AI-Driven Framework for Adaptive Water Network Management with Proof-of-Concept Implementation: Addressing Non-Revenue Water in Jordan

The paper presents an AI-driven framework for managing non-revenue water (NRW) in Jordan, integrating EPANET hydraulic modeling, digital twin technology, SCADA systems, and large language model (LLM) agents. A proof-of-concept using EPYT and the Llama3.1:8b model demonstrates automated hydraulic simulations and flow-based anomaly detection on a network with 1,164 junctions, achieving response times under 2 minutes without API costs. This approach enables real-time monitoring and adaptive decision-making, providing a scalable solution for NRW reduction in water-scarce regions.