Gautam: AI-Enhanced Analytical Methodologies for the Detection and Identification of Drugs in Spiked Drink Samples

Faculty: Science and Engineering

Supervisors: Dr Lata Gautam ([email protected]); Dr Ben Gregson ([email protected]); Dr Sarfaraz Syed (external) ([email protected])

Location: Cambridge

Match-funded by: NG Sensors

We strongly recommend contacting the supervisors for this project for a discussion prior to applying.

Drink spiking is a growing concern in nightlife environments, such as bars, clubs and parties, and it poses a significant challenge for forensic investigations. This project aims to develop portable, AI-enhanced analytical tools capable of rapidly detecting and identifying drugs in drink samples; helping to improve public safety and support real-time forensic decision-making.

Working alongside academic researchers and industry partners, you'll contribute to the creation of a comprehensive drug reference library linked to drink-spiking incidents and help integrate this into the analytical tool (NIR- and MS-based technology), developing a compact analytical device suitable for use by police, forensic laboratories, and even venues. You'll also take part in the development and validation of machine learning models for automatic identification of harmful substances from chemical data.

Your work will include laboratory testing of known potential spiking agents, analysis of anonymised real-world drink samples from nightlife settings, and evaluation of detection performance of the analytical technique including its accuracy, sensitivity, and reliability. Laboratory studies will take place at ARU's Cambridge campus. The project offers opportunities to contribute to scientific publications, present findings at conferences, and be part of a successful academia-industry collaboration with real commercial and community impact.

The spectral data produced by the ChemCorder will be analysed using a combined chemometric and AI-driven approach:

• Unsupervised methods such as Principal Component Analysis (PCA) and Hierarchical Cluster Analysis (HCA) will be used to explore the structure of the data, identify patterns and clusters, and determine key features that distinguish spiked from unspiked drinks.
• These findings will then guide the development of supervised models including Partial Least Squares Discriminant Analysis (PLS-DA) and Partial Least Squares Regression (PLSR).
• The insights gained will support the training and validation of machine learning algorithms for accurate and automated drug identification.

This is an exciting chance to gain hands-on experience with advanced analytical science and modern AI techniques while helping deliver a safer environment for students and the wider public.

Who are we looking for?

• Degree: a good Honours degree (2:1 or above) in a relevant discipline (e.g. Forensic Science or Analytical Chemistry). A Master’s degree in a related subject is desirable.
• Laboratory skills: familiarity with standard analytical science techniques (e.g., sample preparation, handling of drugs of abuse and toxic chemicals) and understanding of national and international guidelines.
• Data analysis skills: Experience with basic statistical methods for interpreting chemical data.
• Communication skills: Strong communication skills, both written and oral, for writing, presentations, and working with partners (industry, law enforcement, academia).

Funding notes

The successful applicant for this project will receive a Vice Chancellor’s PhD Scholarship which covers the tuition fees and provides a UKRI equivalent minimum annual stipend for 3.5 years. For 2025/6 this was £20,780 per year. The award is subject to the successful candidate meeting the scholarship terms and conditions. Please note that the University asserts the right to claim any intellectual property generated by research it funds.

Download the 2026/7 sample terms and conditions