Spatial Variability of Rock Depth using Artificial Intelligence Techniques.

This study describes two Artificial Intelligence (AI) techniques for predicting spatial variability of rock depth in Bangalore. Reduced level of rock (d) at Bangalore, India is arrived from the 652 boreholes data in the area covering 220 km2. The first AI technique uses generalized regression neural network (GRNN) that are trained with suitable spread(s) to predict d at any point in Bangalore. The second technique uses Least Square Support Vector Machine (LSSVM), is a statistical learning theory which adopts a least squares linear system as a loss function instead of the quadratic program in original support vector machine (SVM). Here, LSSVM has been used as a regression technique. A comparative study between the two developed AI techniques has been presented in this paper. The results indicate that the developed GRNN model has the ability to predict d with an acceptable degree of accuracy (Coefficient of Correlation(r) =0.885, and Root Mean Square Error (RMSE) =0.021). Whereas, the developed LSSVM model predicts d with an acceptable degree of accuracy (r =0.967, and RMSE=0.004). This study also highlights the capability of LSSVM model over GRNN. [ABSTRACT FROM AUTHOR]