Engineering and Technology

Artificial intelligence and thermodynamics help solving arson cases

S. Korver, E. Schouten, et al.

This groundbreaking research by Sander Korver, Eva Schouten, Othonas A. Moultos, Peter Vergeer, Michiel M. P. Grutters, Leo J. C. Peschier, Thijs J. H. Vlugt, and Mahinder Ramdin unveils how machine learning and thermodynamic modeling can predict the initial composition of gasoline samples from weathered evidence. Achieving remarkable accuracy with minimal error even in severely weathered cases highlights its potential in linking fire scenes to suspects, revolutionizing arson investigation.

00:00

Playback language: English

Index

Abstract

In arson cases, crucial evidence like DNA or fingerprints is often destroyed. This research combines machine learning, thermodynamic modeling, and quantum mechanics to predict the unweathered composition of gasoline samples from weathered ones found at fire scenes. The approach accurately predicts the initial composition of sixty main components, with error bars around 4% even for samples weathered up to 80% w/w, demonstrating machine learning's value in linking fire scene samples to suspects.

Publisher

Scientific Reports

Published On

Nov 25, 2020

Authors

Sander Korver, Eva Schouten, Othonas A. Moultos, Peter Vergeer, Michiel M. P. Grutters, Leo J. C. Peschier, Thijs J. H. Vlugt, Mahinder Ramdin

Related Publications

Explore these studies to deepen your understanding of the subject.

Computer Science

Ethical principles in machine learning and artificial intelligence: cases from the field and possible ways forward

S. L. Piano

Computer Science

Artificial intelligence enabled COVID-19 detection: techniques, challenges and use cases

M. Panjeta, A. Reddy, et al.

Psychology

Artificial intelligence and social intelligence: preliminary comparison study between AI models and psychologists

N. S. Sufyan, F. H. Fadhel, et al.

Environmental Studies and Forestry

Artificial intelligence and ESG in resources-intensive industries: Reviewing the use of AI in fisheries, mining, plastics, and forestry

R. Deberdt, P. L. Billon, et al.

Listen, Learn & Level Up

Over 10,000 hours of research content in 25+ fields, available in 12+ languages.

No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.

listen to research audio papers with researchbunny