Magnetic inverse modelling of a dike using the artificial neural network approach

Abstract

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.

Magnetic data interpretation for 2D dikes by the metaheuristic bat algorithm: sustainable development cases

“…On the other side, metaheuristic algorithms were developed to interpret the geomagnetic data, which rely on searching for global optimum solution that is more accurate and efficient than graphical and numerical methods 46 . Metaheuristic algorithms such as simulated annealing technique (SA) 47 , 48 , genetic algorithm (GA) 49 , particle swarm optimization (PSO) 50 , 51 , neural networks approach (NN) 22 , 52 , differential evolution algorithm (DE) 53 , and ant-colony optimization algorithm (ACO) 54 . These algorithms are popular among researchers because they are more adaptable and capable of dealing with a wide range of problems than traditional optimization techniques.…”

Depth estimates of anomalous subsurface sources using 2D/3D modeling of potential field data: implications for groundwater dynamics in the Ziway-Shala Lakes Basin, Central Main Ethiopian Rift

“…These structures could be mapped using gravity and magnetic anomalies through the application of different mathematical filtering techniques. The subsurface relief for example could be mapped by defining density/susceptibility interfaces (source-depths) using filters like upward continuation ( Kebede et al, 2020 ), tilt depth ( Chen et al, 2016 ; Salem et al, 2007 ), 3D Euler Deconvolution ( Mammo, 2010 ; Keating and Pilkington, 2004 ), power spectral analysis ( Mammo, 2012 ), 2D Werner Deconvolution ( Mammo, 2012 ), 2D forward modeling ( Mickus et al, 2007 ), 3D structural inversion ( Tiberi et al, 2005 ), genetic algorithm ( Montesinos et al, 2016 ) and artificial neural network approach ( Alimoradi et al, 2011 ). The above mentioned source depth estimations methods are some of the various methods and are chosen differently by different researchers implying that there is no single approach.…”

Regularized nonlinear inversion of magnetic anomalies of simple geometric models using Occam’s method: an application to the Morvarid iron-apatite deposit in Iran

“…However, running time of the simulated annealing algorithm can be significantly reduced using very fast simulated annealing (Sen and Stoffa 1995;Dobróka and Szabó 2011). Alimoradi et al (2011) implemented the artificial neural network for determining the depth of dikes. Beside inversion techniques, a large number of semi-automatic methods have been developed for mapping the subsurface magnetic isolated targets.…”