Document Type : Original Research Paper
Author
Department of Geology, Faculty of Science, Cairo University, Giza, Egypt
Abstract
Innovation in mineral exploration occurs either in the construction of new ore deposit models or the development of new techniques used to locate the ore deposits. Band ratio is the image processing technique developed for mineral exploration. The present study presents a new approach used to evaluate the band ratio technique for discrimination and prediction of the Iron-Titanium mineralization exposed in the Khamal area, Western Saudi Arabia using the ensemble Random Forest model (RF) and SPOT-5 satellite data. SPOT-5 band ratio images are prepared and used as the explanatory variables. The target variable is prepared in which (70%) of the target locations are used for training and the rest are for validation. A confusion matrix and the precision-recall curves are constructed to evaluate the RF model performance and the Receiver Operating Characteristics curves (ROC) are used to rank the band ratio images. Results revealed that the 3/1, 2/1 & 3/2 band ratio images show excellent discrimination with AUC values of 0.986, 0.980 & 0.919 respectively. The present study successfully selects the 3/1 band ratio image as the best classifier and presents a new Fe-Ti mineralization image map. The present study proved the usefulness of the Random Forest classifier for the prediction of the Fe-Ti mineralization with an accuracy of 97%.
Keywords
- AI-based Predictive Model
- Random Forest Algorithm
- SPOT-5 Data
- Fe-Ti Mineralization
- Western Saudi Arabia
Main Subjects
[1]. Madani, A. (2001). Geological studies and remote sensing applications on Wadi Natash volcanic, Eastern Desert, Egypt. PhD thesis, Faculty of Science, Cairo University.
[2]. Tommaso, I., & Rubinstein, N. (2007). Hydrothermal alteration mapping using ASTER data in the Infiernillo porphyry deposit, Argentina. Ore Geol. Rev., 32,275-290.
[3]. Madani, A. (2009). Utilization of landsat ETM+ data for mapping gossans and iron rich zones exposed at Bahrah Area, Western Arabian Shield, Saudi Arabia. JKAU Earth Sci 20(1), 35–49.
[4]. Madani, A., & Emam, A. (2011). SWIR ASTER band ratios for lithological mapping and mineral exploration: a case study from El Hudi area, South Eastern Desert, Egypt. Arab J Geosci 4, 45–52.
[5]. Nouri, R., Jafari, MR., Arian, F., & Feizi, F. (2012). Hydrothermal alteration zone identification based on remote sensing data in the Mahn Area, West of Qazvin Province Iran. World Acad Sci Eng Technol, 67, 479-482.
[6]. Madani, A., & Harbi, H. (2012). Spectroscopy of the mineralized tonalite–diorite intrusions, Bulghah gold mine area, Saudi Arabia: effects of opaques and alteration products on FieldSpec data. Ore Geol Rev 44,148–157.
[7]. Harbi, H., & Madani, A. (2013). Utilization of SPOT 5 data for mapping gold mineralized diorite–tonalite intrusion, Bulghah gold mine area, Saudi Arabia. Arab J Geosci,.
[8]. Tayebi, MH., Hashemi, TM., & Keller, VR. (2014). Alteration mineral mapping with ASTER data by integration of coded spectral ratio imaging and SOM neural network model. Turkish J. Earth Sci., 23, 627-644,
[9]. Madani, A. (2015). Spectroscopy of olivine basalts using FieldSpec and ASTER data: a case study from Wadi Natash volcanic field, South Eastern Desert, Egypt. J Earth Syst Sci 124(7), 1475–1486.
[10]. Sadiya, TB., Halilu, AS., Asmah, TF., Agu, NV., Nsofor, CJ., Sanusi, M., Aliyu, I., & Ibrahim, I. (2015). Hydrothermal alteration mapping in Ijio, Oyo state, Nigeria using satellite imagery & remote sensing technique. SSRG Int. J. Geo Inform. Geolog. Sci. (SSRG-IJGGS), 2, 2.
