Application of Cluster Analysis for Soil Corrosivity Assessment

One important category of transportation infrastructure is underground pipelines. Corrosion of these buried pipeline systems may cause pipeline failures with the attendant hazards of property loss and fatalities. Therefore, developing an ability to estimate the soil corrosivity is important for designing and preserving materials and for risk assessment. Metal deterioration rate highly relies on physicochemical characteristics of a material and the environment of its surroundings. In this study, the field data obtained from the south east region of Mexico was applied for examining various data mining techniques for their ability to cluster soil corrosivity level. Specifically, the soil was classified into different corrosivity level clusters by K-means and GMMs, and the distributions of the degradation rate of the buried petroleum pipeline walls were estimated via the empirical density within each cluster. The soil corrosivity level was compared to the distribution of the metal loss rate between clusters. The clustering method was found to be more flexible than the existing soil corrosivity rating methods.