Ties
Summary and 1 Introduction
1.1. Digital Spatial Twins (SDTS)
1.2. Applications
1.3. Different components of SDTs
1.4. Scope of this work and contributions
2. Related works and 2.1. Twins and digital variants
2.2. Case studies with digital spatial twins
3. Blockons for construction of digital spatial twins and 3.1. Data acquisition and processing
3.2. Modeling, storage and data management
3.3. Big Data analysis system
3.4. GIS -based maps and middleware
3.5. Key functional components
4. Other relevant modern technologies and 4.1. AI & ML
4.2. Blockchain
4.3. Cloud Computing
5. challenges and future work, and 5.1. Acquisition of multimodal and multi-resolution data
5.2. NLP for space requests and 5.3. Comparative analysis of databases and the Big Data platform for SDT
5.4. Automated spatial information and 5.5. Multimodal analysis
5.6. Construction simulation environment
5.7. View complex and various interactions
5.8. Alleviate security and confidentiality problems
6. Conclusion and references
5.4. Automated spatial information
Spatial digital twins generate large amounts of data, often from a wide variety of origin. It is essential to be able to automatically identify interesting information from this data without the need for human entry. In addition, techniques that can predict behavior, risks, opportunities and future trends are also important so that appropriate measures can be taken. While automatically identifying the information has been studied [77, 78, 79]None of these techniques is designed specifically for space data. Consequently, these techniques cannot provide spatial information that is crucial for the operation and management of digital spatial twins. Spatial ideas can take various forms, such as the detection of neighborhoods with abnormally high greenhouse gas emissions, the discovery of spatial correlations between the different attributes such as air quality and traffic accidents in various parts of a city, or mapping and highlighting regions with crime rates above persistence and their correlation with apparent attributes such as The use of electricity, waste production and waste production. In addition, temporal aspects of space data must also be taken into account in the generation of information. For example, it might be interesting to study how spatial correlation between two or more attributes evolves over time. Unfortunately, existing techniques cannot be applied or easily extended for spatial digital twins due to their inability to consider spatial characteristics. In addition, it is crucial to design effective techniques so that information can be generated in a timely manner, allowing system operators to intervene quickly if necessary.
5.5. Multimodal analysis
Image and text integration into multimodal language models, such as clip [103]Allows them to learn the data space jointly and effectively meet the challenges linked to multimodal data. In addition, remarkable progress in large multimodal generative models, such as GPT-4 [99]have shown significant potential in the field of multimodal learning. We plan that it is possible to respond to many requests and find interesting information of the captured satellite image / the image of the drone (i.e. raster space data) with other spatial and non-spatial data. More specifically, the combination of different forms of data such as real -time data (for example, traffic, energy consumption) collected by sensors, images taken by a satellite or a drone, the characteristics of the space district and form a large multimodal model can be able to generate useful information.
5.6. Construction simulation environment
Like many factors such as social interaction, economic factors and human factors may not be captured in SDTs, it is important to build a simulated environment, where these factors can be simulated so that their association with captured SDT data can be assessed. Future research should focus on how to build a realistic simulated environment suitable for SDTs. Different simulation software such as Anylogic, OpenStudio and Simio have been developed for applications such as transport, logistics and manufacturing. Since the scope and scale of an SDT are considerably different from those of DT, there is a potential avenue for research on how to develop a platform to simulate different factors involving SDT.
5.7. View complex and various interactions
An SDT involves various forms of data such as infrastructure data (for example, 3D buildings, roads, etc.), sensor data (for example, energy / gas / water consumption, traffic, etc.) and data on social networks (for example, Twitter, Instagram, etc.). There are a number of data visualization challenges involving the interaction of these complex data objects. For example, as the visualization of more than three dimensions is not understandable for typical users, it is difficult to combine different forms of data, for example, building 3D with the chronological energy consumption of the building on a map. In addition, as the data can be of higher dimension and different types, the visualization of correlations between these data sets through the spatial and temporal dimension requires more research. In addition, how to add and visualize different layers of data attached to a particular location on a card or SIG software to observe interesting information and the interaction of the associated data must be studied.
Authors:
(1) Mohammed Eunus Ali, IT and Engineering Department, Bangladesh University of Engineering and Technology, Ece Building, Dhaka, 1000, Bangladesh;
(2) Muhammad Aamir Cheema, Faculty of Information Technology, Monash University, 20 Walk Walk, Clayton, 3164, Vic, Australia;
(3) Tanzima Hachem, Department of Computer Science and Engineering, Bangladesh University of Engineering and Technology, Ece Building, Dhaka, 1000, Bangladesh;
(4) Anwaar Ulhaq, School of Computing, Charles Sturt University, Port Macquarie, 2444, NSW, Australia;
(5) Muhammad Ali Babar, School of IT and Mathematics, University of Adelaide, Adelaide, 5005, SA, Australia.
