{"id":2885,"date":"2023-01-10T05:00:00","date_gmt":"2023-01-10T04:00:00","guid":{"rendered":"https:\/\/ingenius.ecoledesponts.fr\/?p=2885"},"modified":"2025-07-29T14:39:35","modified_gmt":"2025-07-29T12:39:35","slug":"artificial-intelligence-for-mobility-analysis","status":"publish","type":"post","link":"https:\/\/ingenius.ecoledesponts.fr\/en\/articles\/artificial-intelligence-for-mobility-analysis\/","title":{"rendered":"Artificial intelligence for mobility analysis"},"content":{"rendered":"\n\n\n
\"\"
\u00a9 Elenabsl (source : Adobe Stock)<\/figcaption><\/figure>\n\n\n\n

Mobility, a fundamental need for human beings to fulfill their social desires, is an essential aspect to be taken into consideration when developing the concept of the smart city. An understanding of mobility phenomena is vital in order to understand the urban dynamics that characterize how society functions. Based on the mobility traces produced by various GPS receivers, in-depth personal trip information is increasingly available for AI to acquire  knowledge about human mobility (e.g. patterns, regularities, and preferences). This can be further facilitated with the advancement of greater computing power, the greater availability of portable location-acquisition equipment, and richer cartographical data emerging in the era of digitalization. Although the integration of AI is still in its early stages, the advantages compared to conventional mobility analyses based on traditional travel logs and surveys are prominent, including strong identification power and automatic discovery capabilities. The usage of AI and big data can contribute to overcoming many traditional limitations in mobility analysis in terms of real-time processing and large-scale investigation. Generally speaking, mobility analytics can be conducted on two levels: individual behavior analysis and spatial analysis.<\/p>\n\n\n\n

Individual behavior analysis<\/strong><\/h2>\n\n\n\n

People choose their destinations and travel between those places based on their social needs. Individual mobility behavior and decision-making are by no means formed randomly but are in fact based on certain rationale according to their sociodemographic context. In mobility forecasting, it is important to first recognize the mobility generation from different classes of mobility makers and then investigate the mobility-making based on their needs and utilities. This is where AI can be introduced, as 24\/7 mobility trace collecting (see Fig 1) can significantly enrich the information on how people move around and thus help to investigate the composition of mobility demand. Technically, full paths of mobility trajectories can be collected in short time intervals of up to a few seconds, resulting in rich yet massive datasets. Traditional analytical approaches often struggle to handle such full path data, while by contrast, AI with unsupervised learning (clustering) could help enormously in establishing trajectory patterns, e.g. finding out similar mobility makers and the regularity with which they move around<\/a>. Moreover, by calculating the repetition of trips connected to some places over days, it\u2019s also possible to use AI to efficiently detect the significant places<\/a> (also called anchor places) in an individual\u2019s social life, such as home, the workplace, favorite spots etc., thus assisting the analysis of many important traffic issues such as commuting flows, recreational traveling etc.<\/p>\n\n\n\n

Mobility identification from GPS traces<\/strong><\/h3>\n\n\n\n
\"\"
\u00a9 Danyang Sun, 2022<\/figcaption><\/figure>\n\n\n\n

Fig 1. Mobility identification from GPS traces<\/p>\n\n\n\n

Spatial analysis<\/strong><\/h2>\n\n\n\n

The spatial movements of individuals aggregate in flow streams: such collective patterns interplay with the related territorial configuration, contributing to land-use and transport interaction. \u00a0Firstly, the territorial spaces are occupied by different social functions, such as commercial zone, residential zone, amenities, other zones of interest etc. As mobility generation is highly correlated with the spatial configuration, investigating the characteristics of mobility flows can help to reveal such functional occupations of spaces so as to monitor the evolution of land uses. This can be achieved by using AI to characterize the patterns of temporal flows of trips and activity duration connected to the space. Besides, after knowing the space functions, it is also important to analyze the relations between different spaces to understand the city structures. A typical approach is to identify core-periphery patterns<\/a>. Based on identified individual anchor places, by analyzing the quantity, their density distribution can be modeled over the space, from which one can identify employment hubs or other hotspots. The mobility flows between places can be further used to build topological graphs. By using graph mining approaches based on the flow volumes, spatial communities can be delineated to provide hints for regional planning and cooperation (see Fig below).<\/p>\n\n\n\n

Identification of employment hubs and catchment areas based on home-to-work commuting flow<\/h3>\n\n\n\n
\"\"
\u00a9 Danyang Sun, 2022<\/figcaption><\/figure>\n\n\n\n

