Presentation of neurofuzzy optimally weighted sampling model for geoelectrical data inversion

Intelligent algorithms are used to optimize the process in geophysics and applied in evaluating ground or subsurface parameters. This neurofuzzy sampling model is a great replacement for conventional data interpretation approach using mathematical models. In this algorithm, a novel sampling method is involved to filter noises and errors in each data. Neurofuzzy can train the data, and after training, the fuzzy structure predicts the exact parameter necessary for inversion. During sampling process, the algorithm samples each datum and produces synthetic data in correlation with the neighbouring data. After the sampling process, ANFIS intelligent algorithm learns the data, and based on the inputs and the number of samples, it interprets the appropriate functional output with high-level accuracy. This novel method of sampling algorithm provides a framework for efficient parameter optimization. These implications made to create the specific Graphical User Interface (GUI) for the algorithm and it works well for all types of Vertical Electrical Sounding (VES) data with good performance results.

Automated summary

Intelligent algorithms are utilized in optimizing geophysical processes and evaluating ground or subsurface parameters. The neurofuzzy sampling model provides a great alternative to traditional data interpretation methods by mathematical models. This algorithm incorporates a novel sampling approach to filter noise and errors, allowing it to train data and predict necessary parameters accurately.