The intel war against IEDs continues. Intel relies on data mining and quantitative analysis to map out IED cells and probable IED locations. They are growing more skilled and using more computer models. The limitation is not the lack of intel, but the overabundance of it. It overwhelms any individual’s ability to recognize patterns and probability. That’s where data mining software steps in.

Strategy Page:

The data mining was initially used to figure out who the bomb making crews were, and where they operated from. Then, using math techniques first developed during World War II, the intel geeks began creating predictions about where IEDs were most likely to show up next. By then (2005), American forces had a highly skilled and capable Night Shift that patrolled roads and looked for IEDs, and the people who placed them, before the bombs could hurt anyone. The latest iterations of this predictive systems operate in real time, and live feeds of the data can be sent to combat units, or the Night Shift units looking to shut down or destroy bombs before anyone gets hurt (except for the terrorists caught placing the bombs).

One of the tools that intel uses is basic spatial analysis. When an IED is discovered, intel places a marker on the map at the location. Soon, there are visible IED clusters. They can connect this information with other data to estimate the size and location of insurgent IED cells as well as probable locations of future IEDs. The more data they collect, the more accurate their predictions are. This is similar to epidemiology and crime-fighting analysis.

There is a limitation. It allows intel analysts to uncover the “obvious” IED cells. This probably includes most of the amateurs. The experts disguise themselves, disperse their IEDs randomly, and frequently relocate. The environment is too dynamic and uncertain for static analysis. The challenge is learning how to connect seemingly unrelated events that are distant in time and space.

Former Spook describes the new computer software in development that will further enhace intel’s predictive ability.

Introducing the Rapid Assessment and Dissemination Information Infrastructure (RADII):

How is RADII different from other analytical tools? According to project managers, the system not only correlates information from a wide range of databases, it also employs a recursive learning algorithm that can be “trained” to discover emerging patterns in new data, and compare it to “historical” events of interest. In other words, if RADII finds a correlation between on-going events in a certain location (and finds a correlation to similar activities associated with past IED attacks), it will note the associate, and generate a warning for analysts, who can pass it on to units in the field.

RADII also allows the strongest correlations to be graphically displayed, in either a “links and nodes” wiring diagram, or on maps or imagery of the local area. The graphical depiction is particularly useful in showing how seemingly unrelated events and facilities may actually be part of an IED network, allowing more effective targeting of its elements, and the assessment of where future events are likely to occur.

His whole post is worth a read.

This gives a better idea of how anti-IED intel works.

This is theAir Force summary of RADII

The purpose of the RADII initiative is to develop and demonstrate a software-based Improvised Explosive Device (IED) predictive analysis capability to discern enemy patterns of behavior and predict future IED events. The C2ISRB, in conjunction with SENSIS Corporation, will use a recursively-learning statistical algorithm to perform predictive analysis of IED incidents.

The idea is sound. Computers are better able to track the vast range of data and isolate signals than even the best mathematician.

There have been a number of subtle improvements in the anti-IED war. The vast majority of IEDs no longer cause any casualties, in part due to better intelligence and better technology (namely the MRAP and UGVs). While IEDs continue to make up the super-majority of casualties, this is more due to the inability of the insurgency to inflict casualties through conventional weapons and tactics.