Renovate the mobility landscape<\/strong><\/strong><\/h2>\n\n\n\n

Besides its usage in mobility analytics, today AI has also been widely adopted in solving many classic traffic problems, such as predicting travel times, detecting incidents, monitoring network performances, generating traffic reports etc. The easy updatable essence of modern data allows the possibility of quick responses to mobility changes, benefiting adaptive and ad-hoc transportation upgrades. Various mobility innovations have also been made possible by integrating the computing power to enable more efficient mobility services, including Mobility as a Service and On-demand Transportation. In conclusion, AI and its applications to big data offer us unparalleled opportunities to renovate the mobility landscape. If used responsibly, more possible solutions will become available to design an efficient, coherent, and resilient system for human mobility, contributing to the smart and sustainable development of our cities.<\/p>\n\n\n\n

Text adapted from an article published in Le Cahier des Ponts n\u00b06<\/a>, Les Mobilit\u00e9s, August 2022<\/strong>.<\/p>\n\n\n\n

<\/div>\n","protected":false},"excerpt":{"rendered":"

Mobility, a fundamental need for human beings to fulfill their social desires, is an essential aspect to be taken into […]<\/p>\n","protected":false},"author":6,"featured_media":1805,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_related_content_post":[],"_related_content_subject":[690,692],"_related_content_author":[2888],"_related_content_category":[1720,1716],"_related_content_folder":[4200],"_excerpt":"Artificial intelligence (AI) uses computers\u2019 abilities to automatically learn \u201cknowledge\u201d from data. It has attracted unprecedented attention in recent years, with an increasingly diverse functional applicability. This includes territory analytics, with AI beginning to play a key role in urban planning, transportation systems, land uses, and environmental sustainability thanks to new concepts like \u201cSmart City\u201d and \u201cUrban Computing\u201d.<\/a> How can AI help us to better analyze city dynamics, especially with respect to mobility?","_duration":4,"_manual_duration":false,"footnotes":""},"article-types":[27],"class_list":["post-2885","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","article-types-folder"],"has_blocks":true,"block_data":[{"blockName":"enpc\/excerpt","attrs":{"lock":[],"metadata":[],"className":"","style":""},"innerBlocks":[],"innerHTML":"","innerContent":[],"rendered":""},{"blockName":"core\/image","attrs":{"id":1804,"sizeSlug":"large","linkDestination":"none","align":"wide","blob":"","url":"https:\/\/ingenius.ecoledesponts.fr\/wp-content\/uploads\/2022\/08\/CdP_N6_Couv-1024x512.jpeg","alt":"","caption":"\u00a9 Elenabsl (source : Adobe Stock)","lightbox":[],"title":"","href":"","rel":"","linkClass":"","width":"","height":"","aspectRatio":"","scale":"","linkTarget":"","lock":[],"metadata":[],"className":"wp-block-image alignwide size-large","style":"","borderColor":"","anchor":""},"innerBlocks":[],"innerHTML":"\n

\"\"
\u00a9 Elenabsl (source : Adobe Stock)<\/figcaption><\/figure>\n","innerContent":["\n
\"\"
\u00a9 Elenabsl (source : Adobe Stock)<\/figcaption><\/figure>\n"],"rendered":"\n
\"\"
\u00a9 Elenabsl (source : Adobe Stock)<\/figcaption><\/figure>\n"},{"blockName":"core\/paragraph","attrs":{"align":"","content":"Mobility, a fundamental need for human beings to fulfill their social desires, is an essential aspect to be taken into consideration when developing the concept of the smart city. An understanding of mobility phenomena is vital in order to understand the urban dynamics that characterize how society functions. Based on the mobility traces produced by various GPS receivers, in-depth personal trip information is increasingly available for AI to acquire\u00a0 knowledge about human mobility (e.g. patterns, regularities, and preferences). This can be further facilitated with the advancement of greater computing power, the greater availability of portable location-acquisition equipment, and richer cartographical data emerging in the era of digitalization. Although the integration of AI is still in its early stages, the advantages compared to conventional mobility analyses based on traditional travel logs and surveys are prominent, including strong identification power and automatic discovery capabilities. The usage of AI and big data can contribute to overcoming many traditional limitations in mobility analysis in terms of real-time processing and large-scale investigation. Generally speaking, mobility analytics can be conducted on two levels: individual behavior analysis and spatial analysis.","dropCap":false,"placeholder":"","direction":"","lock":[],"metadata":[],"className":"","style":"","backgroundColor":"","textColor":"","gradient":"","fontSize":"","fontFamily":"","borderColor":"","anchor":""},"innerBlocks":[],"innerHTML":"\n

