Application of Multi Adaptive Neuro-Fuzzy Interference System for detection of subsurface cavities in Bahama Free Port

We aim to estimate the depth of subsurface cavities from gravity data by a new method through a Multiple Adaptive Neuro Fuzzy Interference System (MANFIS).In fact, this method is an intelligent way to interpret gravity data and gain an estimation of depth and shape. The MANFIS model was trained for two main models of cavities: sphere and cylinder in a domain of radius and depth. We tested different MANFIS’s with different number of rules and obtained the optimum value for number of in the hidden layer. Then it was tested in present of 20% Gaussian noise, and also tested for real data of Bahama Free Port. It presented good results for depth estimation of subsurface cavities.