AI-Driven Water Quality & Safety Monitoring (PhD)

ScholarLink Inc.; Sheffield; Hybrid; GBP 18.000 - 21.000; Vollzeit

Zusammenfassung

University of Sheffield invites applicants for a PhD studentship focused on smartification of water quality and safety in Drinking Water Distribution Systems (DWDS). The project combines datasets, intelligent models and simulation results to enhance resilience against daily incidents and extreme events under climate change.

The candidate will develop predictive monitoring using microbial, environmental and hydraulic information, employing graph neural networks and time-series analysis.

Qualifikationen

• A minimum 2:1 honours degree (or international equivalent) in Civil and Environmental Engineering (water), Environmental Sciences or related subject.
• Aptitude for research in drinking water systems, including machine-learning and ecological modelling.
• Familiarity with Python, R or related programming languages for analysis of large datasets.
• Experience with molecular work including DNA sequencing and bioinformatics is highly desirable.
• Willingness to collaborate with other researchers, industry and end-users.
• To be admitted, candidate must meet access requirements to a doctoral programme at The University of Sheffield.

Aufgaben

• Develop intelligent monitoring and predictive models integrating microbial, environmental and hydraulic data for early detection of water quality risks.
• Advance methods like graph convolutional networks to detect and predict contamination events.
• Provide insights into biofilm dynamics and interdependencies between microorganisms and infrastructure.

Kenntnisse

Data Analysis

Machine Learning

Bioinformatics

Ausbildung

2:1 honours in Civil & Environmental Eng (water) or related

Tools

Python

R

Jobbeschreibung

University of Sheffield invites applicants for a PhD studentship focused on smartification of water quality and safety in Drinking Water Distribution Systems (DWDS). The project combines datasets, intelligent models and simulation results to enhance resilience against daily incidents and extreme events under climate change.

The candidate will develop predictive monitoring using microbial, environmental and hydraulic information, employing graph neural networks and time-series analysis.