Geological Information Forecast and 3D Reconstruction Based on Support Vector Machine

In order to represent 3D spatial entity effectively in geological engineering, a new method of geological information forecast and 3D reconstruction is put forward based on support vector machine (SVM). Firstly, for the given geological drill hole data, SVM is adopted to forecast ore grade of information unknown areas within the geological sections and then geological layered data is obtained. Secondly, based on discretization meshwork model, topological relations for control points can be established automatically between adjacent data layers and in this way we can construct surface model of 3D spatial entity. The experiment results show that SVM has a better performance in predictable performance than the traditional BP neural network and the predicted value are close to the actual value which improves precision of 3D modeling greatly.