Search for: All records

Abstract Timely, accurate, and reliable information is essential for decision-makers, emergency managers, and infrastructure operators during flood events. This study demonstrates that a proposed machine learning model,MaxFloodCast, trained on physics-based hydrodynamic simulations in Harris County, offers efficient and interpretable flood inundation depth predictions. Achieving an average$$R^2$$ $R^2$of 0.949 and a Root Mean Square Error of 0.61 ft (0.19 m) on unseen data, it proves reliable in forecasting peak flood inundation depths. Validated against Hurricane Harvey and Tropical Storm Imelda,MaxFloodCastshows the potential in supporting near-time floodplain management and emergency operations. The model’s interpretability aids decision-makers in offering critical information to inform flood mitigation strategies, to prioritize areas with critical facilities and to examine how rainfall in other watersheds influences flood exposure in one area. TheMaxFloodCastmodel enables accurate and interpretable inundation depth predictions while significantly reducing computational time, thereby supporting emergency response efforts and flood risk management more effectively. 

Wastewater-based epidemiology has played a significant role in monitoring the COVID-19 pandemic, yet little is known about degradation of SARS-CoV-2 in sewer networks. Here, we used advanced sewershed modeling software to simulate SARS-CoV-2 RNA degradation in sewersheds across Houston, TX under various temperatures and decay rates. Moreover, a novel metric, population times travel time ( PT ), was proposed to identify localities with a greater likelihood of undetected COVID-19 outbreaks and to aid in the placement of upstream samplers. Findings suggest that travel time has a greater influence on RNA degradation across the sewershed as compared to temperature. SARS-CoV-2 RNA degradation at median travel times was approximately two times greater in 20 °C wastewater between the small sewershed, Chocolate Bayou, and the larger sewershed, 69th Street. Lastly, placement of upstream samplers according to the PT metric can provide a more representative snapshot of disease incidence in large sewersheds. This study helps to elucidate discrepancies between SARS-CoV-2 viral load in wastewater and clinical incidence of COVID-19. Incorporating travel time and SARS-CoV-2 RNA decay can improve wastewater surveillance efforts.