In Taiwan, hydro-meteorological data are fragmented across multiple agencies, limiting the effectiveness of coordinated flood response. To address this challenge and the increasing uncertainty associated with extreme rainfall, a real-time disaster prevention platform has been developed. This system integrates multi-source data and geospatial information through a cluster-based architecture to enhance pluvial flood management. Built on a Service-Oriented Architecture (SOA) and incorporating Internet of Things (IoT) technologies, AI-based convolutional neural networks (CNNs), and 3D drone mapping, the platform enables automated alerts by linking sensor thresholds with real-time environmental data, facilitating synchronized operational responses. Deployed in New Taipei City over the past three years, the system has demonstrably reduced flood risk during severe rainfall events. Region-specific action thresholds and adaptive strategies are continually refined through feedback mechanisms, while integrated spatial and hydrological trend analyses extend the lead time available for emergency response.

Effective mitigation of urban flash floods under extreme rainfalls requires integrated hydrologic monitoring and rapid response mechanisms. The study presents an adaptive flood response framework. It combines real-time rainfall forecasting, CCTV-based flood image classification, drainage network water level monitoring, pumping machinery operations, and automated response controls. The adaptive strategy is structured into three phases to support real-time decision-making: (1) atmospheric sensing and pre-alert actions, (2) subsurface drainage system monitoring and alert activation, and (3) surface run-off detection and response. Over three years of implementation in New Taipei City, the adapted strategy achieved an over 80% success rate in preventing street inundation during intense rainfall events (>25 mm per 10 min). By integrating ensemble modeling, remote sensing, and decision-support tools, the platform transforms climate-induced flood risks into opportunities for resilience.

Effective mitigation of urban flash floods under extreme rainfalls requires integrated hydrologic monitoring and rapid-response mechanisms. The study presents an adaptive flood response framework. It combines real-time rainfall forecasting, CCTV-based flood image classification, drainage network water level monitoring, pumping machinery operations, and automated response controls. The adaptive strategy is structured into three phases to support real-time decision-making: (1) atmospheric sensing and pre-alert actions, (2) subsurface drainage system monitoring and alert activation, and (3) surface run-off detection and response. During a three-year implementation period, the approaches successfully resolved of inundation events after severe rainfall subsides. By integrating ensemble modeling, remote sensing, and decision-support tools, the platform transforms climate-induced flood risks into opportunities for resilience.

Urban areas are gradually being affected by climate change. It is difficult to avoid urban flooding caused by heavy rainfall. Especially road flooding occurs 2-3 times a year in urban areas in the summer of Taiwan, when the regional weather is convective rainfall strong, it is difficult for general weather forecasting models to predict the amount of rainfall in the city in a short period of time. Rainfall areas in urban areas are prone to road flooding. Therefore, the intensity management value (>50dBz) of the radar reflectivity around the city is used to estimate the rainfall and urban flood warning, and the IoT water level monitoring instrument can monitor the water level in the urban rainwater sewer and set the urban flood warning based on the management value. The local low-lying areas of the city can also use CCTV images to identify flooding situation as a tool through AI's CCN deep learning technology and CCTV's flooding big data database that according to CNN's learning, training, and testing, after the completion, CCTV inspection and flood image recognition can be used for urban disaster prevention and relief. Finally, the monitoring data related to urban flooding is collected and displayed through the urban smart flood prevention platform, which provides efficient data collection, increases the response time for disaster relief, and quickly eliminates road flooding in the city. This study takes the urban smart flood prevention platform in New Taipei City, Taiwan as an example.