Mobility, a fundamental need for human beings to fulfill their social desires, is an essential aspect to be taken into consideration when developing the concept of the smart city. An understanding of mobility phenomena is vital in order to understand the urban dynamics that characterize how society functions. Based on the mobility traces produced by various GPS receivers, in-depth personal trip information is increasingly available for AI to acquire  knowledge about human mobility (e.g. patterns, regularities, and preferences). This can be further facilitated with the advancement of greater computing power, the greater availability of portable location-acquisition equipment, and richer cartographical data emerging in the era of digitalization. Although the integration of AI is still in its early stages, the advantages compared to conventional mobility analyses based on traditional travel logs and surveys are prominent, including strong identification power and automatic discovery capabilities. The usage of AI and big data can contribute to overcoming many traditional limitations in mobility analysis in terms of real-time processing and large-scale investigation. Generally speaking, mobility analytics can be conducted on two levels: individual behavior analysis and spatial analysis.<\/p>\n","innerContent":["\n

Mobility, a fundamental need for human beings to fulfill their social desires, is an essential aspect to be taken into consideration when developing the concept of the smart city. An understanding of mobility phenomena is vital in order to understand the urban dynamics that characterize how society functions. Based on the mobility traces produced by various GPS receivers, in-depth personal trip information is increasingly available for AI to acquire  knowledge about human mobility (e.g. patterns, regularities, and preferences). This can be further facilitated with the advancement of greater computing power, the greater availability of portable location-acquisition equipment, and richer cartographical data emerging in the era of digitalization. Although the integration of AI is still in its early stages, the advantages compared to conventional mobility analyses based on traditional travel logs and surveys are prominent, including strong identification power and automatic discovery capabilities. The usage of AI and big data can contribute to overcoming many traditional limitations in mobility analysis in terms of real-time processing and large-scale investigation. Generally speaking, mobility analytics can be conducted on two levels: individual behavior analysis and spatial analysis.<\/p>\n"],"rendered":"\n

Mobility, a fundamental need for human beings to fulfill their social desires, is an essential aspect to be taken into consideration when developing the concept of the smart city. An understanding of mobility phenomena is vital in order to understand the urban dynamics that characterize how society functions. Based on the mobility traces produced by various GPS receivers, in-depth personal trip information is increasingly available for AI to acquire  knowledge about human mobility (e.g. patterns, regularities, and preferences). This can be further facilitated with the advancement of greater computing power, the greater availability of portable location-acquisition equipment, and richer cartographical data emerging in the era of digitalization. Although the integration of AI is still in its early stages, the advantages compared to conventional mobility analyses based on traditional travel logs and surveys are prominent, including strong identification power and automatic discovery capabilities. The usage of AI and big data can contribute to overcoming many traditional limitations in mobility analysis in terms of real-time processing and large-scale investigation. Generally speaking, mobility analytics can be conducted on two levels: individual behavior analysis and spatial analysis.<\/p>\n"},{"blockName":"core\/heading","attrs":{"textColor":"red","textAlign":"","content":"Individual behavior analysis","level":2,"levelOptions":[],"placeholder":"","lock":[],"metadata":[],"align":"","className":"wp-block-heading has-red-color has-text-color","style":"","backgroundColor":"","gradient":"","fontSize":"","fontFamily":"","borderColor":"","anchor":""},"innerBlocks":[],"innerHTML":"\n

Individual behavior analysis<\/strong><\/h2>\n","innerContent":["\n

Individual behavior analysis<\/strong><\/h2>\n"],"rendered":"\n

Individual behavior analysis<\/strong><\/h2>\n"},{"blockName":"core\/paragraph","attrs":{"align":"","content":"People choose their destinations and travel between those places based on their social needs. Individual mobility behavior and decision-making are by no means formed randomly but are in fact based on certain rationale according to their sociodemographic context. In mobility forecasting, it is important to first recognize the mobility generation from different classes of mobility makers and then investigate the mobility-making based on their needs and utilities. This is where AI can be introduced, as 24\/7 mobility trace collecting (see Fig 1) can significantly enrich the information on how people move around and thus help to investigate the composition of mobility demand. Technically, full paths of mobility trajectories can be collected in short time intervals of up to a few seconds, resulting in rich yet massive datasets. Traditional analytical approaches often struggle to handle such full path data, while by contrast, AI with unsupervised learning (clustering) could help enormously in establishing trajectory patterns, e.g. finding out similar mobility makers and the regularity with which they move around. Moreover, by calculating the repetition of trips connected to some places over days, it\u2019s also possible to use AI to efficiently detect the significant places (also called anchor places) in an individual\u2019s social life, such as home, the workplace, favorite spots etc., thus assisting the analysis of many important traffic issues such as commuting flows, recreational traveling etc.","dropCap":false,"placeholder":"","direction":"","lock":[],"metadata":[],"className":"","style":"","backgroundColor":"","textColor":"","gradient":"","fontSize":"","fontFamily":"","borderColor":"","anchor":""},"innerBlocks":[],"innerHTML":"\n