[11]. Zhang, Z., Zuo, R., & Xiong, Y. (2016). A comparative study of fuzzy weights of evidence and random forests for mapping mineral prospectivity for skarn-type Fe deposits in the southwestern Fujian metallogenic belt, China. Science China Earth Sciences 59,556–572.
[12]. Rajendran, S., & Nasir, S. (2017). Characterization of STER spectral bands for mapping of alteration zones of volcanogenic massive sulphide deposits. Ore Geology Reviews 88, 317–335.
[13]. Zamyad, M., Afzal, P., Pourkermani, M., Nouri, R., & Jafari, MR. (2019). Determination of hydrothermal alteration zones using remote sensing methods in Tirka Area, Toroud, NE Iran. J. Indian Soc. Remote Sens., 47(11), 1817-1830.
[14]. Traore, M., Takodjou, Wambo, JD., Ndepete, CP., Tekin, S., Pour, AB., & Muslim, AM. (2020). Lithological and alteration mineral mapping for alluvial gold exploration in the south east of Birao area, Central African Republic using Landsat-8 Operational Land Imager (OLI) data. J. Afr. Earth Sci. p.170.
[15]. Shi, X., Al-Arifi, N., Abdelkareem, M., & Abdalla, F. (2020). Application of remote sensing and GIS techniques for exploring potential areas of hydrothermal mineralization in the central Eastern Desert of Egypt. J. Taibah Univ. Sci. 14, 1421–1432.
[16]. Sekandari, M., Masoumi, I., Pour, AB., Muslim, AM., Rahmani, O., Hashim, M., Zoheir, B., Pradhan, B., Misra, A., & Aminpour, SM. (2020). Application of Landsat-8, Sentinel-2, ASTER andWorldView-3 Spectral Imagery for Exploration of Carbonate-Hosted Pb-Zn Deposits in the Central Iranian Terrane (CIT). Remote Sens. 12, 1239.
[17]. El Sobky, MA., Madani, AA., & Surour, AA. (2020). Spectral characterization of the Batuga granite pluton, South Eastern Desert, Egypt: influence of lithological and mineralogical variation on ASD Terraspec data. Arabian Journal of Geosciences 13, 1246.
[18]. Sadek, MF., El-Kalioubi, BA., Ali-Bik, MW., El Hefnawi, MA., & Elnazer, AA. (2020). Utilizing Landsat-8 and ASTER data in geologic mapping of hyper-arid mountainous region: case of Gabal Batoga area, South Eastern Desert of Egypt. Environ Earth Sci 79(5), 1–14.
[19]. El-Din, GM., El-Noby, ME., Abdelkareem, ZM., & Hamimi, Z. (2021). Using multispectral and radar remote sensing data for geological investigation, Qena-Safaga Shear Zone, Eastern Desert, Egypt. Arab. J. Geosci. 14, 997.
[20]. Madani, AA., Harbi, HM., El-Dougdoug, AA., Surour, AA., & Ahmed, AH. (2021). Spectral Characteristics of Listvenites and Serpentineites Along Ophiolite-Decorated Megashears (Suture Zones) in the Arabian Shield Using ASD Fieldspec and Satellite Data in:Hamimi (ed) The Geology of the Arabian-Nubian Shield, Springer, Cham, 559-583.
[21]. Ige, O., Tende, A., Bale, R., Gajere, J., & Aminu, M. (2022). Spatial mapping of hydrothermal alterations and structural features for gold and cassiterite exploration. Scientific African Volume 17, September 2022, e01307.
[22]. Abd El-Fatah, A., Madani, A., Surour, A., & Azer, M. (2023). Integration of Landsat-8 and Reflectance Spectroscopy data for Mapping of Late Neoproterozoic Igneous Ring Complexes in an Arid Environment: a Case Study of Gebel El-Bakriyah Area, Eastern Desert, Egypt. Journal of Mining and Environment (JME).
