Creating a quality map of a slate deposit using support vector machines

摘要: In this work, we create a quality map of slate deposit, using the results an investigation based on surface geology and continuous core borehole sampling. Once location sampling points have been defined, different kinds support vector machines (SVMs)-SVM classification (multiclass one-against-all), ordinal SVM regression-are used to draw up map. The are also compared with those for kriging. obtained demonstrate that regression perfectly comparable kriging possess some additional advantages, namely, their interpretability control outliers in terms vectors. Likewise, benefits covariogram as kernel evaluated, view incorporating problem association structure feature space geometry. our problem, strategy not only improved but implied substantial computational savings.