Geological mapping using extreme gradient boosting and the deep neural networks: application to silet area, central Hoggar, Algeria

• Autorzy: Elbegue Abderrahmane Aref , Allek Karim , Zeghouane Hocine

Identyfikatory

DOI

10.1007/s11600-022-00814-7

• Języki publikacji: EN

Abstrakty

EN

Nowadays, machine learning algorithms are considered a powerful tool for analyzing big and complex data due to their ability to deliver accurate and fast results. The main objective of the present study is to prove the effectiveness of the extreme gradient boosting (XGBoost) method as well as employed data types in the Saharan region mapping. To reveal the potential of the XGBoost, we conducted two experiments. The first was to use different combinations of: airborne gamma-ray spectrometry data, airborne magnetic data, Landsat 8 data and digital elevation model. The objective is to train 9 XGBoost models in order to determine each data type sensitivity in capturing the lithological rock classes. The second experiment was to compare the XGBoost to deep neural networks (DNN) to display its potential against other machine learning algorithms. Compared to the existing geological map, the application of XGBoost reveals a great potential for geological mapping as it was able to achieve a correlation score of (78%) where igneous and metamorphic rocks are easily identified compared to sedimentary rocks. In addition, using different data combinations reveals airborne magnetic data utility to discriminate some lithological units. It also reveals the potential of the apparent density, derived from airborne magnetic data, to improve the algorithm’s accuracy up to 20%. Furthermore, the second experiment in this study indicates that the XGBoost is a better choice for the geological mapping task compared to the DNN. The obtained predicted map shows that the XGBoost method provides an efficient tool to update existing geological maps and to edit new geological maps in the region with well outcropped rocks.

Słowa kluczowe

EN

machine learning; geological mapping; airborne geophysical data; Landsat 8; XGBoost; Hoggar

PL

nauczanie maszynowe; mapowanie geologiczne; lotnicze dane geofizyczne; Landsat 8; XGBoost; Hoggar

• Wydawca: Instytut Geofizyki PAN ; Springer
• Czasopismo: Acta Geophysica
• Rocznik: 2022
• Tom: Vol. 70, no 4
• Strony: 1581--1599
• Opis fizyczny: Bibliogr. 37 poz.

Twórcy

autor

Elbegue Abderrahmane Aref

• Laboratoire de Physique de la Terre, Université M’hamed Bougara, Boumerdes, Algeria

• https://orcid.org/0000-0001-7477-4680

autor

Allek Karim

• Laboratoire de Physique de la Terre, Université M’hamed Bougara, Boumerdes, Algeria

autor

Zeghouane Hocine

• Department of Geological Sciences, Mouloud Mammeri University, Tizi Ouzou, Algeria

