Toward Developing Techniques─Agnostic Machine Learning Classification Models for Forensically Relevant Glass Fragments.

Glass fragments found in crime scenes may constitute important forensic evidence when properly analyzed, for example, to determine their origin. This analysis could be greatly helped by having a large and diverse database of glass fragments and by using it for constructing reliable machine learning (ML)-based glass classification models. Ideally, the samples that make up this database should be analyzed by a single accurate and standardized analytical technique. However, due to differences in equipment across laboratories, this is not feasible. With this in mind, in this work, we investigated if and how measurement performed at different laboratories on the same set of glass fragments could be combined in the context of ML. First, we demonstrated that elemental analysis methods such as particle-induced X-ray emission (PIXE), laser ablation inductively coupled plasma mass spectrometry (LA-ICP-MS), scanning electron microscopy with energy-dispersive X-ray spectrometry (SEM-EDS), particle-induced Gamma-ray emission (PIGE), instrumental neutron activation analysis (INAA), and prompt Gamma-ray neutron activation analysis (PGAA) could each produce lab-specific ML-based classification models. Next, we determined rules for the successful combinations of data from different laboratories and techniques and demonstrated that when followed, they give rise to improved models, and conversely, poor combinations will lead to poor-performing models. Thus, the combination of PIXE and LA-ICP-MS improves the performances by ∼10-15%, while combining PGAA with other techniques provides poorer performances in comparison with the lab-specific models. Finally, we demonstrated that the poor performances of the SEM-EDS technique, still in use by law enforcement agencies, could be greatly improved by replacing SEM-EDS measurements for Fe and Ca by PIXE measurements for these elements. These findings suggest a process whereby forensic laboratories using different elemental analysis techniques could upload their data into a unified database and get reliable classification based on lab-agnostic models. This in turn brings us closer to a more exhaustive extraction of information from glass fragment evidence and furthermore may form the basis for international-wide collaboration between law enforcement agencies.

Inter-laboratory workflow for forensic applications: Classification of car glass fragments.

The International Atomic Energy Agency (IAEA) has coordinated a research project titled "Enhancing Nuclear Analytical Techniques to Meet the Needs of Forensics Sciences" (CRP F11021) with the aim of empowering accelerator and reactor based techniques for applications in forensic sciences. One of the key topics of this project was the analysis and classification of forensic glass specimens using Ion Beam Analysis (IBA) techniques and in particular, Particle Induced X-ray Emission (PIXE). To this end, glass fragments from car windows from different car models and manufacturers provided by the Israeli police force were subjected to PIXE measurements at three laboratories to determine their elemental compositions and possible glass corrosion. Major and trace elements were measured and given as an input to machine learning (ML) algorithms in order to develop classification models to determine the origin of the glass samples. First, we have developed ML models based on the results obtained at each lab. These models successfully classified glass fragments into different car models with an accuracy> 80% on external test sets. Next, we demonstrated that following an appropriate pre-processing step, results from different labs could be combined into a single unified database for the derivation of a classification model. This model demonstrates good performances that matches or surpasses the performances of models derived from the individual labs. This finding paves the way towards establishing an international database that is composed of measurements from various PIXE labs. We believe that using this methodology of combining various sources of measurements will improve models' performances and generality and will make the models accessible to law enforcement agencies around the world.