The use of AI in policing to date has largely been in areas such as facial recognition and helping to deploy resources in the most effective ways, but a recent study led by Northumbria University highlights how it can also help to crack unsolved crimes, especially by providing insights into the weapons used in committing the crime.

“Machine learning uses a series of algorithms to model complex data relationships,” the authors say. “Through careful fine-tuning, these can be applied to predict important characteristics of the ammunition used in a particular shooting event from those of the respective gunshot residue (GSR) deposited on surrounding surfaces or items, such as spent cases, wounds, and, potentially, also the shooter’s hands.”

The team believes their approach represents a marked improvement from current methods of GSR analysis, with the new approach affording unprecedented accuracy.  It’s an approach that the team believes could bring fresh insights to some high profile, unsolved crimes of the past such as the Bloody Sunday killings of 1972.

“After Bloody Sunday, the problem was to determine if gunshots were fired by civilians or military staff,” they explain. “The investigators found large amounts of GSR all over victims and concluded that these resulted from shooting activities. It was later established, however, that these were likely due to the secondary, post-event transfer of contaminations from military staff – whose hands were rich with GSRs – to dead bodies. Small amounts of GSR, indeed, may be transferred by prolonged contacts with contaminated surfaces, such as those that took place when soldiers helped transport victims to the hospital after the event.”

Forensic Examination

The team has extensive knowledge of utilizing Machine Learning for forensic applications, with data collected from firing a range of ammunition, including the gun cartridges and the smokeless powders to determine a relationship between the ammunition and the residue.

Their initial success has prompted the team to believe their work could be applied more widely in forensic science, and potentially even in analytical chemistry more generally.

“The benefits are countless,” they explain. “They may even extend to other fields in analytical sciences that routinely encounter changeable chemical traces, such as the analysis of improvised explosive devices, arson accelerants, and environmental pollutants.”

The path from laboratory to market is seldom an easy one, but the results from this study are certainly interesting enough to suggest that police officers will soon have additional help when it comes to solving murders.