Optimized Tsunami Vulnerability Area Classification Using Hybrid Fuzzy-SVM Model Through Spatial Data Processing

Tsunami disasters pose serious threats to human life and coastal infrastructure and require accurate mapping of tsunami-prone areas for effective disaster mitigation and coastal planning. Machine learning methods, including weighted overlay and Support Vector Machine (SVM), are widely used but often struggle to represent gradual transitions between vulnerability classes. This study proposes a hybrid fuzzy–SVM approach to enhance the accuracy and robustness of tsunami vulnerability classification. Three geospatial parameters, elevation, land cover, and inundation extent, were used as primary inputs, each transformed through fuzzy membership functions to handle uncertainty and spatial ambiguity. The fuzzy-transformed variables were aggregated into a normalized Fuzzy Vulnerability Index (FVI), which was subsequently classified using SVM with linear and RBF kernels under a one-vs-rest scheme to generate vulnerability maps for the southern coast of East Java. Experimental results demonstrated that the proposed hybrid fuzzy–SVM outperformed both conventional SVM and weighted overlay methods. The model achieved an overall accuracy of 91.3%, precision of 0.911, recall of 0.910, and F1-score of 0.910, indicating strong agreement between predicted and reference vulnerability maps. Overall, the hybrid fuzzy–SVM framework provides a more flexible and data-driven approach to tsunami vulnerability assessment.