Vulnerability mapping of karst springs and its application for the delineation of protection zones (Mecsek Karst, Hungary)

Over the past decade or two, vulnerability mapping become a useful tool to determine the sensitivity of karst aquifers and allows the analysis of karstic aquifers affected by human activities. The Tettye Catchment, one of the eight catchments of the Mecsek Karst aquifer (SW Hungary), supplies drinking water for Pécs, the fifth most populous city in Hungary. However, due to its partly urbanized character and heterogeneous karstic features, this catchment is highly sensitive to anthropogenic impacts. In this study we aimed to generate resource vulnerability maps and risk maps to assess the role of physical and anthropogenic factors on groundwater vulnerability in the Mecsek Karst. Two formerly validated methods were used, the COP (Concentration, Overlaying layers and Precipitation) and SA (Slovene Approach) methods. The resource vulnerability maps, validated by former tracer tests, were combined with the hazard map obtained from the COST action 620 and EU Water Directive to generate risk maps. Tracer-based transit times were commonly less than 20 days in the majority of the areas of extreme vulnerability. During the current study, a new protocol has been elaborated for the delineation of the protection zones of karstic aquifers. Comparing the two methods, the SA performed better in terms of intrinsic vulnerability mapping, as it had a higher spatial resolution and was more detailed than the COP map and had a more sophisticated vulnerability indexing. In addition, high spatial correlation was revealed between the transit time maps and the SA map. Reassessed risk zonation, with appropriate legal consequences, likely minimizes undesired human activities within the zone of protection, hence maintaining water quality that complies with the protection acts

GIS-BASED RAPID EARTHQUAKE EXPOSURE AND VULNERABILITY MAPPING USING LIDAR DEM AND MACHINE LEARNING ALGORITHMS: CASE OF PORAC, PAMPANGA

Disaster risk reduction and management (DRRM) not only requires a thorough understanding of hazards but also knowledge of how much built-up structures are exposed and vulnerable to a specific hazard. This study proposed a rapid earthquake exposure and vulnerability mapping methodology using the municipality of Porac, Pampanaga as a case study. To address the challenges and limitations of data access and availability in DRRM operations, this study utilized Light Detection and Ranging (LiDAR) data and machine learning (ML) algorithms to produce an exposure database and conduct vulnerability estimation in the study area. Buildings were delineated through image thresholding and classification of the normalized Digital Surface Model (nDSM) and an exposure database containing building attributes was created using Geographic Information System (GIS). ML algorithms such as Support Vector Machine (SVM), logistic regression, and Random Forest (RF) were then used to predict the model building type (MBT) of delineated buildings to estimate seismic vulnerability. Results showed that the SVM model yielded the lowest accuracy (53%) while logistic regression and RF models performed fairly (72% and 78% respectively) as indicated by their F-1 scores. To improve the accuracy of the exposure database and vulnerability estimation, this study recommends that the proposed building delineation process be further refined by experimenting with more appropriate thresholds or by conducting point cloud classification instead of pixel-based image classification. Moreover, ground truth MBT samples should be used as training data for MBT prediction. For future work, the methodology proposed in this study can be implemented when conducting earthquake damage assessments.