The ability to delineate geologic facies and to estimate their properties from sparse data is essential for modeling physical and biochemical processes occurring in the subsurface. If such data are poorly differentiated, this challenging task is complicated further by preventing a clear distinction between different hydrofacies even at locations where data are available. We study the problem of facies delineation in geologic formations by means of the Support Vector Machine (SVM). To show the potential of the SVM, we randomly generate a two-dimensional porous medium composed of two heterogeneous materials, and then reconstruct boundaries between these materials from a few data points. We assess the performance and accuracy of the SVM-based facies delineation technique and assess in the presence of either well differentiated or poorly differentiated information about hydraulic parameters, such as hydraulic conductivity.