Network SpaceTime AI: Concepts, Methods and Applications
SpacetimeAI and GeoAI are currently hot topics, applying the latest algorithms in computer science, such as deep learning, to spatiotemporal data. Although deep learning algorithms have been successfully applied to raster data due to their natural applicability to image processing, their application...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Surveying and Mapping Press
2022-09-01
|
| Series: | Journal of Geodesy and Geoinformation Science |
| Subjects: | |
| Online Access: | http://jggs.chinasmp.com/fileup/2096-5990/PDF/1668663213341-859404354.pdf |
| _version_ | 1811224706440757248 |
|---|---|
| author | Tao CHENG,Yang ZHANG,James HAWORTH |
| author_facet | Tao CHENG,Yang ZHANG,James HAWORTH |
| author_sort | Tao CHENG,Yang ZHANG,James HAWORTH |
| collection | DOAJ |
| description | SpacetimeAI and GeoAI are currently hot topics, applying the latest algorithms in computer science, such as deep learning, to spatiotemporal data. Although deep learning algorithms have been successfully applied to raster data due to their natural applicability to image processing, their applications in other spatial and space-time data types are still immature. This paper sets up the proposition of using a network (&graph)-based framework as a generic spatial structure to present space-time processes that are usually represented by the points, polylines, and polygons. We illustrate network and graph-based SpaceTimeAI, from graph-based deep learning for prediction, to space-time clustering and optimisation. These applications demonstrate the advantages of network (graph)-based SpacetimeAI in the fields of transport&mobility, crime&policing, and public health. |
| first_indexed | 2024-04-12T08:52:31Z |
| format | Article |
| id | doaj.art-23b1df83e94a46e0a1b0e558af804df8 |
| institution | Directory Open Access Journal |
| issn | 2096-5990 |
| language | English |
| last_indexed | 2024-04-12T08:52:31Z |
| publishDate | 2022-09-01 |
| publisher | Surveying and Mapping Press |
| record_format | Article |
| series | Journal of Geodesy and Geoinformation Science |
| spelling | doaj.art-23b1df83e94a46e0a1b0e558af804df82022-12-22T03:39:31ZengSurveying and Mapping PressJournal of Geodesy and Geoinformation Science2096-59902022-09-0153789210.11947/j.JGGS.2022.0309Network SpaceTime AI: Concepts, Methods and ApplicationsTao CHENG,Yang ZHANG,James HAWORTH0SpaceTimeLab, Department of Civil, Environmental and Geomatic Engineering, University College London, London WC1E 6BT, UKSpacetimeAI and GeoAI are currently hot topics, applying the latest algorithms in computer science, such as deep learning, to spatiotemporal data. Although deep learning algorithms have been successfully applied to raster data due to their natural applicability to image processing, their applications in other spatial and space-time data types are still immature. This paper sets up the proposition of using a network (&graph)-based framework as a generic spatial structure to present space-time processes that are usually represented by the points, polylines, and polygons. We illustrate network and graph-based SpaceTimeAI, from graph-based deep learning for prediction, to space-time clustering and optimisation. These applications demonstrate the advantages of network (graph)-based SpacetimeAI in the fields of transport&mobility, crime&policing, and public health.http://jggs.chinasmp.com/fileup/2096-5990/PDF/1668663213341-859404354.pdf|spatiotemporal intelligence|network|graph|deep learning|spatiotemporal prediction|spatiotemporal clustering|spatiotemporal optimization |
| spellingShingle | Tao CHENG,Yang ZHANG,James HAWORTH Network SpaceTime AI: Concepts, Methods and Applications Journal of Geodesy and Geoinformation Science |spatiotemporal intelligence|network|graph|deep learning|spatiotemporal prediction|spatiotemporal clustering|spatiotemporal optimization |
| title | Network SpaceTime AI: Concepts, Methods and Applications |
| title_full | Network SpaceTime AI: Concepts, Methods and Applications |
| title_fullStr | Network SpaceTime AI: Concepts, Methods and Applications |
| title_full_unstemmed | Network SpaceTime AI: Concepts, Methods and Applications |
| title_short | Network SpaceTime AI: Concepts, Methods and Applications |
| title_sort | network spacetime ai concepts methods and applications |
| topic | |spatiotemporal intelligence|network|graph|deep learning|spatiotemporal prediction|spatiotemporal clustering|spatiotemporal optimization |
| url | http://jggs.chinasmp.com/fileup/2096-5990/PDF/1668663213341-859404354.pdf |
| work_keys_str_mv | AT taochengyangzhangjameshaworth networkspacetimeaiconceptsmethodsandapplications |