Answers are grounded in this paper and cite their sources.
Technology powered by the Internet of Things (IoT) and Machine Learning (ML) is transforming flood monitoring and disaster management. This study systematically examines key components including sensors, machine learning models, and communication networks within IoT-based flood detection and prediction systems. Using the PRISMA framework, the researcher evaluated 44 high-quality papers from IEEE Xplore, ScienceDirect, and other relevant databases. The review highlights ultrasonic sensors, rain gauges, water level, and flow sensors as the most effective hardware components, often paired with environmental sensors. In forecasting flood risks, machine learning algorithms, such as Random Forest (RF), had the highest accuracy, followed by K-Nearest Neighbors (KNN), Multilayer Perceptron (MLP), Decision Trees (DT), Long Short-Term Memory (LSTM) networks, and Convolutional Neural Networks (CNN), have also shown high predictive accuracy. Several protocols provide real-time data transmission, including LoRaWAN, Zigbee, GSM, and MQTT, while ThingSpeak, TagoIO, Grafana, and Blynk provide intuitive dashboards for monitoring and data visualization. IoT-driven systems enhance disaster response by providing early flood warnings, which allow authorities to act ahead of time. To reduce disaster risks and enhance community resilience to climate change, this study synthesizes current research on IoT-enabled solutions for floodwater level monitoring, prediction systems, and early warning systems. It outlines future directions for developing flood management solutions that are more resilient to disasters.
No takes yet. Share an insight, caveat, or question.
Pahuriray et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: