AI could help crack unsolvable murder cases

If techniques such as those we are developing now were available at the time, they could have been used to determine if GSRs came from civilian ammunition or military fire, which would have been a critical piece of evidence.”

Dr. Gallidabino specializes in statistical modelling and machine learning techniques for forensic applications. He personally developed and tested both the innovative chemical technique and the mathematical models used in the approach, after firing a range of ammunition. After collecting the gun cartridges, he analyzed them, and particularly the volatile part of the GSR, before turning his attention to the original smokeless powders. From here, he was able to establish a relationship between the ammunition and the residue, with the same statistical methods used by computer scientists to train robots.

Following on from this, the research team has called for this unique method to be applied much more widely in the field of forensic science and, more generally, analytical chemistry. “The benefits are countless” Dr. Gallidabino said. “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.”

Dr. Leon Barron, Senior Lecturer in Forensic Science from King’s College London, added: “The fusion of state-of-the-art laboratory analysis with computer-based machine learning will enable us to capitalize on the vast amounts of data we now generate to make ground-breaking advances like this more frequently. In forensic science, and often given the varied scenarios and sequences of events involved, machine learning represents one of the most promising ways to make sense of evidence more rapidly to support the Criminal Justice System.”

Jill Dando
On 26 April 1999, the 38-year-old BBC star was shot dead on the doorstep of her home in Fulham, West London in what remains one of the U.K.’s most high-profile unsolved murders. Barry George, who lived a few minutes from Jill’s house, was jailed for eight years for her murder but was cleared after a retrial in 2008 following concerns raised over forensic evidence. The case remains open.

Having more knowledge about the source of GSR at the time of the murder could have been useful, according to Dr. Gallidabino and the rest of the research team.

One single GSR particle was found in the pocket of the coat of Barry George (the suspect)” he says. “This particle was shown to have a really similar composition to those found on the victim, Jill Dando, according to techniques available at time. As no approved method existed to compare GSR compositions on different surfaces, however, this evidence was strongly contested. With our approach, we hope in the future to provide robust tools to law enforcement agencies to more efficiently address this kind of situation.”

— Read more in Matteo D. Gallidabino et al., “Quantitative profile–profile relationship (QPPR) modelling: a novel machine learning approach to predict and associate chemical characteristics of unspent ammunition from gunshot residue (GSR),” The Analyst (2 November 2018) (DOI: 10.1039/C8AN01841C)