[23]. Ali, D., & Frimpong, S. (2020). Artificial intelligence, machine learning and process automation: Existing knowledge frontier and way forward for mining sector. Artif. Intell. Rev. 53, 6025–6042.
[24]. Brown, WM., Gedeon, TD., Groves, D., & Barnes, RG. (2000). Artificial neural networks: A new method for mineral prospectivity mapping. Australian Journal of Earth Sciences 47, 757–770.
[25]. Carranza, EJ. (2014). Data-driven evidential belief modeling of mineral potential using few prospects and evidence with missing values. Natural Resources Research 24, 291–304.
[26]. Porwal, A., Carranza, EJ., Hale, M. (2003). Artificial neural networks for mineral-potential mapping: A case study from Aravalli Province, western India. Nat Resour Res 12, 155–171.
[27]. Fung, CC., Iyer, V., Brown, W., & Wong, KW. (2005). Comparing the performance of different neural networks architectures for the prediction of mineral prospectivity. In Proceedings of the fourth international conference on machine learning and cybernetics, Guangzhou 394–398.
[28]. Abedi, M., Norouzi, GH., & Bahroudi, A. (2012). Support vector machine for multi- classification of mineral prospectivity areas. Computers Geosciences 46, 272–283.
[29]. Rodriguez-Galiano, VF., Chica-Olmo, M., & Chica-Rivas, M. (2014). Predictive modelling of gold potential with the integration of multisource information based on random forest: A case study on the Rodalquilar area, Southern Spain. Int J Geogr Inf Sci 28, 1336–1354.
[30]. Carranza, EJ., & Laborte, AG. (2015b). Random forest predictive modeling of mineral prospectivity with small number of prospects and data with missing values in Abra (Philippines). Computers & Geosciences 74, 60–70.
[31]. Zhang, Z., Zuo, R., & Xiong, Y. (2015). A comparative study of fuzzy weights of evidence and random forests for mapping mineral prospectivity for skarn-type fe deposits in the southwestern Fujian metallogenic belt, China. Sci China Earth Sci 59, 556–572.
[32]. Carranza, EJ., & Laborte, AG. (2016). Data-driven predictive modeling of mineral prospectivity using random forest: a case study in Catanduanes Island (Philippines). Natural Resources Research 25, 35-50.
[33]. Rodriguez-Galiano, V., Sanchez-Castillo, M., Chica-Olmo, M., & Chica-Rivas, M. (2015). Machine learning predictive models for mineral prospectivity: An evaluation of neural networks, random forest, regression trees and support vector machines. Ore Geol Rev 71, 804–818.
[34]. McKay, G., & Harris, JR. (2016). Comparison of the data-driven random forests model and a knowledge-driven method for mineral prospectivity mapping: A case study for gold deposits around the Huritz Group and Nueltin Suite, Nunavut, Canada. Natural Resources Research 25, 125–143.
[35]. Zhang, Z., Zuo, R., & Xiong, Y. (2016). A comparative study of fuzzy weights of evidence and random forests for mapping mineral prospectivity for skarn-type Fe deposits in the southwestern Fujian metallogenic belt, China. Science China Earth Sciences 59, 556–572.
[36]. Hariharan, S., Tirodkar, S., Porwal, A., Bhattacharya, A., & Joly, A. (2017). Random forest-based prospectivity modelling of greenfieldterrains using sparse deposit data: An example from the Tanami Region,Western Australia. Nat Resour Res 26, 489–507.
[37]. Wang,Y., Fang, Z., & Hong, H. (2019). Comparison of convolutional neural networks for landslide susceptibility mapping in Yanshan County, China. Sci Total Environ 666, 975–993.
[38]. Sun, T., Chen, F., Zhong, L., Liu, W., & Wang, Y. (2019). GIS-based mineral prospectivity mapping using machine learning methods: A case study from Tongling ore district, eastern China. Ore Geol Rev 109, 26–49.
