Bayesian decision tool for the analysis of occupational accidents in the construction of embankments

Instability and poor construction practices are responsible for the high accident rate in embankment construction in Spain. Applying a methodology based on data mining and attribute selection and using a 6-year database of accidents, key attributes in accidents associated with the construction of embankments were analyzed. Once the main predictors were identified, Bayesian networks in order to quantify the specific causes of different types of accidents were built. Thus, the main reasons for accidents as a preliminary phase to enhancing safety and embankment stability in mining and civil engineering works can be accurately identified and quantified.