Machine Learning Algorithms for Automatic Lithological Mapping Using Remote Sensing Data: A Case Study from Souk Arbaa Sahel, Sidi Ifni Inlier, Western Anti-Atlas, Morocco

Abstract

Remote sensing data proved to be a valuable resource in a variety of earth science applications. Using high-dimensional data with advanced methods such as machine learning algorithms (MLAs), a sub-domain of artificial intelligence, enhances lithological mapping by spectral classification. Support vector machines (SVM) are one of the most popular MLAs with the ability to define non-linear decision boundaries in high-dimensional feature space by solving a quadratic optimization problem. This paper describes a supervised classification method considering SVM for lithological mapping in the region of Souk Arbaa Sahel belonging to the Sidi Ifni inlier, located in southern Morocco (Western Anti-Atlas). The aims of this study were (1) to refine the existing lithological map of this region, and (2) to evaluate and study the performance of the SVM approach by using combined spectral features of Landsat 8 OLI with digital elevation model (DEM) geomorphometric attributes of ALOS/PALSAR data. We performed an SVM classification method to allow the joint use of geomorphometric features and multispectral data of Landsat 8 OLI. The results indicated an overall classification accuracy of 85%. From the results obtained, we can conclude that the classification approach produced an image containing lithological units which easily identified formations such as silt, alluvium, limestone, dolomite, conglomerate, sandstone, rhyolite, andesite, granodiorite, quartzite, lutite, and ignimbrite, coinciding with those already existing on the published geological map. This result confirms the ability of SVM as a supervised learning algorithm for lithological mapping purposes.

Updated Lithological Map in the Forest Zone of the Centre, South and East Regions of Cameroon Using Multilayer Perceptron Neural Network and Landsat Images

“…Satellite remote-sensing data and advances in digital image processing (DIP) techniques provided a new impulse to the development of lithological mapping (Imane et al, 2019). Spectral data from space and airborne sensors were widely applied to geological mapping, including lithological discrimination (Ninomiya et al, 2005), structural mapping (Raharimahefa & Kusky, 2009), hydrothermal alteration (Zhang et al, 2016), and economic mineral deposits (Cardoso-Fernandes et al, 2019).…”

“…The architecture is important to achieve top performance, but, like most machine learning algorithms, the quality of the input data is generally more critical than the specific algorithm used (Latifoc et al, 2018). (Imane et al, 2019), worked on a supervised classification method considering SVM (Support Vector Machine) for lithological mapping in the region of Souk Arbaa Sahel belonging to the Sidi Ifni inlier, located in southern Morocco (Western Anti-Atlas). The aims of their study were firstly to refine the existing lithological map of this region, and secondly to evaluate and study the performance of the SVM approach by using combined spectral features of Landsat 8 OLI (Operational Land Imager) with digital elevation model (DEM) geomorphometric attributes of ALOS/PALSAR data.…”

“…They performed a SVM classification method to allow the joint use of geomorphometric features and multispectral data of Landsat 8 OLI and results indicated an overall classification accuracy of 85%. The SVM and ANN were not able to detect a large quartz vein because of several factors including vegetation cover, atmospheric effects, heterogeneity of the chemical and mineralogical composition of the rock at the sub-pixel level, spectral and spatial resolution of the image, and soil presence (Imane et al, 2019). All these factors affect the spectral responses of the lithological units even after rigorous pre-processing tasks.…”

Remote Sensing Exploration of Fullerene Bearing Shungite in Mangampet Baryte Mines, India

“…Different kernels are used to convert the nonlinear space to linear space of higher dimension, which effectively de nes the optimal hyperplane in nonlinear classi cations. The radial basis function (RBF) is the most used kernel for lithological mapping 16,21,46 . In the present study, the SVM classi cation of Landsat 8 data is used for demarcating the boundaries of shungite rocks using the training pixels collected by ground truth and geological map.…”

“…A wide range of mineral types ranging from copper-gold mineralization, chromite occurrences, ma c-ultrama c rocks, hydrothermal alteration minerals, beach minerals were successfully demarcated using remote sensing data and techniques. Apart from band ratio, spectral indices and PCA, advanced image classi cation algorithms including Machine Learning, Random Forest, and Arti cial neural networks were also used for mapping lithology 21 , gold mineralization 22 , Cu potential areas 23 , etc. In mineral exploration studies, structural and geochemical characterisation is fundamental to con rm the mineral type, grain size, etc.…”