Publication Date
5-2020
Abstract
The state of Florida sits on the karst terrain where soluble bedrocks are underlain; thus, a sinkhole is a common geohazard. These sinkholes have caused damage to property and infrastructure, as well as threatened human life. It is essential to develop a tool for predicting the potential of sinkhole occurrence. This study presents the methodology of the development of the sinkhole hazard model and map. An artificial neural network (ANN) method was employed. A sinkhole inventory map was prepared using Subsidence Incident Reports of Florida Geological Survey (FGS) with GIS. Hydrogeological factors related to soil erosion and stability (or ground collapse) were identified and used in model development. The selected seven contributing factors include hydraulic head difference, groundwater recharge rate, soil permeability, overburden thickness, surficial aquifer system thickness, intermediate aquifer system thickness, and proximity to karst features. The results show that the Orlando area has a higher probability of larger sinkholes than the Ocala area. This result is consistent with the fact that areas with thick overburden layers create larger sinkholes than thin areas.
Rights Information
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 License.
DOI
https://doi.org/10.5038/9781733375313.1031
An artificial neural network approach to sinkhole hazard assessment for East Central Florida
The state of Florida sits on the karst terrain where soluble bedrocks are underlain; thus, a sinkhole is a common geohazard. These sinkholes have caused damage to property and infrastructure, as well as threatened human life. It is essential to develop a tool for predicting the potential of sinkhole occurrence. This study presents the methodology of the development of the sinkhole hazard model and map. An artificial neural network (ANN) method was employed. A sinkhole inventory map was prepared using Subsidence Incident Reports of Florida Geological Survey (FGS) with GIS. Hydrogeological factors related to soil erosion and stability (or ground collapse) were identified and used in model development. The selected seven contributing factors include hydraulic head difference, groundwater recharge rate, soil permeability, overburden thickness, surficial aquifer system thickness, intermediate aquifer system thickness, and proximity to karst features. The results show that the Orlando area has a higher probability of larger sinkholes than the Ocala area. This result is consistent with the fact that areas with thick overburden layers create larger sinkholes than thin areas.
