• Geomechanics and Engineering
• /
• v.36 no.5
• /
• pp.441-453
• /
• 2024

Sinkhole subsidence and collapse is a common geohazard often formed in karst areas such as the state of Florida, United States of America. To predict the sinkhole occurrence, we need to understand the formation mechanism of sinkhole and its karst hydrogeology. For this purpose, investigating the factors affecting sinkholes is an essential and important step. The main objectives of the presenting study are (1) the development of a machine learning (ML)-based model, namely C5.0 decision tree (C5.0 DT), for the prediction of sinkhole susceptibility, which accounts for sinkhole/subsidence inventory and sinkhole contributing factors (e.g., geological/hydrogeological) and (2) the construction of a regional-scale sinkhole susceptibility map. The study area is east central Florida (ECF) where a cover-collapse type is commonly reported. The C5.0 DT algorithm was used to account for twelve (12) identified hydrogeological factors. In this study, a total of 1,113 sinkholes in ECF were identified and the dataset was then randomly divided into 70% and 30% subsets for training and testing, respectively. The performance of the sinkhole susceptibility model was evaluated using a receiver operating characteristic (ROC) curve, particularly the area under the curve (AUC). The C5.0 model showed a high prediction accuracy of 83.52%. It is concluded that a decision tree is a promising tool and classifier for spatial prediction of karst sinkholes and subsidence in the ECF area.

• Journal of The Geomorphological Association of Korea
• /
• v.24 no.4
• /
• pp.75-89
• /
• 2017

Sinkholes are key karst landforms that primarily evolve through the dissolution of limestone, and it posing a significant threat to roads, buildings, and other man-made structures. This study aims to analyze the area susceptible to sinkhole development using GIS and to identify potential danger area from sinkholes. Eight sinkhole related factors (slope angle, distance to caves, distance to faults, bedrock lithology, soil depth, drainage class, distance to mines, and distance to traffic routes) were constructed as spatial databases with sinkhole inventory. Based on the spatial database, sinkhole susceptibility maps were produced using nearest neighbor distance and frequency ratio models. The maps were verified with prediction rate curve and area under curve. The result indicates that the nearest neighbor distance and frequency ratio models predicted 95.3% and 94.4% of possible sinkhole locations respectively. Furthermore, to identify potential sinkhole danger area, the susceptibility map was compared with population distribution and land use map. It has been found that very highly susceptible areas are along Osipcheon and southeast southwest part of Hajang-myeon and south part of Gagok-myeon of Samcheok-si. Among those areas, it has been identified that potential sinkhole danger areas are Gyo-dong, Seongnae-dong, Jeongna-dong, Namyang-dong and Dogye-eup. These results can be useful in the aspects of land use planning and hazard prevention and management.

• Journal of the Korean Geotechnical Society
• /
• v.37 no.12
• /
• pp.117-125
• /
• 2021

The occurrence of ground subsidence and sinkhole in downtown areas, which threatens the safety of citizens, has been frequently reported. Among the various mechanisms of a sinkhole, soil erosion through the damaged part of the sewer pipe was found to be the main cause in Seoul. In this study, a random forest model for predicting the occurrence of sinkholes caused by damaged sewer pipes based on sewage pipe information was trained using the information on the sewage pipe and the locations of the sinkhole occurrence case in Seoul. The random forest model showed excellent performance in the prediction of sinkhole occurrence after the optimization of its hyperparameters. In addition, it was confirmed that the sewage pipe length, elevation above sea level, slope, depth of landfill, and the risk of ground subsidence were affected in the order of sewage pipe information used as input variables. The results of this study are expected to be used as basic data for the preparation of a sinkhole susceptibility map and the establishment of an underground cavity exploration plan and a sewage pipe maintenance plan.