Li Zhuo Haiyan Tao Junying Yang A fusion model of temporal graph attention network and machine learning for inferring commuting flow from human activity intensity dynamics International Journal of Applied Earth Observations and Geoinformation Temporal convolution network Graph attention network Human activity intensity dynamics Commuting flow |
| title | A fusion model of temporal graph attention network and machine learning for inferring commuting flow from human activity intensity dynamics |
| title_full | A fusion model of temporal graph attention network and machine learning for inferring commuting flow from human activity intensity dynamics |
| title_fullStr | A fusion model of temporal graph attention network and machine learning for inferring commuting flow from human activity intensity dynamics |
| title_full_unstemmed | A fusion model of temporal graph attention network and machine learning for inferring commuting flow from human activity intensity dynamics |
| title_short | A fusion model of temporal graph attention network and machine learning for inferring commuting flow from human activity intensity dynamics |
| title_sort | fusion model of temporal graph attention network and machine learning for inferring commuting flow from human activity intensity dynamics |
| topic | Temporal convolution network Graph attention network Human activity intensity dynamics Commuting flow |
| url | http://www.sciencedirect.com/science/article/pii/S156984322300434X |
| work_keys_str_mv | AT qinglishi afusionmodeloftemporalgraphattentionnetworkandmachinelearningforinferringcommutingflowfromhumanactivityintensitydynamics AT lizhuo afusionmodeloftemporalgraphattentionnetworkandmachinelearningforinferringcommutingflowfromhumanactivityintensitydynamics AT haiyantao afusionmodeloftemporalgraphattentionnetworkandmachinelearningforinferringcommutingflowfromhumanactivityintensitydynamics AT junyingyang afusionmodeloftemporalgraphattentionnetworkandmachinelearningforinferringcommutingflowfromhumanactivityintensitydynamics AT qinglishi fusionmodeloftemporalgraphattentionnetworkandmachinelearningforinferringcommutingflowfromhumanactivityintensitydynamics AT lizhuo fusionmodeloftemporalgraphattentionnetworkandmachinelearningforinferringcommutingflowfromhumanactivityintensitydynamics AT haiyantao fusionmodeloftemporalgraphattentionnetworkandmachinelearningforinferringcommutingflowfromhumanactivityintensitydynamics AT junyingyang fusionmodeloftemporalgraphattentionnetworkandmachinelearningforinferringcommutingflowfromhumanactivityintensitydynamics |