Artificial neural systems have been used in a variety of problems in the fields of science and engineering. Here we describe a study of the application of neural networks in solving some geophysical inverse problems. In particular, we try to estimate the depth of dikes using magnetic data and a three-layer feed forward neural network. The network is trained by synthetic data as input and output. For forward neural network training we use the back-propagation algorithm. Results indicate that forward neural networks, if adequately trained, can predict a reasonably accurate depth for dikes. The proposed method was applied to magnetic data over the Darmian Iron field in Iran. Results were compared to real values from well data and proved the good performance of the trained neural network in predicting the dike's depth. same depth and also the same width. In Fig. 1(c) the effect of dike width is illustrated by comparing the anomaly profile over two dikes, which have different widths but are situated at the same depth and angle.

Near-surface soils contaminated with non-aqueous phase liquids, such as coal tar, crude oil, and chlorinated solvents, remain a serious problem. Smouldering remediation is a technique now being applied in the field for in situ destruction of non-aqueous phase liquids. Based on a selfsustaining exothermic reaction, smouldering remediation generates a hot region (>400 °C) that propagates through the subsurface. Self-potential is here considered for the first time as a nondestructive means for monitoring the smouldering remediation process. First, a series of sandbox experiments were conducted to investigate the magnitude of the thermoelectric coupling coefficient (C TE ) for different sand sizes, water contents, and heat sources. Measured C TE values ranged from -0.47 mV/°C for coarse, water-saturated sand to -0.05 mV/°C for fine sand with a saturation of 30%. Next, self-potential measurements were conducted during several laboratory smouldering remediation experiments, examining the response as a function of both space and time. A significant self-potential anomaly was observed on the surface during the smouldering period. Moreover, the magnitude of the self-potential anomaly was demonstrated to be highly correlated to the separation distance between the (moving) reaction front and the (stationary) self-potential electrode positions. Overall, this research suggests that the self-potential method has a significant promise as a non-invasive monitoring tool for in situ smouldering remediation of contaminated sites.