An automatic inversion tool for geoelectrical resistivity data using supervised learning algorithm of adaptive neuro fuzzy inference system (ANFIS)

Abstract

Estimation of subsurface parameters of earth need an efficient and knowledge based algorithm to enthrall the real world truth clearly. Implementing the adaptive neuro fuzzy inference system (ANFIS) is worthwhile in this case of non-linear parametric approach. The ambiguous property of the conventional inversion technique results can be prevailing over by implementing the soft computing tool. The coalesce behavior of neural networks logics and fuzzy sets with certain rule based logics will concise the inversion technique to obtain the preferred result. In the present study, ANFIS algorithm was applied in direct inversion approach and the most prominent of this approach is supervised learning techniques adapted in the algorithm specially to enroll the concepts of inverting the geoelectrical data in a systematic way. The subsurface parameters of earth are mysteriously identified by sounding or direct bore techniques. Sounding method in geophysics plays the prominent role in understanding the subsurface features of earth. But major part of the sounding method relies on inversion techniques. Since the data obtained from the earth is non-linear and heterogeneous it is difficult to estimate the parameters more clearly. Thus apart from using any conventional inversion techniques which are mainly focusing on initial model layer parameters. If the initial layer parameters are not given in the particular range, then the forward modeling solution tends dissimilarity of observed bore hole/litholog data. Thus direct inversion dominates in estimating the parameters with the help of soft computing inversion techniques. The proposed technique solves most of the subsurface problems since it depends on the trained knowledge. The supervised learning technique has been validated with Tuticorin and Kanyakumari coastal region data and found to be successful.