About this Research Topic
Urbanization, being a fundamental issue intrinsically linked to the development of society, has been assuming increasing importance in recent decades. Smart development of cities is essential for developing the education and research sectors, creating jobs, improving health services and making the environment cleaner. Unwise planning can lead to unsustainable urbanization and constitutes a brake on the development of society and the technology that underpins the services provided to citizens. This Research Topic is open to contributions that are part of the innovative solutions in the field of artificial intelligence applied to Smart Cities, with the aim of providing new effective tools to address the challenges of urban growth.
In this context, it is of paramount importance to develop technological solutions that help cities to exploit the available resources in an effective way, and that improve the management of information and its sharing among different actors. In particular, Smart City related technologies have the potential to increase the sustainability of urban development, rationalize costs and improve services, reduce emissions and water consumption, and decrease travel time. One of the areas of greatest interest is IoT, which integrates with mobile technologies (e.g., applications that provide real-time information on public transportation delays, GIS systems that provide the shortest route to a destination). Other possible applications of interest may be systems for tracking air pollutants, managing energy costs as a function of demand, and managing satellite data used to monitor physical parameters. All of these technologies have the ability to increase, and sustain, economic growth, and consequently improve the standard of living of citizens, enabling the development of increasingly efficient and low-cost services.
On the other hand, the exponential growth of data generated in urban contexts requires effective tools for their analysis. In this regard, urban governance can benefit from the application of machine learning tools. Artificial Intelligence can make a significant contribution, providing real-time predictive and analytical tools, usable in a wide range of contexts (e.g., predicting urban development from satellite images, mapping land coverage and usage). Today's increasingly powerful and easily accessible computing resources in the Cloud provide researchers with powerful and flexible tools for data analysis and intelligent modeling, and the creation of easily scalable, fast and accurate services.
Intelligent technologies can help collect various types of data (e.g., geographic or traffic and weather data) and can be leveraged to monitor and manage urban contexts, while providing useful insights and recommendations to improve decision-making, with the goal of making cities more sustainable.
We welcome papers that are focused on the following topics of interests (but are not limited to):
- Location intelligence in the Cloud
- Spatial prediction and interpolation techniques
- Deep Learning for GIS imagery interpretation
- Methods and tools for location intelligence applications
- Machine learning for urban growth prediction and planning
- Weather/Traffic/Air Pollutants Forecasting
- AI for detection of terrain features and densely-distributed building footprints
- Extraction of geographic information from unstructured (textual) data
- Analysis of Real-Time Information gathered by traffic cameras and other sensors
- Machine Learning for Social Sensing of geographical data
- Geographic object-based image analysis with remote sensing
- Geospatial Recommendation Systems
- Image Classification and Scene Segmentation for Alerting Systems
- Geo-enrichment Techniques
- Deep Learning and Reinforcement Learning on Geospatial Knowledge Graphs
- Spatially Explicit Machine Learning Methods and Models for GeoAI
- GeoAI for Geospatial Image Analysis
- GeoAI Resources and Infrastructures
- Image acquisition with automated label annotation
- Pre-processing of satellite imagery on the edge/ground
- Time series analysis of geospatial data
- Techniques for geographic knowledge discovery
- Analysis of geotagged crowdsourced data
- ML for earth sciences and sustainability
- Spatial representation learning and deep neural networks for spatio-temporal data
- Deep learning methods for disaster response
- Tools and methods for (explainable) XGeoAI
- Multimodal Fusion learning of geographic attributed datasets
- GeoAI methods for mobility and traffic data analytics
- Spatial Analysis and Processing of Structured and Semi-Structured Information
- Geospatial data conflation
In this context, it is of paramount importance to develop technological solutions that help cities to exploit the available resources in an effective way, and that improve the management of information and its sharing among different actors. In particular, Smart City related technologies have the potential to increase the sustainability of urban development, rationalize costs and improve services, reduce emissions and water consumption, and decrease travel time. One of the areas of greatest interest is IoT, which integrates with mobile technologies (e.g., applications that provide real-time information on public transportation delays, GIS systems that provide the shortest route to a destination). Other possible applications of interest may be systems for tracking air pollutants, managing energy costs as a function of demand, and managing satellite data used to monitor physical parameters. All of these technologies have the ability to increase, and sustain, economic growth, and consequently improve the standard of living of citizens, enabling the development of increasingly efficient and low-cost services.
On the other hand, the exponential growth of data generated in urban contexts requires effective tools for their analysis. In this regard, urban governance can benefit from the application of machine learning tools. Artificial Intelligence can make a significant contribution, providing real-time predictive and analytical tools, usable in a wide range of contexts (e.g., predicting urban development from satellite images, mapping land coverage and usage). Today's increasingly powerful and easily accessible computing resources in the Cloud provide researchers with powerful and flexible tools for data analysis and intelligent modeling, and the creation of easily scalable, fast and accurate services.
Intelligent technologies can help collect various types of data (e.g., geographic or traffic and weather data) and can be leveraged to monitor and manage urban contexts, while providing useful insights and recommendations to improve decision-making, with the goal of making cities more sustainable.
We welcome papers that are focused on the following topics of interests (but are not limited to):
- Location intelligence in the Cloud
- Spatial prediction and interpolation techniques
- Deep Learning for GIS imagery interpretation
- Methods and tools for location intelligence applications
- Machine learning for urban growth prediction and planning
- Weather/Traffic/Air Pollutants Forecasting
- AI for detection of terrain features and densely-distributed building footprints
- Extraction of geographic information from unstructured (textual) data
- Analysis of Real-Time Information gathered by traffic cameras and other sensors
- Machine Learning for Social Sensing of geographical data
- Geographic object-based image analysis with remote sensing
- Geospatial Recommendation Systems
- Image Classification and Scene Segmentation for Alerting Systems
- Geo-enrichment Techniques
- Deep Learning and Reinforcement Learning on Geospatial Knowledge Graphs
- Spatially Explicit Machine Learning Methods and Models for GeoAI
- GeoAI for Geospatial Image Analysis
- GeoAI Resources and Infrastructures
- Image acquisition with automated label annotation
- Pre-processing of satellite imagery on the edge/ground
- Time series analysis of geospatial data
- Techniques for geographic knowledge discovery
- Analysis of geotagged crowdsourced data
- ML for earth sciences and sustainability
- Spatial representation learning and deep neural networks for spatio-temporal data
- Deep learning methods for disaster response
- Tools and methods for (explainable) XGeoAI
- Multimodal Fusion learning of geographic attributed datasets
- GeoAI methods for mobility and traffic data analytics
- Spatial Analysis and Processing of Structured and Semi-Structured Information
- Geospatial data conflation
Keywords: GIS, location intelligence, spatial prediction, spatial interpolation, object detection, geospatial AI, GeoAI, Smart Cities, image classification, remote sensing
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
