Artificial intelligence and thermodynamics help solving arson cases

Journal article (2020)

Authors

Eva Schouten Student
O. Moultos Engineering Thermodynamics - Mechanical, Maritime and Materials Engineering
Peter Vergeer Nederlands Forensisch Instituut (NFI)
Michiel M.P. Grutters Nederlands Forensisch Instituut (NFI)
Leo J.C. Peschier Nederlands Forensisch Instituut (NFI)
T.J.H. Vlugt Engineering Thermodynamics - Mechanical, Maritime and Materials Engineering
M. Ramdin Engineering Thermodynamics - Mechanical, Maritime and Materials Engineering
Research Group
Engineering Thermodynamics (Mechanical, Maritime and Materials Engineering) (TU Delft)
Copyright: © 2020 Sander Korver, Eva Schouten, O. Moultos, Peter Vergeer, Michiel M.P. Grutters, Leo J.C. Peschier, T.J.H. Vlugt, M. Ramdin
DOI: https://doi.org/10.1038/s41598-020-77516-x
More Info
expand_more

Published Date

2020

Language

English

Faculty

Mechanical, Maritime and Materials Engineering

Department

Process and Energy

Research Group

Engineering Thermodynamics

Abstract

In arson cases, evidence such as DNA or fingerprints is often destroyed. One of the most important evidence modalities left is relating fire accelerants to a suspect. When gasoline is used as accelerant, the aim is to find a strong indication that a gasoline sample from a fire scene is related to a sample of a suspect. Gasoline samples from a fire scene are weathered, which prohibits a straightforward comparison. We combine machine learning, thermodynamic modeling, and quantum mechanics to predict the composition of unweathered gasoline samples starting from weathered ones. Our approach predicts the initial (unweathered) composition of the sixty main components in a weathered gasoline sample, with error bars of ca. 4% when weathered up to 80% w/w. This shows that machine learning is a valuable tool for predicting the initial composition of a weathered gasoline, and thereby relating samples to suspects.