People choose their destinations and travel between those places based on their social needs. Individual mobility behavior and decision-making are by no means formed randomly but are in fact based on certain rationale according to their sociodemographic context. In mobility forecasting, it is important to first recognize the mobility generation from different classes of mobility makers and then investigate the mobility-making based on their needs and utilities. This is where AI can be introduced, as 24\/7 mobility trace collecting (see Fig 1) can significantly enrich the information on how people move around and thus help to investigate the composition of mobility demand. Technically, full paths of mobility trajectories can be collected in short time intervals of up to a few seconds, resulting in rich yet massive datasets. Traditional analytical approaches often struggle to handle such full path data, while by contrast, AI with unsupervised learning (clustering) could help enormously in establishing trajectory patterns, e.g. finding out similar mobility makers and the regularity with which they move around<\/a>. Moreover, by calculating the repetition of trips connected to some places over days, it\u2019s also possible to use AI to efficiently detect the significant places<\/a> (also called anchor places) in an individual\u2019s social life, such as home, the workplace, favorite spots etc., thus assisting the analysis of many important traffic issues such as commuting flows, recreational traveling etc.<\/p>\n","innerContent":["\n

People choose their destinations and travel between those places based on their social needs. Individual mobility behavior and decision-making are by no means formed randomly but are in fact based on certain rationale according to their sociodemographic context. In mobility forecasting, it is important to first recognize the mobility generation from different classes of mobility makers and then investigate the mobility-making based on their needs and utilities. This is where AI can be introduced, as 24\/7 mobility trace collecting (see Fig 1) can significantly enrich the information on how people move around and thus help to investigate the composition of mobility demand. Technically, full paths of mobility trajectories can be collected in short time intervals of up to a few seconds, resulting in rich yet massive datasets. Traditional analytical approaches often struggle to handle such full path data, while by contrast, AI with unsupervised learning (clustering) could help enormously in establishing trajectory patterns, e.g. finding out similar mobility makers and the regularity with which they move around<\/a>. Moreover, by calculating the repetition of trips connected to some places over days, it\u2019s also possible to use AI to efficiently detect the significant places<\/a> (also called anchor places) in an individual\u2019s social life, such as home, the workplace, favorite spots etc., thus assisting the analysis of many important traffic issues such as commuting flows, recreational traveling etc.<\/p>\n"],"rendered":"\n

People choose their destinations and travel between those places based on their social needs. Individual mobility behavior and decision-making are by no means formed randomly but are in fact based on certain rationale according to their sociodemographic context. In mobility forecasting, it is important to first recognize the mobility generation from different classes of mobility makers and then investigate the mobility-making based on their needs and utilities. This is where AI can be introduced, as 24\/7 mobility trace collecting (see Fig 1) can significantly enrich the information on how people move around and thus help to investigate the composition of mobility demand. Technically, full paths of mobility trajectories can be collected in short time intervals of up to a few seconds, resulting in rich yet massive datasets. Traditional analytical approaches often struggle to handle such full path data, while by contrast, AI with unsupervised learning (clustering) could help enormously in establishing trajectory patterns, e.g. finding out similar mobility makers and the regularity with which they move around<\/a>. Moreover, by calculating the repetition of trips connected to some places over days, it\u2019s also possible to use AI to efficiently detect the significant places<\/a> (also called anchor places) in an individual\u2019s social life, such as home, the workplace, favorite spots etc., thus assisting the analysis of many important traffic issues such as commuting flows, recreational traveling etc.<\/p>\n"},{"blockName":"core\/heading","attrs":{"level":3,"textColor":"medium-grey","textAlign":"","content":"Mobility identification from GPS traces","levelOptions":[],"placeholder":"","lock":[],"metadata":[],"align":"","className":"wp-block-heading has-medium-grey-color has-text-color","style":"","backgroundColor":"","gradient":"","fontSize":"","fontFamily":"","borderColor":"","anchor":""},"innerBlocks":[],"innerHTML":"\n