[39]. Chen, C., He, B., & Zeng, Z. (2014). A method for mineral prospectivity mapping integrating C4. 5 decision tree, weights-of-evidence and m-branch smoothing techniques: a case study in the eastern Kunlun Mountains, China. Earth Science Informatics 7, 13–24.
[40]. Sun, T., Hui, Li., Kaixing, Wu., Fei Chen, Zhong Zhu, & Zijuan Hu (2020). Data-Driven Predictive Modelling of Mineral Prospectivity Using Machine Learning and Deep Learning Methods: A Case Study from Southern Jiangxi Province, China. Minerals, 10(2),102.
[41]. Jooshaki, M., Nad, A., & Michaux, S. (2021). A Systematic Review on the Application of Machine Learning in Exploiting Mineralogical Data in Mining and Mineral Industry. Minerals 11, 816.
[42]. Li, S., Chen, J., & Liu, C. (2022). Overview on the Development of Intelligent Methods for Mineral Resource Prediction under the Background of Geological Big Data. Minerals 12, 616.
[43]. Farhadi, S., Afzal, P., Boveiri Konari, M., Daneshvar Saein, L., & Sadeghi, B., (2022). Combination of machine learning algorithms with concentration-area fractal method for soil geochemical anomaly detection in sediment-hosted Irankuh Pb-Zn deposit, Central Iran. Minerals 12(6), 689.
[44]. Afzal, P., Farhadi, S., Konari, MB., Meigooni, MS., & Saein, LD., (2022). Geochemical anomaly detection in the Irankuh District using Hybrid Machine learning technique and fractal modeling. Geopersia 12(1), 191-199.
[45]. Farhadi, S., Tatullo, S., Konari, MB., & Afzal, P., (2024). Evaluating StackingC and ensemble models for enhanced lithological classification in geological mapping. Journal of Geochemical Exploration 260, 107441.
[46]. Bonham-Carter, G. (1994). Geographic information systems for geoscientists: Modelling with GIS. Oxford:Pergamon Press.
[47]. Carranza, EJ., Mangaoang, JC., & Hale, M. (1999). Application of mineral exploration models and GIS to generate mineral potential maps as input for optimum land-use planning in the Philippines. Natural Resources Research 8, 165–173.
[48]. Singer, DA., & Kouda, R. (1999). A Comparison of the weights of evidence method and probabilistic neural networks. Natural Resources Research 8, 87–298.
[49]. Asadi, HH., & Hale, M. (2001). A predictive GIS model for mapping potential gold and base metal mineralization in Takab area, Iran. Comput Geosci 27, 901–912.
[50]. Chica-Olmo, M., Abarca, F., & Rigol, JP. (2002). Development of a Decision Support System based on remote sensing and GIS techniques for gold-rich area identification in SE Spain. International Journal of Remote Sensing, 23(22), 4801-4814.
[51]. Harris, D., Zurcher, L., Stanley, M., Marlow, J., & Pan, G. (2003). A comparative analysis of favorability mappings by weights of evidence, probabilistic neural networks, discriminant analysis, and logistic regression. Nat Res Res 12, 241-255.
[52]. Carranza, EJ., Woldai, T., & Chikambwe, EM. (2005). Application of data-driven evidential belief functions to prospectivity mapping for aquamarine-bearing pegmatites, Lundazi District, Zambia. Natural Resources Research 14, 47–63.
[53]. Caumon, GJ., Ortiz, O., & Rabeau, (2006). A comparative study of three data-driven Mineral Potential Mapping techniques. Int. Assoc. for Mathematical Geology XIth International Congress Université de Liège – Belgium Liège – September, 3rd - 8th S13-05.
[54]. Carranza, EJ., van Ruitenbeek, FJ., Hecker, C., van der Meijde, M., & van der Meer, FD. (2008). Knowledge-guided data-driven evidential belief modeling of mineral prospectivity in Cabo de Gata, SE Spain. Int J Appl Earth Obs 10, 374–387.
