A method for predicting an occurrence of a geological feature in a geologic thin section image uses a backpropagation-enabled classification process trained by inputting extracted training image fractions having substantially the same absolute horizontal and vertical length and associated labels for classes from a predetermined set of geological features, and iteratively computing a prediction of the probability of occurrence of each of the classes for the extracted training image fractions. The trained backpropagation-enabled classification model is used to predict the occurrence of the classes in extracted fractions of non-training geologic thin section images having substantially the same absolute horizontal and vertical length as the training image fractions.