3D Geophysical Post-Inversion Feature Extraction for Mineral Exploration through Fast-ICA

Abstract

A major problem in the post-inversion geophysical interpretation is the extraction of geological information from inverted physical property models, which do not necessarily represent all underlying geological features. No matter how accurate the inversions are, each inverted physical property model is sensitive to limited aspects of subsurface geology and is insensitive to other geological features that are otherwise detectable with complementary physical property models. Therefore, specific parts of the geological model can be reconstructed from different physical property models. To show how this reconstruction works, we simulated a complex geological system that comprised an original layered Earth model that has passed several geological deformations and alteration overprints. Linear combination of complex geological features comprised three physical property distributions: electrical resistivity, induced polarization chargeability, and magnetic susceptibility models. This study proposes a multivariate feature extraction approach to extract information about the underlying geological features comprising the bulk physical properties. We evaluated our method in numerical simulations and compared three feature extraction algorithms to see the tolerance of each method to the geological artifacts and noises. We show that the fast-independent component analysis (Fast-ICA) algorithm by negentropy maximization is a robust method in the geological feature extraction that can handle the added unknown geological noises. The post-inversion physical properties were also used to reconstruct the underlying geological sources. We show that the sharpness of the inverted images is an important constraint on the feature extraction process. Our method successfully separates geological features in multiple 3D physical property models. This methodology is reproducible for any number of lithologies and physical property combinations and can recover the latent geological features, including the background geological patterns from overprints of chemical alteration.

3D Geophysical Predictive Modeling by Spectral Feature Subset Selection in Mineral Exploration

“…Even if the geophysical inversion provides the most accurate physical property distributions, each physical property image provides only partial information about subsurface geology. This phenomenon can be seen as a linear mixing process, and ICA can help to reconstruct the hidden geological features from multiple physical property images [17,18]. The advantage of this method is that it can separate the host geology from alteration overprints in multidimensional physical property space [17].…”

“…This phenomenon can be seen as a linear mixing process, and ICA can help to reconstruct the hidden geological features from multiple physical property images [17,18]. The advantage of this method is that it can separate the host geology from alteration overprints in multidimensional physical property space [17].…”

“…PCA is an unsupervised algorithm that linearly transforms the multivariate datasets into new features called Principal Components (PCs) by maximizing the variance of the input data [14,16]. However, the uncorrelatedness of principal components is a weaker form of independence; therefore, PCA is not a good choice for separating overlapped features inside multiple physical property images [17]. Alternatively, independent component analysis (ICA), precisely the negentropy maximization approach, has been proposed as a robust tool for separating background lithotypes from alteration events [17,18].…”

“…However, the uncorrelatedness of principal components is a weaker form of independence; therefore, PCA is not a good choice for separating overlapped features inside multiple physical property images [17]. Alternatively, independent component analysis (ICA), precisely the negentropy maximization approach, has been proposed as a robust tool for separating background lithotypes from alteration events [17,18]. Unlike PCA, ICA performs beyond the Gaussian assumption and incorporates higher-order statistics to find maximally independent latent features [14,16].…”

Integrated geophysical approach for ore exploration: Case study of Sidi Bou Aouane–Khadhkhadha Pb–Zn province – Northern Tunisia

“…Thus, the detected anomalous regions reflect the nature, size, shape and position to restrict the target to the more likely potential mineralized area (Dentith et al., 1994; Ford et al., 2007; Zaid et al., 2022). When targeting sulphide minerals, electrical methods (mainly IP and electrical resistivity) are deemed to be the best selection (Abbassi & Cheng, 2021; Flores & Peralta‐Ortega, 2009; Mammo, 2013; Mostafaei & Ramazi, 2019). Gravity is useful in detecting ore deposit when density contrast is high.…”