Bibliografia

• 1. Abdi AM (2020) Land cover and land use classification performance of machine learning algorithms in a boreal landscape using Sentinel-2 data. Giscience Remote Sens 57:1–20
• 2. Bertrand J-M, Michard A, Boullier A-M, Dautel D (1986) Structure and U/Pb geochronology of Central Hoggar (Algeria): a reappraisal of its Pan-African evolution. Tectonics 5:955–972
• 3. Bertrand JM (1974) Evolution polycyclique des gneiss précambriens de l’Aleksod (Hoggar central, Sahara algérien): aspects structuraux, pétrologiques, géochimiques et géochronologiques. Université Montpellier II-Sciences et Techniques du Languedoc
• 4. Bressan TS, Kehl de Souza M, Girelli TJ, Junior FC (2020) Evaluation of machine learning methods for lithology classification using geophysical data. Comput Geosci 139:104475. https://doi.org/10.1016/j.cageo.2020.104475
• 5. Caby R, Dostal J, Dupuy C (1977) Upper proterozoic volcanic graywackes from northwestern Hoggar (Algeria)—geology and geochemistry. Precambrian Res 5:283–297. https://doi.org/10.1016/0301-9268(77)90034-1
• 6. Chen T, Guestrin C (2016) XGBoost: a scalable tree boosting system. In: Proceedings of 22nd ACM SIGKDD international conference knowledge discovery data min 785–794. https://doi.org/10.1145/2939672.2939785
• 7. Cohen J (1960) A coefficient of agreement for nominal scales. Educ Psychol Meas 20:37–46. https://doi.org/10.1177/001316446002000104
• 8. Cracknell MJ, Reading AM (2014) Geological mapping using remote sensing data: a comparison of five machine learning algorithms, their response to variations in the spatial distribution of training data and the use of explicit spatial information. Comput Geosci 63:22–33. https://doi.org/10.1016/j.cageo.2013.10.008
• 9. Cracknell MJ, Reading AM (2013) The upside of uncertainty: Identification of lithology contact zones from airborne geophysics and satellite data using random forests and support vector machines. Geophysics 78:WB113–WB126
• 10. Darnley AG (1993) Some notes on the importance of airborne gamma-ray spectrometry in international geochemical mapping. J Geochemical Explor 49:201–212. https://doi.org/10.1016/0375-6742(93)90045-N
• 11. Dauth C (1997) Airborne magnetic, radiometric and satellite imagery for regolith mapping in the yilgarn craton of western australia. Explor Geophys 28:199–203. https://doi.org/10.1071/EG997199
• 12. Harris JR, Grunsky EC (2015) Predictive lithological mapping of Canada’s North using Random Forest classification applied to geophysical and geochemical data. Comput Geosci 80:9–25
• 13. Harris JR, Juan HX, Rainbird R, Behnia P (2014) Remote predictive mapping 6. A comparison of different remotely sensed data for classifying bedrock types in Canada’s arctic: application of the robust classification method and random forests. Geosci Canada 41:557–584. https://doi.org/10.12789/geocanj.2014.41.062
• 14. Joelsson SR, Benediktsson JA, Sveinsson JR (2007) Random forest classification of remote sensing data. In: Image processing for remote sensing. CRC Press, pp 61–78
• 15. Joharestani MZ, Cao C, Ni X et al (2019) PM2.5 prediction based on random forest, XGBoost, and deep learning using multisource remote sensing data. Atmosphere (basel) 10:373. https://doi.org/10.3390/atmos10070373
• 16. Kuhn M, Johnson K (2013) Applied predictive modeling. Springer, New York
• 17. Kuhn S, Cracknell MJ, Reading AM (2018) Lithologic mapping using Random Forests applied to geophysical and remote-sensing data: a demonstration study from the Eastern Goldfields of Australia. Geophysics 83:B183–B193
• 18. Kusky TM, Ramadan TM (2002) Structural controls on Neoproterozoic mineralization in the South Eastern Desert, Egypt: an integrated field, Landsat TM, and SIR-C/X SAR approach. J Afr Earth Sci 35:107–121. https://doi.org/10.1016/S0899-5362(02)00029-5
• 19. Lee Y, Han D, Ahn M-H et al (2019) Retrieval of total precipitable water from Himawari-8 AHI data: a comparison of random forest, extreme gradient boosting, and deep neural network. Remote Sens 11:1741
• 20. Liégeois JP (2019) A new synthetic geological map of the tuareg shield: an overview of its global structure and geological evolution. In: Springer Geology. pp 83–107
• 21. Ourhzif Z, Algouti A, Algouti A, Hadach F (2019) Lithological mapping using landsat 8 oli and aster multispectral data in imini-ounilla district south high atlas of marrakech. Int Arch Photogramm Remote Sens Spat Inf Sci ISPRS Arch 42:1255–1262. https://doi.org/10.5194/isprs-archives-XLII-2-W13-1255-2019
• 22. Radford DDG, Cracknell MJ, Roach MJ, Cumming GV (2018) Geological mapping in western Tasmania using radar and random forests. IEEE J Sel Top Appl Earth Obs Remote Sens 11:3075–3087
• 23. Rosenblum S, Brownfield IK (2000) Magnetic susceptibilities of minerals. Citeseer, Pennsylvania
• 24. RStudio (2011) RStudio: integrated development environment for R (Version 0.97.311). J Wildl Manag 75:1753–1766
• 25. Sabins FF (1999) Remote sensing for mineral exploration. Ore Geol Rev 14:157–183. https://doi.org/10.1016/S0169-1368(99)00007-4
• 26. Sahin EK (2020) Assessing the predictive capability of ensemble tree methods for landslide susceptibility mapping using XGBoost, gradient boosting machine, and random forest. SN Appl Sci 2:1–17
• 27. Sayler K (2020) Landsat 8 Collection 2 (C2) Level 2 Science Product (L2SP) Guide. 2:
• 28. Shannon CE (1948) A mathematical theory of communication. Bell Syst Tech J 27:379–423
• 29. Slavinski H, Morris B, Ugalde H et al (2010) Integration of lithological, geophysical, and remote sensing information: a basis for remote predictive geological mapping of the Baie Verte Peninsula, Newfoundland. Can J Remote Sens 36:99–118
• 30. Sun T, Chen F, Zhong L et al (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
• 31. Thomas A (2020) Processing and analysis of aster and landsat 8 scenes to aid in geological mapping: a case study of murchison greenstone belt area, South Africa. Geomatics Environ Eng 14:107–123. https://doi.org/10.7494/geom.2020.14.3.107
• 32. Geological Survey US (2016) Landsat 8 data users handbook. Nasa 8:97
• 33. Witten IH, Frank E, Hall MA (2011) Data mining: practical machine learning tools and techniques, 3rd edn. Morgan Kaufmann Publishers Inc., San Francisco
• 34. Yang G, Collins MJ, Gong P (1998) Multisource data selection for lithologic classification with artificial neural networks. Int J Remote Sens 19:3675–3680. https://doi.org/10.1080/014311698213885
• 35. Yawsangratt S (2002) A gravity study of northern Botswana : a new perspective and its implications for regional geology
• 36. Youssef AM, Pourghasemi HR (2021) Landslide susceptibility mapping using machine learning algorithms and comparison of their performance at Abha Basin, Asir Region, Saudi Arabia. Geosci Front 12:639–655
• 37. Youssef MAS, Elkhodary ST (2013) Utilization of airborne gamma ray spectrometric data for geological mapping, radioactive mineral exploration and environmental monitoring of southeastern Aswan city, South Eastern Desert. Egypt Geophys J Int 195:1689–1700. https://doi.org/10.1093/gji/ggt375

Uwagi

PL

Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023).