Indonesia Conference Directory

Disasters can cause enormous calamity in many ways which impacted people at all levels.The socially vulnerable individuals or communities often do not have enough data resources for disaster events, which makes it difficult for researchers and stakeholders to address cause-and-effect relationships between variables. In this study, Self Organizing Map (SOM) is used as an effective platform for analysis of a data set in a volcanic disaster in terms of the number of parameters and samples (or sites); while Social Vulnerability Index (SoVI) is used for vulnerability index creation to measure the level of vulnerability (high to low). Using SOM, this study, specifically, aims to classify the vulnerable areas and to determine the most important variables in characterizing social vulnerability levels for homogenous groups (or clusters) which are classified by the similarity of all variables. The data set used for this analysis consisted of 12 variables associated with socioeconomic features. We demonstrated that the SOM approach provided reliable estimates of clustering and the most significant variables, while SoVI works well in ensuring that positive value indicates high vulnerability, and vice versa. Therefore, it could be useful for the social vulnerability assessment by stakeholders and decision makers.