Mobility identification from GPS traces<\/strong><\/h3>\n","innerContent":["\n

Mobility identification from GPS traces<\/strong><\/h3>\n"],"rendered":"\n

Mobility identification from GPS traces<\/strong><\/h3>\n"},{"blockName":"core\/image","attrs":{"id":1791,"sizeSlug":"full","linkDestination":"none","blob":"","url":"https:\/\/ingenius.ecoledesponts.fr\/wp-content\/uploads\/2022\/08\/CdP_N6_P10-11_Sun_figure1.png","alt":"","caption":"\u00a9 Danyang Sun, 2022","lightbox":[],"title":"","href":"","rel":"","linkClass":"","width":"","height":"","aspectRatio":"","scale":"","linkTarget":"","lock":[],"metadata":[],"align":"","className":"wp-block-image size-full","style":"","borderColor":"","anchor":""},"innerBlocks":[],"innerHTML":"\n
\"\"
\u00a9 Danyang Sun, 2022<\/figcaption><\/figure>\n","innerContent":["\n
\"\"
\u00a9 Danyang Sun, 2022<\/figcaption><\/figure>\n"],"rendered":"\n
\"\"
\u00a9 Danyang Sun, 2022<\/figcaption><\/figure>\n"},{"blockName":"core\/paragraph","attrs":{"align":"","content":"Fig 1. Mobility identification from GPS traces","dropCap":false,"placeholder":"","direction":"","lock":[],"metadata":[],"className":"","style":"","backgroundColor":"","textColor":"","gradient":"","fontSize":"","fontFamily":"","borderColor":"","anchor":""},"innerBlocks":[],"innerHTML":"\n

Fig 1. Mobility identification from GPS traces<\/p>\n","innerContent":["\n

Fig 1. Mobility identification from GPS traces<\/p>\n"],"rendered":"\n

Fig 1. Mobility identification from GPS traces<\/p>\n"},{"blockName":"core\/heading","attrs":{"style":{"elements":{"link":{"color":{"text":"var:preset|color|red"}}}},"textColor":"red","textAlign":"","content":"Spatial analysis","level":2,"levelOptions":[],"placeholder":"","lock":[],"metadata":[],"align":"","className":"wp-block-heading has-red-color has-text-color has-link-color","backgroundColor":"","gradient":"","fontSize":"","fontFamily":"","borderColor":"","anchor":""},"innerBlocks":[],"innerHTML":"\n

Spatial analysis<\/strong><\/h2>\n","innerContent":["\n

Spatial analysis<\/strong><\/h2>\n"],"rendered":"\n

Spatial analysis<\/strong><\/h2>\n"},{"blockName":"core\/paragraph","attrs":{"align":"","content":"The spatial movements of individuals aggregate in flow streams: such collective patterns interplay with the related territorial configuration, contributing to land-use and transport interaction. \u00a0Firstly, the territorial spaces are occupied by different social functions, such as commercial zone, residential zone, amenities, other zones of interest etc. As mobility generation is highly correlated with the spatial configuration, investigating the characteristics of mobility flows can help to reveal such functional occupations of spaces so as to monitor the evolution of land uses. This can be achieved by using AI to characterize the patterns of temporal flows of trips and activity duration connected to the space. Besides, after knowing the space functions, it is also important to analyze the relations between different spaces to understand the city structures. A typical approach is to identify core-periphery patterns. Based on identified individual anchor places, by analyzing the quantity, their density distribution can be modeled over the space, from which one can identify employment hubs or other hotspots. The mobility flows between places can be further used to build topological graphs. By using graph mining approaches based on the flow volumes, spatial communities can be delineated to provide hints for regional planning and cooperation (see Fig below).","dropCap":false,"placeholder":"","direction":"","lock":[],"metadata":[],"className":"","style":"","backgroundColor":"","textColor":"","gradient":"","fontSize":"","fontFamily":"","borderColor":"","anchor":""},"innerBlocks":[],"innerHTML":"\n

