🎓 Discover PhD and Master's programmes at leading universities worldwide — Sign up free to save searches and get email alerts
Sign In Register Free
AUO

Human-in-the-Loop AI for Equitable and Climate-Resilient Sewer Systems

AGH University of Science and Technology Department of Computer Science
✓ Funded (Competition) ⏰ Closing Soon machine learning hydraulic modelling reinforcement learning artificial intelligence climate resilience environmental equity urban infrastructure water management

Develop AI-powered, human-in-the-loop decision frameworks to enhance climate resilience and equity in urban sewer systems under uncertainty. Integrate physics-informed models with preference-based reinforcement learning for rapid, transparent intervention planning.

AI-generated overview

🌍
Why This Research Matters

This research addresses critical gaps in managing urban sewer infrastructure under climate uncertainty, explicitly incorporating social equity and regulatory constraints. By delivering auditable and robust decision-support frameworks, it enables utilities to make timely, equitable interventions supporting sustainable and resilient cities.

Physics-Informed Machine Learning Reinforcement Learning Climate Resilience Urban Sewer Systems Environmental Equity Scenario Generation

Project Description

This PhD project tackles a critical global challenge: climate-resilient urban infrastructure, specifically sewer and stormwater systems increasingly overwhelmed by climate change and urbanisation. Current challenges include: increased flooding and sewer overflow infrastructure designed for outdated climate conditions high economic and environmental costs disproportionate impact on vulnerable communities The project addresses a key gap: slow physics-based simulations opaque data-driven AI systems It proposes a human-in-the-loop AI framework that is: fast interpretable equity-aware decision-focused The research will develop three core components: Physics-informed AI models graph-based models of sewer networks predict flow, overflow, and system behaviour Scenario generation simulate climate change and urban growth include uncertainty and stress-testing Reinforcement learning decision system recommends infrastructure interventions incorporates: expert input regulatory constraints cost and safety considerations equity objectives The system will: prioritise interventions like upgrades and maintenance generate transparent and auditable decisions be tested on real-world case studies (UK and Australia) Expected outputs: scalable AI models for infrastructure planning scenario libraries for stress testing decision-support tools for utilities software modules for real-world deployment

Entry Requirements

Academic Requirements:

Strong degree (2:1 or above typically expected) in:
Computer Science
Data Science
Engineering
Mathematics
or related field

Preferred Skills:

machine learning / AI
reinforcement learning
data modelling
programming (Python etc.)
interest in sustainability or infrastructure

How to Apply

Apply via the official University of Exeter funding page:

👉 https://www.exeter.ac.uk/study/funding/award/?id=5845

Steps:

Visit the application link
Submit application via university portal
Upload required documents:
CV
Personal statement
Academic transcripts
References

Contact:

Dr Jawad Fayaz — J.Fayaz@exeter.ac.uk

Eligibility

UK/Home
EU
International

Supervisor Profile

DJ
Dr Jawad Fayaz
AGH University of Science and Technology, Department of Computer Science
Google Scholar

Dr Jawad Fayaz specializes in integrating physics-based and machine learning methodologies for environmental and infrastructural challenges. His research focuses on sustainable urban infrastructure modeling and climate adaptation strategies. He has a strong track record in developing robust AI-driven decision-support systems to enhance environmental equity.