Using AI to Aid GEOINT Analysis Results in More Effective and Efficient Intelligence

Using Artificial Intelligence (AI) techniques to augment GEOINT analytic processing, Riverside Research has demonstrated that analyst time is refocused on deeper analytics while detection accuracy and sensitivity are increased, enabling more effective and efficient intelligence.


The following case study relates to an article published in the USGIF Trajectory magazine in July 2017, based on work conducted for the National Air and Space Intelligence Center.


GEOINT analysts have stated their desire for innovation in the process of generating geospatial intelligence. For example, the National System for Geospatial Intelligence Strategic Concept of Operations (CONOPS) for 2015 provides guidance for using intelligent machine learning (ML) algorithms to aid the GEOINT analyst. The CONOPS lists “tool-assisted information generation” and “fully automated information generation” as key elements of GEOINT analytic information generation. It also talks about “augmenting analytic capabilities through artificial intelligence (AI) and knowledge processes (cognitive/rule-based inferencing, link analysis, pattern identification).”

In response and in coordination with the government and other industry teams, Riverside Research AI experts led efforts to incorporate ML/AI algorithms first against OPIR data, expanding across GEOINT and then to other Intelligence data, to produce Intelligence Community mission-essential products. In our Open Innovation Center AI/ML lab, we have also prototyped various types of neural networks for future development, proving their utility in working with GEOINT and broader Intelligence data.


There are many examples of ML and neural network algorithms that have been and are being applied to OPIR: principal component analysis, linear discriminant analysis, support vector machines, self-organizing maps, artificial neural networks (ANNs), and convolutional neural networks (CNNs). These algorithms have been incorporated to help with change detection, target detection, feature selection, object clustering, tracking, background suppression, false alarm rejection, classification, and other tasks. An ANN was recently demonstrated to suppress false alarms by 31 percent and increase the positive predictive value by more than 15 percent.

Incorporating these algorithms into the analytic process also helps to solve the ever-increasing big data problem. ML/AI tools free up analysts’ time, allowing them to focus on producing accurate and detailed reports. ML/AI algorithms also improve ability to detect events that can be missed by the human eye, in essence performing big data triage.

The insertion of AI techniques into GEOINT has been shown to provide more accurate detections and tracks, produce faster and more efficient processes, and allow for some processes to be automated. In the future, we can look forward to highly intelligent machines further advancing our capabilities by fusing multiple intelligence products to produce a synergistic, highly intelligent product for the intelligence community.