i3WaterS › Doctoral positions

Incident Hub – in the preparation of water distribution systems through AI and lessons learned

Description

Research Objectives

The main research goal of iWaterS is to provide, for the first time, rational analyses and explainable intelligent decision support of WDS to increase resilience to day-to-day incidents and to extreme events in the context of climate change such as floods or droughts, through new interdisciplinary and integral approaches for exploiting datasets (on-line, off-line), intelligent models (data-driven, numerical) and simulation results (digital twins, multiagent systems).

The specific research objective of this offer are the following: the Doctoral Candidate will develop innovative Artificial Intelligence methodologies to improve preparedness and resilience in drinking Water Distribution Systems (WDSs) through the creation of an intelligent Incident Hub. The project aims to transform heterogeneous operational data and expert knowledge into actionable intelligence that supports utilities in understanding, characterising and managing disruptive events.

The research objectives are to:

• Generate systematic/viable tools for the collection of evidence in an incident Hub of disruptive events, from the opinion of experts (related causes of the event), the management times of the event and information from sensors (effects) that allow the development/training and validation of AI based tools for the characterization of disruptive events in WDSs.
• Develop methodologies to combine heterogeneous information sources, including sensor measurements, operational records, incident management logs and expert knowledge, into a structured knowledge repository.
• Design, develop, implement and validate innovative supervised and non-supervised learning solutions based on AI to characterize the events and establish the potential causal-effect relationship in the events contained in the Incident Hub.
• Investigate how causal relationships between incident causes, operational responses and observed impacts can be identified using advanced Artificial Intelligence techniques.
• Develop explainable AI methods capable of extracting meaningful patterns and lessons learned from historical incidents to support future operational decision-making.
• Advanced preprocessing and hybrid intelligent clustering will be used to characterize the events and specific intelligent interpretation
• Validate the proposed methodologies using real-world datasets provided by European water utilities and assess their transferability across different operational contexts.

Expected Results:

1) Systematic tools that allow the appropriate collection of evidence,

2) new Hub of incidents and,

3) new AI based tools to characterize the disruptive events that allows obtaining relevant information from different sources in relation to the events.

Requirements

Education level

Master Degree

Skills / Qualifications

• Machine Learning and Data Mining
• Knowledge-Based Systems
• Data-driven models
• Explainable Artificial Intelligence (XAI)
• Multi-Agent Systems
• Decision Support Systems
• Python, R, Java or related programming languages
• Data integration and interoperability
• Documenting in Latex
• Teamwork

Required languages

English – C1

Spanish or catalan will be taken into consideration