Artificial neural network inversion of magnetic anomalies caused by 2D fault structures
- PDF / 585,257 Bytes
- 8 Pages / 595.276 x 790.866 pts Page_size
- 43 Downloads / 141 Views
ORIGINAL PAPER
Artificial neural network inversion of magnetic anomalies caused by 2D fault structures Mansour A. Al-Garni 1
Received: 6 July 2015 / Accepted: 6 November 2015 / Published online: 24 February 2016 # Saudi Society for Geosciences 2015
Abstract A new approach is proposed to interpret magnetic anomalies caused by 2D fault structures. This approach is based on the artificial neural network inversion, utilizing particularly modular neural network algorithm. The inversion process is implemented to estimate the parameters of 2D fault structures where it has been verified first on synthetic models. The results of the inversion show that the parameters derived from the inversion agree well with the true ones. The analysis of noise has been studied in order to investigate the stability of the approach where it has been tested for contaminated anomalies with 5 and 10 % of white Gaussian noise. The results of the inversion provide satisfactory results even with contaminated signals. The validity of the approach has been demonstrated through real data taken from New South Wales, Australia. A comparable and satisfactory agreement is shown between the inversion results of the neural network and those from techniques published in literatures. Keywords Neural network . Magnetic . 2D fault structures . Inversion
Introduction In the interpretation of magnetic and gravity problems, the anomalies can be attributed to simple models such as dikes
* Mansour A. Al-Garni [email protected]; [email protected] 1
Department of Geophysics, Faculty of Earth Sciences, King Abdulaziz University, P.O. Box 80206, Jeddah 21589, Saudi Arabia
and faults where the parameters are usually determined through an inversion scheme (Murthy et al. 2001). Several techniques for interpreting magnetic anomalies have been addressed in literatures. Theoretical anomaly curves were generated for different geological models for interpreting field magnetic anomalies (Gay 1963, 1965; High and Smith 1975; Atchuta Rao and Ram Babu 1983). The main drawback of the curve matching is the time consumed that it takes for fitting the field magnetic anomaly with a lot of the generated theoretical curves, which are not practical. Another approach was presented utilizing the characteristic curves in which the variation of certain characteristic distances and amplitudes of an anomaly are covered in relation to the causative target parameters (among them Smellie 1956; Bruckshaw and Kunaratnam 1963; Powell 1965, 1967; Grant and West 1965; Moo 1965; Bean 1966; Grant and Martin; 1966; Koulomzine et al. 1970; Am 1972; Telford et al. 1976; Parakasa Rao and Krishna Murthy 1978; Rao and Murthy 1978). Because these methods are highly subjective, they might lead to substantial errors in parameter estimations; hence, this is considered also one of the main drawbacks of these methods. Am (1972) tested carefully the interpretation methods that were published before 1971 and showed many new charts of characteristic curves for manual interpretation of magnetic anomalies ca
Data Loading...