[55]. Partington, G. (2010). Developing models using GIS to assess geological and economic risk: An example from VMS copper gold mineral exploration in Oman. Ore Geology Reviews 38, 197–207.
[56]. Madani, A. (2011). Knowledge-driven GIS modeling technique for gold exploration, Bulghah gold mine area, Saudi Arabia. Egypt J Remote Sensing and Space Sci 14:91–97.
[57]. Joly, A., Porwal, A., & McCuaig, TC. (2012). Exploration targeting for orogenic gold deposits in the Granites-Tanami Orogen: Mineral system analysis, targeting model and prospectivity analysis. Ore Geology Reviews 48, 349–383.
[58]. Ford, A., Miller, JM., & Mol, AG. (2015). A comparative analysis of weights of evidence, evidential belief functions, and fuzzy logic for mineral potential mapping using incomplete data at the scale of investigation. Natural Resources Research 25, 19–33.
[59]. Carranza, EJ., & Laborte, AG. (2015a). Data-driven predictive mapping of gold prospectivity, Baguio district, Philippines: application of Random Forest algorithm. Ore Geology Reviews 71, 777–787.
[60]. Harris, JR., Grunsky, E., Behnia, P., & Corrigan, D. (2015). Data- and knowledge-driven mineral prospectivity maps for Canada's North. Ore Geology Reviews 71:788-803.
[61]. Sun, T., Wu, K., Chen, L., Liu, W., Wang, Y., & Zhang, C. (2017). Joint application of fractal analysis and weights-of-evidence method for revealing the geological controls on regional-scale tungsten mineralization in southern Jiangxi Province, China. Minerals 7, 243.
[62]. Olasehinde, A., & Ashano, E. (2021). Data Driven Predictive Modelling of Mineral Prospectivity Using Principal Component Analysis: A Case Study of Riruwai Complex. Advances in Applied Science Research 12(7), 33.
[63]. Atef, A., Madani, A., Surour, A., & Azer, M. (2023). A predictive GIS model for mapping gold- and copper-bearing alteration zones at South Gabal Um Monqul and Gabal Al Kharaza prospects, north Eastern Desert, Egypt. Journal of mining and environment.
[64]. Taha, AM., Xi, Y., He, Q., Hu, A., Wang, S., & Liu, X. (2023), Investigating the Capabilities of Various Multispectral Remote Sensors Data to Map Mineral Prospectivity Based on Random Forest Predictive Model: A Case Study for Gold Deposits in Hamissana Area, NE Sudan. Minerals 13, 49.
[65]. Chevremont, P., & Johan, Z., (1981). Wadi Khamal-Wadi Murattijah Ultramafic-Mafic Layered Complex, Saudi Arabian. Deputy Ministry for Mineral Resources: Open File Report BRGMOF-01,36, 143.
[66]. Harbi, HM. (2008). Geology and Lithostratigraphy of the Ultramafic-Mafic Rocks and Associated Mineralizations, Wadi Khamal Area, West-Central Arabian Shield. JKAU: Earth Sci 19, 119-157.
[67]. Bache, J., & Chevermont, P. (1976). Mineral Investigations for Nickel and Copper in the Wadi Khamal Region: Bureau de Recherches Geologiques et Minieres, Open-File-Report-JED-OR-79(8),37.
[68]. Pellaton, C. (1979). Geologic Map of the Yanbu Al Bahr Quadrangle, Sheet 24C, Kingdom of Saudi Arabia, Saudi Dir. Gen. Miner. Resour. Geologic Map GM-48-A, 16.
[69]. Hashem, WB. (1981). The Geology of the Wadi Khamal Basic Layered Intrusion, Yanbou Al Bahr, Saudi Arabia, Unpublished Ph.D. Thesis, University of Bristol UK.
[70]. Al Ghamdi, AM. (1994). Mineralization and Associated Platinum Group Elements in mafic-ultramafic rocks, Northwestern Arabian Shield, K.S.A: Unpublished Ph.D. Thesis, King Abdulaziz University, Faculty of Earth Sciences.