The spatial movements of individuals aggregate in flow streams: such collective patterns interplay with the related territorial configuration, contributing to land-use and transport interaction. \u00a0Firstly, the territorial spaces are occupied by different social functions, such as commercial zone, residential zone, amenities, other zones of interest etc. As mobility generation is highly correlated with the spatial configuration, investigating the characteristics of mobility flows can help to reveal such functional occupations of spaces so as to monitor the evolution of land uses. This can be achieved by using AI to characterize the patterns of temporal flows of trips and activity duration connected to the space. Besides, after knowing the space functions, it is also important to analyze the relations between different spaces to understand the city structures. A typical approach is to identify core-periphery patterns<\/a>. Based on identified individual anchor places, by analyzing the quantity, their density distribution can be modeled over the space, from which one can identify employment hubs or other hotspots. The mobility flows between places can be further used to build topological graphs. By using graph mining approaches based on the flow volumes, spatial communities can be delineated to provide hints for regional planning and cooperation (see Fig below).<\/p>\n","innerContent":["\n

The spatial movements of individuals aggregate in flow streams: such collective patterns interplay with the related territorial configuration, contributing to land-use and transport interaction. \u00a0Firstly, the territorial spaces are occupied by different social functions, such as commercial zone, residential zone, amenities, other zones of interest etc. As mobility generation is highly correlated with the spatial configuration, investigating the characteristics of mobility flows can help to reveal such functional occupations of spaces so as to monitor the evolution of land uses. This can be achieved by using AI to characterize the patterns of temporal flows of trips and activity duration connected to the space. Besides, after knowing the space functions, it is also important to analyze the relations between different spaces to understand the city structures. A typical approach is to identify core-periphery patterns<\/a>. Based on identified individual anchor places, by analyzing the quantity, their density distribution can be modeled over the space, from which one can identify employment hubs or other hotspots. The mobility flows between places can be further used to build topological graphs. By using graph mining approaches based on the flow volumes, spatial communities can be delineated to provide hints for regional planning and cooperation (see Fig below).<\/p>\n"],"rendered":"\n

The spatial movements of individuals aggregate in flow streams: such collective patterns interplay with the related territorial configuration, contributing to land-use and transport interaction. \u00a0Firstly, the territorial spaces are occupied by different social functions, such as commercial zone, residential zone, amenities, other zones of interest etc. As mobility generation is highly correlated with the spatial configuration, investigating the characteristics of mobility flows can help to reveal such functional occupations of spaces so as to monitor the evolution of land uses. This can be achieved by using AI to characterize the patterns of temporal flows of trips and activity duration connected to the space. Besides, after knowing the space functions, it is also important to analyze the relations between different spaces to understand the city structures. A typical approach is to identify core-periphery patterns<\/a>. Based on identified individual anchor places, by analyzing the quantity, their density distribution can be modeled over the space, from which one can identify employment hubs or other hotspots. The mobility flows between places can be further used to build topological graphs. By using graph mining approaches based on the flow volumes, spatial communities can be delineated to provide hints for regional planning and cooperation (see Fig below).<\/p>\n"},{"blockName":"core\/heading","attrs":{"level":3,"textColor":"medium-grey","textAlign":"","content":"Identification of employment hubs and catchment areas based on home-to-work commuting flow","levelOptions":[],"placeholder":"","lock":[],"metadata":[],"align":"","className":"wp-block-heading has-medium-grey-color has-text-color","style":"","backgroundColor":"","gradient":"","fontSize":"","fontFamily":"","borderColor":"","anchor":""},"innerBlocks":[],"innerHTML":"\n

Identification of employment hubs and catchment areas based on home-to-work commuting flow<\/h3>\n","innerContent":["\n

Identification of employment hubs and catchment areas based on home-to-work commuting flow<\/h3>\n"],"rendered":"\n

Identification of employment hubs and catchment areas based on home-to-work commuting flow<\/h3>\n"},{"blockName":"core\/image","attrs":{"id":1793,"sizeSlug":"large","linkDestination":"none","blob":"","url":"https:\/\/ingenius.ecoledesponts.fr\/wp-content\/uploads\/2022\/08\/CdP_N6_P10-11_Sun_figure2-1024x407.png","alt":"","caption":"\u00a9 Danyang Sun, 2022","lightbox":[],"title":"","href":"","rel":"","linkClass":"","width":"","height":"","aspectRatio":"","scale":"","linkTarget":"","lock":[],"metadata":[],"align":"","className":"wp-block-image size-large","style":"","borderColor":"","anchor":""},"innerBlocks":[],"innerHTML":"\n
\"\"
\u00a9 Danyang Sun, 2022<\/figcaption><\/figure>\n","innerContent":["\n
\"\"
\u00a9 Danyang Sun, 2022<\/figcaption><\/figure>\n"],"rendered":"\n
\"\"
\u00a9 Danyang Sun, 2022<\/figcaption><\/figure>\n"},{"blockName":"core\/heading","attrs":{"textColor":"red","textAlign":"","content":"Renovate the mobility landscape","level":2,"levelOptions":[],"placeholder":"","lock":[],"metadata":[],"align":"","className":"wp-block-heading has-red-color has-text-color","style":"","backgroundColor":"","gradient":"","fontSize":"","fontFamily":"","borderColor":"","anchor":""},"innerBlocks":[],"innerHTML":"\n

