Ge, W., Cheng, Q., Tang, Y., Jing, L. and Gao, C. (2018) Lithological Classification Using Sentinel-2A Data in the Shibanjing Ophiolite Complex in Inner Mongolia, China. Remote Sensing, 10, 638.
https://doi.org/10.3390/rs10040638

has been cited by the following article:

• TITLE: Lithological Mapping Using Landsat 8 OLI in the Meso-Cenozoic Tarfaya Laayoune Basin (South of Morocco): Comparison between ANN and SID Classification

  AUTHORS: Amine Bouwafoud, Mustapha Mouflih, Abdelmajid Benbouziane

  KEYWORDS: Tarfaya-Laayoune Basin, Geological Mapping, Supervised Classification, Artificial Neural Network, Spectral Information Divergence

  JOURNAL NAME: Open Journal of Geology, Vol.11 No.12, December 20, 2021

  ABSTRACT: In the Saharian domain, the Tarfaya-Laayoune coastal basin developed in a stable passive margin, where asymmetrical sedimentation increase from East to West and reach a sediment stack of about 14 kilometers. However, the morphology of the studied area corresponds to a vast plateau (hamada) presenting occasional major reliefs. For this purpose, remote sensing approach has been applied to find the best approaches for truthful lithological mapping. The two supervised classification methods by machine learning (Artificial Neural Network and Spectral Information Divergence) have been evaluated for a most accurate classification to be used for our lithofacies mapping. The latest geological maps and RGB images were used for pseudo-color groups to identify important areas and collect the ROIs that will serve as facilities samples for the classifications. The results obtained showed a clear distinction between the various formation units, and very close results to the field reality in the ANN classification of the studied area. Thus, the ANN method is more accurate with an overall accuracy of 92.56% and a Kappa coefficient is 0.9143.