Snap Tasking



The field of geographic intelligence has changed in recent years. New technologies such as Big Data, Artificial Intelligence, Cloud Services,

and others are revolutionizing the way customers consume geographic information.


If in the past geographic intelligence knew to give information that includes location and target change in varying time ranges (faster or less), today,

this is not enough. Customers are aware of new capabilities and accordingly vary their expectations. The change in question does not skip

the area of geographic intelligence from space.


Satellite images and its analysis provide only part of the intelligence picture. The satellite remains the only tool capable of overcoming the political

problems of sovereignty in intelligence gathering. As such, it is a primary validation tool. However, the satellite alone can not provide an overall

intelligence image in short time cycles.


Continuous monitoring from the space of a geographical area is still considered a technological aspiration. The solution lies in combining existing

capabilities based on satellite images, along with intelligence research skills.



Data-based intelligence

At ISI we call the new ability – The next generation of geospatial intelligence (NGGI). The new concept of geographic intelligence wants to build

a broader context as possible around the target.


The context developed by using existing data about the target on the Internet, social networks, forums, databases and other sources of information.

Together, the new data tell a broader story and enriches the fundamental geographic knowledge.


Once the information collected, the data analysis tool is used to conclude the target.

The development of artificial intelligence techniques such as Deep Learning, Multi Agent Simulation, Data Mining and more,

enables rapid analysis and linking of points in a way that has not been possible before.



 Ex: Multi layer data correlation


One area where we have been able to make a significant change in capabilities is naval intelligence. At sea, one of the challenges is to detect and tracka

non-cooperative vessel that is not transmitting any AIS data. 


Detection of moving vessels with satellite sensors is a challenging task. To provide an economical solution for this challenge one should decrease

the uncertainty regarding the ship position. Using multi-agent based modeling and simulation, we developed a prediction algorithm for

the vessel behavior and selection algorithm which recommends on the best satellite and its observation window for this mission.



Snap tasking

Deep learning enables the system autonomously detect ships in existing satellite imagery, and by correlating this detection with various other sensors,

the uncooperative vessels are identified autonomously as well.



Ex: Multi Agent Simulation



Ex: multi agent simulation



Ex: Predicted location after 4h


The forecasting model allows us to direct the satellite at all its transitions above the area of interest. Focusing photography using algorithms

allows for better utilization of the satellite on the one hand, and on the other allows to track even vessels that are trying to hide.


Another ability is to determine using monitoring the behavior of a vessel to which category it belongs. Cargo, fishing boat, commercial boat and more.

Again, here, too, AIS enables the manipulation of the information and the use of the new generation of geographic intelligence tools,

allowing the validation of information.



Depth investigations

When it comes to intelligence gathering, depth research is sometimes necessary. For example, when you want to verify the innocence of a

particular vessel. In such a case, a photograph of the ship will indeed make it possible to know its location and its shipping route,

but this information alone will not be able to “clean” the vessel from an intelligence standpoint.


In this case, it is necessary to combine information from open sources of intelligence (OSINT). The Internet, commercial databases,

social networks and more. These help to understand the broader context of the vessel.


Information such as ownership, the structure of control, what materials the vessel carries, events that she participated in, etc.

These circles of information around the initial information about the craft help the analyst understand the broad intelligence picture.



Supply chain intelligence

The new geographic intelligence gathering capabilities enable the use of Big Data. That is, analyzing an enormous amount of data to

find related points. Using Big Data allows you to find new insights about your goal.


For example, it is now possible to find behavior patterns of a container and understand the entire course of the goods.

It is no longer a one-time photo or a series of photographs of the craft carrying the container. But the whole story around that container.


In the age of terrorist networks and global crime, geographical intelligence that includes the location of the object is no longer enough.

You have to give the analyst the overall picture. Without it, you can not track the whole supply chain of the organization.



Geo – economic intelligence

Another area in which new-generation geographic intelligence provides insights is commercial information. The use of Big Data on large sets

of data makes it possible to see trends in changes in geographic goals.


One example is oil reserves. The ability to capture changes to the site at any given time. Add information about the movement of tankers

in the AIS system and collect information about the location from the Internet, enables the validation of the oil inventory on the site.

The same tools can also be used to measure the movement of inventories at a particular plant or monitor the activity of goods in the port.

There is no doubt that the new generation of geographic intelligence makes it possible to understand the story of the goal better.

Whether it is a military, criminal or commercial purpose – In the new intelligence world, the dots can connect in a way that was not possible

in the past.




© 2016 ISI All rights reserved