Renovate the mobility landscape<\/strong><\/strong><\/h2>\n","innerContent":["\n

Renovate the mobility landscape<\/strong><\/strong><\/h2>\n"],"rendered":"\n

Renovate the mobility landscape<\/strong><\/strong><\/h2>\n"},{"blockName":"core\/paragraph","attrs":{"align":"","content":"Besides its usage in mobility analytics, today AI has also been widely adopted in solving many classic traffic problems, such as predicting travel times, detecting incidents, monitoring network performances, generating traffic reports etc. The easy updatable essence of modern data allows the possibility of quick responses to mobility changes, benefiting adaptive and ad-hoc transportation upgrades. Various mobility innovations have also been made possible by integrating the computing power to enable more efficient mobility services, including Mobility as a Service and On-demand Transportation. In conclusion, AI and its applications to big data offer us unparalleled opportunities to renovate the mobility landscape. If used responsibly, more possible solutions will become available to design an efficient, coherent, and resilient system for human mobility, contributing to the smart and sustainable development of our cities.","dropCap":false,"placeholder":"","direction":"","lock":[],"metadata":[],"className":"","style":"","backgroundColor":"","textColor":"","gradient":"","fontSize":"","fontFamily":"","borderColor":"","anchor":""},"innerBlocks":[],"innerHTML":"\n

Besides its usage in mobility analytics, today AI has also been widely adopted in solving many classic traffic problems, such as predicting travel times, detecting incidents, monitoring network performances, generating traffic reports etc. The easy updatable essence of modern data allows the possibility of quick responses to mobility changes, benefiting adaptive and ad-hoc transportation upgrades. Various mobility innovations have also been made possible by integrating the computing power to enable more efficient mobility services, including Mobility as a Service and On-demand Transportation. In conclusion, AI and its applications to big data offer us unparalleled opportunities to renovate the mobility landscape. If used responsibly, more possible solutions will become available to design an efficient, coherent, and resilient system for human mobility, contributing to the smart and sustainable development of our cities.<\/p>\n","innerContent":["\n

Besides its usage in mobility analytics, today AI has also been widely adopted in solving many classic traffic problems, such as predicting travel times, detecting incidents, monitoring network performances, generating traffic reports etc. The easy updatable essence of modern data allows the possibility of quick responses to mobility changes, benefiting adaptive and ad-hoc transportation upgrades. Various mobility innovations have also been made possible by integrating the computing power to enable more efficient mobility services, including Mobility as a Service and On-demand Transportation. In conclusion, AI and its applications to big data offer us unparalleled opportunities to renovate the mobility landscape. If used responsibly, more possible solutions will become available to design an efficient, coherent, and resilient system for human mobility, contributing to the smart and sustainable development of our cities.<\/p>\n"],"rendered":"\n

Besides its usage in mobility analytics, today AI has also been widely adopted in solving many classic traffic problems, such as predicting travel times, detecting incidents, monitoring network performances, generating traffic reports etc. The easy updatable essence of modern data allows the possibility of quick responses to mobility changes, benefiting adaptive and ad-hoc transportation upgrades. Various mobility innovations have also been made possible by integrating the computing power to enable more efficient mobility services, including Mobility as a Service and On-demand Transportation. In conclusion, AI and its applications to big data offer us unparalleled opportunities to renovate the mobility landscape. If used responsibly, more possible solutions will become available to design an efficient, coherent, and resilient system for human mobility, contributing to the smart and sustainable development of our cities.<\/p>\n"},{"blockName":"core\/paragraph","attrs":{"textColor":"medium-grey","align":"","content":"Text adapted from an article published in Le Cahier des Ponts n\u00b06, Les Mobilit\u00e9s, August 2022.","dropCap":false,"placeholder":"","direction":"","lock":[],"metadata":[],"className":"has-medium-grey-color has-text-color","style":"","backgroundColor":"","gradient":"","fontSize":"","fontFamily":"","borderColor":"","anchor":""},"innerBlocks":[],"innerHTML":"\n

