Many urban areas in tropical Southeast Asia, e.g., Bangkok in Thailand, have recently been experiencing unprecedentedly intense flash floods due to climate change. The rapid flood inundation has caused extremely severe damage to urban residents and social infrastructures. In addition, urban Southeast Asia usually has inadequate capacities in drainage systems, complicated land use patterns, and a large vulnerable population in limited urban areas. To reduce the urban flood risk and enhance the resilience of vulnerable urban communities, it has been of essential importance to develop real-time urban flood forecasting systems for flood disaster prevention authorities and the urban public. This paper reviewed the state-of-the-art models of real-time forecasting systems for urban flash floods. The real-time system basically consists of the following subsystems, i.e., rainfall forecasting, drainage system modelling, and inundation area mapping. This paper summarized the recent radar data utilization methods for rainfall forecasting, physical-process-based hydraulic models for flood inundation prediction, and data-driven artificial intelligence (AI) models for the real-time forecasting system. This paper also dealt with available technologies for modelling, e.g., digital surface models (DSMs) for the finer urban terrain of drainage systems. The review indicated that an obstacle to using process-based hydraulic models was the limited computational resources and shorter lead time for real-time forecasting in many urban areas in tropical Southeast Asia. The review further discussed the prospects of data-driven AI models for real-time forecasting systems.

In urban areas of Thailand, and especially in Bangkok, recent flash floods have caused severe damage and prompted a renewed focus to manage their impacts. The development of a real-time warning system could provide timely information to initiate flood management protocols, thereby reducing impacts. Therefore, we developed an innovative real-time flood forecasting system (RTFlood system) and applied it to the Ramkhamhaeng polder in Bangkok, which is particularly vulnerable to flash floods. The RTFlood system consists of three modules. The first module prepared rainfall input data for subsequent use by a hydraulic model. This module used radar rainfall data measured by the Bangkok Metropolitan Administration and developed forecasts using the TITAN (Thunderstorm Identification, Tracking, Analysis, and Nowcasting) rainfall model. The second module provided a real-time task management system that controlled all processes in the RTFlood system, i.e., input data preparation, hydraulic simulation timing, and post-processing of the output data for presentation. The third module provided a model simulation applying the input data from the first and second modules to simulate flash floods. It used a dynamic, conceptual model (PCSWMM, Personal Computer version of the Stormwater Management Model) to represent the drainage systems of the target urban area and predict the inundation areas. The RTFlood system was applied to the Ramkhamhaeng polder to evaluate the system’s accuracy for 116 recent flash floods. The result showed that 61.2% of the flash floods were successfully predicted with accuracy high enough for appropriate pre-warning. Moreover, it indicated that the RTFlood system alerted inundation potential 20 min earlier than separate flood modeling using radar and local rain stations individually. The earlier alert made it possible to decide on explicit flood controls, including pump and canal gate operations.

Plastic pollution in the ocean is a severe environmental problem worldwide because rivers carry plastic waste from human activities, harming the ocean’s health, ecosystems, and people. Therefore, monitoring the amount of plastic waste flowing from rivers and streams worldwide is crucial. In response to this issue of river-floating waste, our present research aimed to develop an automated waste measurement method tailored for real rivers. To achieve this, we considered three scenarios: clear visibility, partially submerged waste, and collective mass. We proposed the use of object detection and tracking techniques based on deep learning architectures, specifically the You Only Look Once (YOLOv5) and Simple Online and Realtime Tracking with a Deep Association Metric (DeepSORT). The types of waste classified in this research included cans, cartons, plastic bottles, foams, glasses, papers, and plastics in laboratory flume experiments. Our results demonstrated that the refined YOLOv5, when applied to river-floating waste images, achieved high classification accuracy, with 88% or more for the mean average precision. The floating waste tracking using DeepSORT also attained F1 scores high enough for accurate waste counting. Furthermore, we evaluated the proposed method across the three different scenarios, each achieving an 80% accuracy rate, suggesting its potential applicability in real river environments. These results strongly support the effectiveness of our proposed method, leveraging the two deep learning architectures for detecting and tracking river-floating waste with high accuracy.