Geospatial Decision Making

A joint article was presented by Cyrus Shahabi, Yao-Yi Chiang, Kelvin Chung, Kai-Chen Huang, Jeff Khoshgozaran-Haghighi, Craig Knoblock, Sung Chun Lee, Ulrich Neumann, Ram Nevatia, Arjun Rihan, Snehal Thakkar, and Suya You of the Integrated Media Systems Center – Department of Computer Science, University of Southern California on how the increase in the availability of geospatial data has motivated the effort to seamlessly integrate the data into an information-rich and realistic 3D environment. These models are important because of their use by cartographers, military and national intelligence agencies, city planners, military simulations, and video games. The article on this topic can be found at: http://64.233.167.104/search?q=cache:MMeeHj63ekUJ:graphics.usc.edu/cgit/pdf/papers/Geodec06-icme.pdf+geospatial+decision+making&hl=en&ct=clnk&cd=1&gl=us

The main challenge in designing the system is how to accurately integrate and visualize all aspects of a geographic region, given the existence of diverse data sources that have varying degrees of accuracy and consistency. Moreover, the user should be able to query the system and get information about the location that can then facilitate decision making. Examples of information that could be used by decision-makers are: high-resolution imagery, maps, road networks, and 3D models of buildings. All of which have significant interest to military intelligence. In addition, the system has applications in several other domains, including urban planning, emergency response, online real-estate, simulation and training, and computer games. In a previous blog I discussed the need for geospatial decision making in logistics.

The paper by the team from the Department of Computer Science, University of Southern California proposed applying relevant techniques developed independently in the fields of databases, artificial intelligence, computer graphics and computer vision to developing a working geospatial DSS. The paper presented a general architecture for such a system and describes how the system would be implemented. The decision support system as it was envisioned would not only allows navigation through a 3D model, but also issue queries and retrieve information as the user navigates through the area. In particular, the system seamlessly integrates satellite imagery, accurate 3D models, textures and video streams, road vector data, maps, point data, and temporal data for a specific geographic location. In addition, users can intuitively interact with the system using a glove-based interface.

The uses of this system appear to have endless applications in military simulations. Troops can now fight in a computer generated simulation that depicts accurate terrain and geopolitical situations. Individual decision making can now be reinforced or expanded by providing the individual with the experience of armed conflict without the associated dangers. The result should be less inappropriate decisions on the real battlefield and more lives saved in the process.

In order to efficiently and accurately integrate a wide variety of information about a geographic location, the DSS utilizes a geographic data integration system called Prometheus. Prometheus organizes the available information sources in a domain hierarchy containing well-known domain concepts, such as, satellite image, map, or vector data. Moreover, Prometheus also models different types of integration operations and their effects. Examples of the integration operations include Overlay and Align. The Overlay operation may result in two information layers not aligning with each other while the Align operation improves the alignment between two data layers. When the DSS receives a request to retrieve the data for a geographic location, it can send a request to the data integration system to obtain different types of information (i.e. vector data, raster maps, and satellite imagery). Prometheus determines the relevant sources for the requested data, retrieves relevant data from the sources, performs necessary alignment or integration operations, and returns the integration information to the DSS which can then be displayed on the 3D model.

One of the key aspects of the DSS is to integrate temporal data with other available sources of information. The fusion of temporal data sources significantly enhances the ability of a user to visualize the dynamic nature of an environment over a given time period. In order to add this capability to the system, the DSS can tracks all tagged assets that move in or around the area covered by the DSS in real-time. From a military standpoint, this would allow the Commanding officer to see a 3-dimentional model of the battlefield and know the location off all of his assets in real time. Depending on the degree on intelligence available concerning the interior of buildings, etc. this DSS would provide unparalleled command and control capabilities.

The geo-coordinates of each vehicle or man would be transmitted to a server every 10 seconds via modems installed on the vehicles and by the men. Individual transmitters could be kept small by placing a central server on each vehicle and the individual’s data could be relayed to the central server from there. This would require the individual to only carry a small radio sized transmitter. The system can thus track their location in real-time and displays the information on the 3D model. Vehicle and personnel status information could also be relayed at the same time. In addition, the integration of the large assortment of standard military overlay information could be added to and displayed by the DSS to add to the system’s decision making capability.

A geospatial decision making capability would greatly enhance current military command and control systems. Under the present geopolitical situation it is unlikely that the U.S. will engage in hostilities with a “modern” world power. The current situation indicates a conflict with other third world adversaries is more likely. As a result the communication links vital to the successful operation of this system would most likely not be impaired by countermeasures (jamming), or exploited to ascertain the location of our forces. Therefore, I would recommend that the military pursue this technology not only for use in simulators but also for exploitation as a DSS or command and control system.