Text adapted from an article published in Le Cahier des Ponts n\u00b06<\/a>, Les Mobilit\u00e9s, August 2022<\/strong>.<\/p>\n","innerContent":["\n

Text adapted from an article published in Le Cahier des Ponts n\u00b06<\/a>, Les Mobilit\u00e9s, August 2022<\/strong>.<\/p>\n"],"rendered":"\n

Text adapted from an article published in Le Cahier des Ponts n\u00b06<\/a>, Les Mobilit\u00e9s, August 2022<\/strong>.<\/p>\n"},{"blockName":"core\/spacer","attrs":{"height":"0px","width":"","lock":[],"metadata":[],"className":"wp-block-spacer","style":"height:0px","anchor":""},"innerBlocks":[],"innerHTML":"\n

<\/div>\n","innerContent":["\n
<\/div>\n"],"rendered":"\n
<\/div>\n"}],"seo":{"title":"Artificial intelligence for mobility analysis"},"media":{"img":"\"\"","src":"https:\/\/ingenius.ecoledesponts.fr\/wp-content\/uploads\/2022\/08\/CdP_N6_Couv-scaled.jpeg"},"url":"\/en\/articles\/artificial-intelligence-for-mobility-analysis\/","related":{"post":[],"author":[{"title":"Danyang Sun","url":"\/en\/authors\/danyang-sun\/","id":"2888","media":"\"\"","slug":"danyang-sun"}],"subject":[{"title":"Digital Technology, Modeling & Artificial Intelligence","url":"\/en\/subjects\/digital-technology-modeling-artificial-intelligence\/","id":"690","media":"\"\"","slug":"digital-technology-modeling-artificial-intelligence"},{"title":"Mobility, Transport & Infrastructure","url":"\/en\/subjects\/mobility-transport-infrastructure\/","id":"692","media":"\"\"","slug":"mobility-transport-infrastructure"}],"category":[{"title":"Article collection","url":"\/en\/articles\/category\/dossier\/","id":"1720","media":"","slug":"dossier","_related_post_type":"folder"},{"title":"Articles","url":"\/en\/articles\/category\/articles\/","id":"1716","media":"","slug":"articles","_related_post_type":""}],"folder":[{"title":"Mobilities","url":"\/en\/folders\/mobilities\/","id":"4200","media":"\"\"","slug":"mobilities"}]},"translated":"https:\/\/ingenius.ecoledesponts.fr\/articles\/lintelligence-artificielle-pour-lanalyse-de-la-mobilite\/","icon":"icon-folder","duration":"4","custom_excerpt":"Artificial intelligence (AI) uses computers\u2019 abilities to automatically learn \u201cknowledge\u201d from data. It has attracted unprecedented attention in recent years, with an increasingly diverse functional applicability. This includes territory analytics, with AI beginning to play a key role in urban planning, transportation systems, land uses, and environmental sustainability thanks to new concepts like \u201cSmart City\u201d and \u201cUrban Computing\u201d.<\/a> How can AI help us to better analyze city dynamics, especially with respect to mobility?","duration_type":"","_links":{"self":[{"href":"https:\/\/ingenius.ecoledesponts.fr\/en\/wp-json\/wp\/v2\/posts\/2885","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/ingenius.ecoledesponts.fr\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/ingenius.ecoledesponts.fr\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/ingenius.ecoledesponts.fr\/en\/wp-json\/wp\/v2\/users\/6"}],"replies":[{"embeddable":true,"href":"https:\/\/ingenius.ecoledesponts.fr\/en\/wp-json\/wp\/v2\/comments?post=2885"}],"version-history":[{"count":4,"href":"https:\/\/ingenius.ecoledesponts.fr\/en\/wp-json\/wp\/v2\/posts\/2885\/revisions"}],"predecessor-version":[{"id":8933,"href":"https:\/\/ingenius.ecoledesponts.fr\/en\/wp-json\/wp\/v2\/posts\/2885\/revisions\/8933"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/ingenius.ecoledesponts.fr\/en\/wp-json\/wp\/v2\/media\/1805"}],"wp:attachment":[{"href":"https:\/\/ingenius.ecoledesponts.fr\/en\/wp-json\/wp\/v2\/media?parent=2885"}],"wp:term":[{"taxonomy":"article-types","embeddable":true,"href":"https:\/\/ingenius.ecoledesponts.fr\/en\/wp-json\/wp\/v2\/article-types?post=2885"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}