[71]. Eldougdoug, A., Abd El-Rahman, Y., & Harbi, H. (2020). The Ediacaran Post-Collisional Khamal Gabbro-Anorthosite Complex from the Arabian Shield and Its Fe-Ti-P Ore: An Analogy to Proterozoic Massif-Type Anorthosites. Lithos 372–373, 105674.
[72]. Abuamarah, B A., Alshehri, F., Azer, MK., & Asimow, PD. (2023). Loveringite from the Khamal Layered Mafic Intrusion: The First Occurrence in the Arabian Shield, Northwest Saudi Arabia. Minerals 13,172.
[73]. Galaup, M., & Dupuy, S. (2003). Benefits of SPOT 5 imagery for town planning with new adapted processing techniques. Proceedings of IGARSS 2003, IEEE International Geoscience and Remote Sensing symposium.
[74]. Clandillon, S., Yesou, H., & Meyer, C. (2003). Benefits of SPOT 5 HR and VHR data for forest management and windfall damage mapping. Proceedings of IGARSS, IEEE International Geoscience and Remote Sensing symposium.
[75]. Yésou, H, Clandillon, S., Allenbach, B., Bestault, C., De Fraipont, P., Inglada, J., & Favard, C. (2003). A constellation of advantages with SPOT SWIR and VHR SPOT 5 data for flood extent mapping during the September 2002 Gard event (France). Proceedings of IGARSS 2003, IEEE International Geoscience and Remote Sensing symposium.
[76]. Kakiuchi, H., Onaka, M., Asai, M., & Itoh, F. (2004). Topographic mapping at scale of 1:25,000 using SPOT 5 satellite imagery. ISPRS 2004, Istanbul, Turkey.
[77]. Ferreira, F. (2004). Using SPOT 5 to improve census cartography. ISPRS, Istanbul, Turkey.
[78]. Retière, A., Senegas, O., Parriaux, A., Haeberlin, Y., & Turberg, P. (2004). Validation of SPOT 5 satellite imagery for geological hazard identification and risk assessment for landslides, mud- and debris flows in Matagalpa, Nicaragua. ISPRS 2004, Istanbul, Turkey.
[79]. Fajji, NG., Palamuleni, LG., & Mlambo, V. (2018). Application of SPOT Imagery for Landcover Mapping and Assessing Indicators of Erosion and Proportion of Bareground in Arid and Semi-arid Environment. J Remote Sens GIS 7, 240.
[80]. Breiman, L. (2001). Random forests. Machine learning 45, 5-32.
[81]. Madani, A., & Niyazi, B. (2023). Groundwater Potential Mapping Using Remote Sensing and Random Forest Machine Learning Model: A Case Study from Lower Part of Wadi Yalamlam,Western Saudi Arabia. Sustainability 2023, 15, 2772.
[82]. O’Brien, JJ., Spry, PG., Nettleton, D., Xu, R., & Teale, GS. (2015). Using Random Forests to distinguish gahnite compositions as an exploration guide to Broken Hill-type Pb–Zn–Ag deposits in the Broken Hill domain, Australia. J Geochem Explor 149, 74–86.
[83]. Long, T., Zhou, Z., Hancke, G., Bai, Y., & Gao, Q. (2022). A Review of Artificial Intelligence Technologies in Mineral Identification: Classification and Visualization. J. Sens. Actuator Netw. 2022, 11, 50.
[84]. Davis, J., & Goadrich, M., (2006). The relationship between Precision-Recall and ROC curves. Proceedings of the 23rd international conference on Machine learning. 233–240.
[85]. Saito, T., & Rehmsmeier, M. (2015). The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced Datasets. PLoS ONE 10(3): e0118432.
[86]. Fawcett, T. (2005). An introduction to ROC analysis. Pattern Recognition Letters 27, 861–874.
)