A PREDICTIVE FLOOD MODEL FOR URBAN KARST ENVIRONMENTS

Urban karst environments are often plagued by groundwater flooding, a type of flooding where water rises from the subsurface to the surface through the underlying caves and karst features. The heterogeneity and duality of karst systems make them very unpredictable, especially during intense storm events; urbanization exacerbates the problem with the addition of many impervious surfaces. Residents in such areas are frequently disturbed and financially burdened by the effects of karst groundwater flooding. The City of Bowling Green, Kentucky is one of the largest cities in the United States built entirely upon karst and experiences frequent, unpredictable groundwater flooding making it the ideal study area for this project. This research will attempt to aid the flooding problem in Bowling Green, with the creation of a predictive flood model for the Lost River Basin – a 150 km² groundwater basin that contains most of the city. The machine learning model will be trained using precipitation and antecedent condition data to predict fluctuations of the potentiometric surface under varying conditions. High-resolution data monitoring of 1-minute intervals will be employed at 44 water level monitoring sites and 9 precipitation sites to ensure accuracy of the model. As a result, this study will allow residents to better prepare for rain events, offer additional information on the storage and response times of an urban karst aquifer, and create a strong methodology for other flood-prone, urban karst areas to utilize for flood prediction.