Machine Learning for Detecting Virus Infection Hotspots Via Wastewater-Based Epidemiology: The Case of SARS-CoV-2 RNA.

Wastewater-based epidemiology (WBE) has been proven to be a useful tool in monitoring public health-related issues such as drug use, and disease. By sampling wastewater and applying WBE methods, wastewater-detectable pathogens such as viruses can be cheaply and effectively monitored, tracking people who might be missed or under-represented in traditional disease surveillance. There is a gap in current knowledge in combining hydraulic modeling with WBE. Recent literature has also identified a gap in combining machine learning with WBE for the detection of viral outbreaks. In this study, we loosely coupled a physically-based hydraulic model of pathogen introduction and transport with a machine learning model to track and trace the source of a pathogen within a sewer network and to evaluate its usefulness under various conditions. The methodology developed was applied to a hypothetical sewer network for the rapid detection of disease hotspots of the disease caused by the SARS-CoV-2 virus. Results showed that the machine learning model's ability to recognize hotspots is promising, but requires a high time-resolution of monitoring data and is highly sensitive to the sewer system's physical layout and properties such as flow velocity, the pathogen sampling procedure, and the model's boundary conditions. The methodology proposed and developed in this paper opens new possibilities for WBE, suggesting a rapid back-tracing of human-excreted biomarkers based on only sampling at the outlet or other key points, but would require high-frequency, contaminant-specific sensor systems that are not available currently.

Real time control of nature-based solutions: Towards Smart Solutions and Digital Twins in Rangsit Area, Thailand.

The intensity and frequency of hydro-meteorological hazards have increased due to fast-growing urbanisation activities and climate change. Hybrid approaches that combine grey infrastructure and Nature-Based Solutions (NBSs) have been applied as an adaptive and resilient strategy to cope with climate change uncertainties and incorporate other co-benefits. This research aims to investigate the feasibility of Real Time Control (RTC) for NBS operation in order to reduce flooding and improve their effectiveness. The study area is the irrigation and drainage system of the Rangsit Area in Thailand. The results show that during the normal flood events, the RTC system effectively reduces water level at the Western Raphiphat Canal Station compared to the system without RTC or with additional storage. Moreover, the RTC system facilitates achieving the required minimum volume and increasing the volume in the retentions. These findings highlight the potential of using RTC to improve the irrigation and drainage system operation as well as NBS implementation to reduce flooding. The RTC system can also assists in equitable water distribution between Klongs and retention areas, while also increasing the water storage in the retention areas. This additional water storage can be utilized for agricultural purposes, providing further benefits. These results represent an essential starting point for the development of Smart Solutions and Digital Twins in utilizing Real-Time Control for flood reduction and water allocation in the Rangsit Area in Thailand.

Flood risk management in Sint Maarten - A coupled agent-based and flood modelling method.

Disaster risk reduction is a major concern of small island developing states. Measures to reduce risk should not only be based on the magnitude of physical hazard, but also on the exposure and vulnerability of communities. In this article, we examine flood risk management policies in the Caribbean island of Sint Maarten using coupled agent-based and flood models. The agent-based model is used to model actors' behaviour in relation to urban building development and policies that are designed to reduce flood hazard and communities' vulnerability and exposure. The policies considered in the model are a Beach Policy, a Building and Housing Ordinance, a Flood Zoning policy and hazard mitigation structural measures. The flood model is used to simulate coastal and pluvial floods on the island. Agent behaviour such as building new houses and implementing hazard reduction measures affect the flood model as these actions affect the rainfall-runoff process. The flood maps generated from the updated flood model simulations are then used to assess the impact and update agents' attributes and behaviour. The simulations results show that low-lying areas are populated, which increases the exposure, and the number of vulnerable houses is also high. Hence, out of the four policies, implementing hazard reduction measures is the most important. Reducing the flood hazard by widening existing drainage channels, constructing new ones and building dykes as coastal flood defence would reduce the hazard, hence reducing the number of flooded houses. As it affects all households on the island, the Building and Housing Ordinance is an important policy to reduce vulnerability. In general, the coupled model outputs can be used to inform policy decision making and provide insights to policymakers on the island.