Five building blocks of spatial digital twins

Links table

Abstract and 1 introduction

1.1. Spatial DVD (SDTS)

1.2. Applications

1.3. Various components of SDTS

1.4. The scope of this work and contributions

2. Related work and 2.1. Digital twins and variables

2.2. Spatial Digital Twin Studies

3. Building blocks of spatial digital twins and 3.1. Get and process data

3.2. Data modeling, storage and management

3.3. Huge data analysis system

3.4. Maps and intermediate programs based on geographic information systems

3.5. Main functional ingredients

4. Other related modern technologies and 4.1. Amnesty International and ML

4.2. Blockchain

4.3. Cloud computing

5. Challenges and future work, and 5.1. Acquire multi -defined and accurate data

5.2. NLP Spatial Information and 5.3. Measurement with databases and huge data platforms for SDT

5.4. Spatial visions and 5.5. Multi -media

5.6. Build an simulator environment

5.7. Imagine complex and varied interactions

5.8. Reducing security and privacy concerns

6. Conclusion and references

3.5. Main functional ingredients

We divided SDT functions on a large scale into five different categories: exploration and perception; Inquiries mining simulation; And predictive analysis. After that, we discuss these details.

3.5.1. Exploration and perception

One of the areas in which the SDTS has developed more than others is perception. Many research papers and systems [63] Focus on the perception, as well as referring the perception system as the main goal of spatial digital twin (which does not represent a completely valid claim because the other major jobs discussed in this section are no less important). In the conception of SDTS, a basic map layer is usually used and different layers of data such as 3D buildings, mobility effects and spatial networks are added. In addition to maps and geographic information systems programs such as OpenStreetmap and Arcgis, there are a number of 3D perception platforms such as Cesium [62]3dexperience [15]Hxdr platform [72]Etc. While certain aspects of spatial ideas and relationships can be understood, current perception techniques fail to capture the full range of deep spatial relationships within various types and time devices for data. For example, the perception of a 3D building is proven along with energy consumption in the time chains on the map it is a difficult task.

3.5.2. Query

Despite comprehensive research on spatial databases and spatial information, a handful of commercial database systems, such as Oracle Spatial and Postgresql, currently provides support for spatial information on the basic spatial database. However, these systems do not meet the types of emerging data such as three -dimensional data and paths, and do not address specialized queries such as identifying 3D visible objects from the query point [74] Or find similar paths [75]. More importantly, it is not easy for users to write spatial SQL queries and recover the required information from these database systems. Users usually find that it is more suitable for formulating spatial queries in the form of a text, such as searching for a POI point on maps platforms such as Google Maps and Bing Maps. This integration can be proven between textual information with basic spatial techniques, specifically in SDT, it is a very effective way for users to access the spatial data they want. Modern NLP research focuses on converting a text description of the user to SQL (AKA, Text-TosQL) and recovering the information required for the rules of relationships [76]. Spatial extensions of these technologies can help users to inquire about spatial data.

3.5.3. Mining

Data extraction techniques are extremely important in analyzing data created by SDTS and identifying patterns, relationships and trends that can provide valuable visions on how the material world works. For example, mining techniques can be used to identify areas in the city where greenhouse gas emissions are high or to detect abnormal cases in air quality in certain areas. It is important to design techniques that can determine interesting visions [77, 78, 79] From data automatically with small or non -human intervention. These technologies are necessary for the effective use of SDTS because they allow us to convert primary data into canable visions that can be used to improve the performance of physical systems and improve decisions. Later, in section 5.4, we discuss some research challenges in data mining for SDTS that must be processed to completely exploit their potential.

3.5.4. simulation

Simulator is decisive in spatial digital twins because it provides an unparalleled method for testing and analyzing the performance of the system and its behavior. Technology developments, such as cloud computing, machine learning and the Internet of Things (IOT), revolutionized SDTS simulation functions [80].

Spatial twin simulations can be applied in many scenarios. For example, the traffic flow in transportation can be simulated, and transportation methods can be improved to reduce congestion and improve safety [81]. Energy consumption can be simulated in a building or neighborhood, and chances of revision can be determined. Production processes can be simulated to enhance efficiency and reduce waste. Emergency situations, such as natural disasters or terrorist attacks, can be simulated to plan and train response efforts. In health care, patient flows and hospital operations can be simulated to improve resource customization and improve patient care [82, 83].

Various software tools are available for SDTS simulation, including Anylogic, OpenSTudio, Simio and Arena. These tools can be used for modeling and simulating systems in various applications, such as transportation, manufacturing, health care and logistics services [84]. In actual time, information is an important component of SDTS simulations, as it provides current and accurate data about the designed system. Information can be obtained in the actual time from sensors, cameras and other Internet of Things, and improving the accuracy and importance of simulation [85].

3.5.5. prediction

Amnesty International can use data in an actual time to predict and make notes for SDTS [86]. This is achieved through training models on historical data and the real time to predict future results, identify abnormal cases, and provide recommendations for improvement. In actual time, data is very important in many scenarios, such as improving traffic flow, predictive maintenance, and emergency response planning [87, 88, 89]. For example, in improving traffic flow, data can be used in actual time from sensors and cameras to predict traffic congestion and improve transportation methods to reduce travel time and improve safety [90]. In predictive maintenance, data in an actual time of sensors and devices can detect anomalies of equipment and predict maintenance needs, and avoid costly stopping.

Several organizations have implemented AI/ML in SDTS with actual time data. For example, San Diego uses data in actual time to predict and prevent them by analyzing weather conditions and other environmental factors. Dubai AI/ML Electricity and Water Authority is used to predict energy consumption, improve energy use in buildings, and take advantage of actual time data to respond to energy demand fluctuations. The Rotterdam Port uses data in an actual time to predict the ship’s movements and improve outlet resources, allowing the most efficient and effective port operations [91, 92].