Home // IoTAI 2025, The Second International Conference on IoT-AI // View article
Authors:
Markus Aho
Aki Happonen
Marko Jäntti
Kaapo Pehkonen
Keywords: LoRaWAN; IoT; Environmental Monitoring; Predictive Maintenance; Artificial Intelligence; Sensor Networks; Gateway Configuration; Field Testing; Kuopio; Random Forest; Implementation; ITIL 4; Pattern Matching
Abstract:
This paper addresses the overarching research problem: How can an Artificial Intelligence(AI)-based water-level monitoring service be implemented and deployed for effective flood prediction in an urban environment? To explore this, three research questions are posed: RQ1—What type of network architecture can be used in AI-based monitoring of water levels? RQ2—How can the AI-based water-level monitoring service be implemented regarding devices, components, and AI models? and RQ3—Which challenges are related to the implementation and deployment of the AI-based water-level monitoring service? A private LoRaWAN network was set up in Kuopio, Finland, integrating 16 Elsys ELT Ultrasonic sensors with Kerlink and RAK gateways to monitor stormwater wells despite structural obstacles. The study spanned from Fall 2023 to Spring 2025, employing iterative field tests, AI model comparisons (linear regression, decision trees, random forest), and Information Technology Infrastructure Library (ITIL)-based pattern matching. The findings demonstrate the feasibility and robustness of a tailored IoT network, highlighting best practices for sensor placement, gateway configuration, and predictive analytics. These insights provide a blueprint for other cities aiming to harness low-power technologies and AI for early flood warnings and data-driven urban water management.
Pages: 7 to 13
Copyright: Copyright (c) IARIA, 2025
Publication date: July 6, 2025
Published in: conference
ISBN: 978-1-68558-286-9
Location: Venice, Italy
Dates: from July 6, 2025 to July 10, 2025