Journal of Mining Engineering

Journal of Mining Engineering

Modeling oil spring exploration based on their spectral characteristics

Document Type : research - paper

Authors
SHIRIN CHAZANI 1
Parviz Zeaieanfirouzabadi 2
Seyed Mohammad Tavakkoli Sabour 2
1 . Department of Remote Sensing and GIS, Kharazmi University, Iran
2 Department of Remote Sensing and GIS, Kharazmi University, Iran
10.22034/ijme.2024.2016373.1996
Abstract
This research presents a method for extracting the spectral characteristics of oil springs (oil seepages) and their exploration by applying artificial neural networks and maximum likelihood algorithms on Landsat 8 OLI images. The study area covers three provinces: Khuzestan, Fars, kohkiluyeh, and Boyar Ahmad. Vegetation, water, soil spectral indices, and tasseled cap transformation outputs along surface reflectance images generated the feature space required to explore oil springs. Samples were manually collected from all the features of oil springs to identify and explore oil springs, including different land uses and the existing oil springs already recorded by the Ministry of Petroleum. The separability of oil spring samples was examined with the help of spectral values and signs of sample features. Then, using the statistical data of a part of the samples, the feedforward neural network training with 8 hidden layers was carried out and evaluated. Also, the model parameters for the maximum likelihood algorithm were estimated using the extracted samples. Finally, the trained neural network and maximum likelihood algorithm were applied to the spectral characteristics of the entire study area to extract the probable locations of the oil springs. The results based on the test data showed that the neural network with a kappa coefficient of 92.07% and an overall accuracy of 99.53% separated the oil springs from other land uses. However, the maximum likelihood algorithm showed Poor performance in separating the oil springs from other land uses. The kappa coefficient and its overall accuracy were equal to 22.93% and 73.35%, respectively. By examining the classified image obtained from the neural network, 15 new points were extracted as promising locations for oil springs. These points were verified and confirmed by Google Earth images.
Keywords
Oil Spring Reflectance
Oil Polluted Soils
Level 2 Landsat Images
Maximum Likelihood Algorithm
Artificial Neural Networks
Subjects
Sayedain, S. A.; 2013; "Exploration of Oil Seepages (Hydrocarbon) Using Target Detection Algorithms in Hyperspectral Images", M.Sc, K.N. Toosi University of Technology.## Van Der Meer, F., P. Van Dijk, H. Van Der Werff and H. Yang; 2002; "Remote sensing and petroleum seepage: a review and case study" , Terra Nova, 14(1): 1-17. ## Segal, D. B., M. D. Ruth, I. S. Merin, H. Watanabe, K. Soda, O. Takano and M. Sano; 1985; "Remote Detection of Anomalous Mineralogy Associated with Hydrocarbon Production", Lisbon Valley, Utah: ABSTRACT, Mountain Geology, 23(2): 51-62## Ellis, J. M., H. H. Davis and J. A. Zamudio, 2001; "Exploring for onshore oil seep.", Oil and Gas Journal, 99(37): 49-58. ## Xu, D., G. Ni, T. Jiang, L. Jiang and M. Chi; 2007; "Integration of field work and hyperspectral data for oil and gas exploration", IEEE International Geoscience and Remote Sensing Symposium. ## Khan, S. and S. Jacobson (2008). "Remote sensing and geochemistry for detecting hydrocarbon micro-seepages." Geological Society of America Bulletin 120: 95-105## Lammogliaa, T. and C. R. S. Filhoa; 2008; "Characterization of Hydrocarbon Micro seepages in the Tucano Basin, (Brazil) through Hyperspectral Classification and Neural Network Analysis of Advanced Space-borne Thermal Emission and Reflection Radiometer (ASTER) Data.", The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. ## Perry, S. L., F. A. Kruse and C. Carlston; 2011;" Evidence of Hydrocarbon Seepage Using Multispectral Satellite Imagery, Kurdistan, Iraq., 73rd EAGE Conference and Exhibition-Workshops 2011, European Association of Geoscientists & Engineers. ## Hamzeh, M.; 2011; "Identification of Oil Seepages Using Hyperspectral Images", Case Study: Khouzestan Province. M.Sc., University of Tehran. ## Shi, P., B. Fu, Y. Ninomiya, J. Sun and Y. Li; 2012; "Multispectral remote sensing mapping for hydrocarbon seepage-induced lithologic anomalies in the Kuqa foreland basin, south Tian Shan", Journal of Asian Earth Sciences, 46: 70-77. ## Dehban Varmazani, M.; 2016; "Identification of oil pollution area in Khuzestan using multispectral and thermal landsat image and Fieldspec3 Spectroradiometer", M.Sc, Shahid Chamran University of Ahvaz. ## Roberto De la Rosa, Milagrosa Aldana, Vincenzo Costanzo-Alvarez, Santiago Yepez, Cristina Amon.; 2021; “The surface expression of hydrocarbon seeps characterized by satellite image spectral analysis and rock magnetic data (Falcon basin, western Venezuela)”, Journal of South American Earth Sciences, Volume 106, 103036. ## Jinru, X. and B. Su; 2017; "Significant Remote Sensing Vegetation Indices: A Review of Developments and Applications", Journal of Sensors, 2017: 1-17. ## Rasul, A., H. Balzter, G. R. F. Ibrahim, H. M. Hameed, J. Wheeler, B. Adamu, S. a. Ibrahim and P. M. Najmaddin; 2018; "Applying built-up and bare-soil indices from Landsat 8 to cities in dry climates", Land 7(3): 81. ## Sukmono, A., A. Nugraha and H. Firdaus; 2019; "Integration of Leaf Water Content Index (LWCI) and Enhanced Vegetation Index (EVI) for Stress Detection of Rice Plant Using Landsat 8 Satellitte Imagery", KnE Engineering. ## Yan, D., C. Huang and Y. Zhang; 2020; "Improved Landsat-Based Water and Snow Indices for Extracting Lake and Snow Cover/Glacier in the Tibetan Plateau", Water 12. ## Jackson, R. D.; 1983; "Spectral indices in N-Space.", Remote Sensing of Environment, 13(5): 409-421. ## Crist, E. P. and R. J. Kauth; 1986; "The Tasseled Cap de-mystified", Photogrammetric Engineering and Remote Sensing, 52: 81-86. ## Ali, S. M. and S. S. Salman; 2016; " Landsat-8 (OLI) classification method based on tasseled cap transformation features", 2016 Al-Sadeq International Conference on Multidisciplinary in IT and Communication Science and Applications (AIC-MITCSA), Baghdad. ## Jensen, “Introductory Digital Image Processing: A Remote Sensing Perspective, 4th edition. 2015; Pearson series in geographic information science. ##
Journal of Mining Engineering
Volume 19, Issue 63
Spring 2024
Pages 66-96

  • Receive Date 27 November 2023
  • Revise Date 05 June 2024
  • Accept Date 06 July 2024