Geochemical exploration numerical modeling using convolutional neural network (Case study: Gonabad region) | |
| روش های تحلیلی و عددی در مهندسی معدن | |
| مقاله 5، دوره 12، شماره 31، مرداد 1401، صفحه 47-58 اصل مقاله (855.23 K) | |
| نوع مقاله: مقاله پژوهشی | |
| شناسه دیجیتال (DOI): 10.22034/anm.2022.2705 | |
| نویسندگان | |
| Mandana Tahmooresi؛ Behnam Babaei؛ Saeed Dehghan* | |
| Dept. of Mining , Mahallat Branch, Islamic Azad University, Mahallat, Iran. | |
| چکیده | |
| Modeling of mineral potentials to identify promising districts in large exploration regions for detailed exploration operations is one of the main stages of exploration. In this research, a new approach based on a convolutional neural network is proposed for geochemical numerical modeling and mineral potential exploration. In the first step, in order to create the intelligent geochemical exploration modeling, the codes of the convolutional neural network algorithm and its evaluation indicators are programmed in MATLAB environment. After preprocessing of stream sediment geochemical data, including identification of outliers, estimation of censored data, and data normalization and standardization, factor analysis is performed in order to reduce the dimension of the study space, identify the main variables that control the concentration of deposit elements, and define factors. The variables used in modeling are the result of factor analysis of stream sediment data. The average accuracy of the mentioned modeling is obtained as 96%. In the second step, using the geostatistical method (universal kriging), the average accuracy of estimation points via ArcGIS software is calculated to be 75%. At the end of this study, the performances of numerical modeling using convolutional neural network and universal kriging as well as the support vector machine and its integration with the continuous genetic algorithm, which was studied in the previous article, are compared. The evaluation results show that machine learning algorithms are more accurate in identifying promising mineral districts compared to traditional methods. It is important to note that the results of this study are in good agreement with the results of field studies and mineralized sampling. | |
| کلیدواژهها | |
| Numerical modeling؛ Geochemical exploration؛ Convolutional neural network؛ Khorasan Razavi؛ Iran | |
| عنوان مقاله [English] | |
| Geochemical exploration numerical modeling using convolutional neural network (Case study: Gonabad region) | |
| نویسندگان [English] | |
| Mandana Tahmooresi؛ Behnam Babaei؛ Saeed Dehghan | |
| Dept. of Mining , Mahallat Branch, Islamic Azad University, Mahallat, Iran. | |
| چکیده [English] | |
| Modeling of mineral potentials to identify promising districts in large exploration regions for detailed exploration operations is one of the main stages of exploration. In this research, a new approach based on a convolutional neural network is proposed for geochemical numerical modeling and mineral potential exploration. In the first step, in order to create the intelligent geochemical exploration modeling, the codes of the convolutional neural network algorithm and its evaluation indicators are programmed in MATLAB environment. After preprocessing of stream sediment geochemical data, including identification of outliers, estimation of censored data, and data normalization and standardization, factor analysis is performed in order to reduce the dimension of the study space, identify the main variables that control the concentration of deposit elements, and define factors. The variables used in modeling are the result of factor analysis of stream sediment data. The average accuracy of the mentioned modeling is obtained as 96%. In the second step, using the geostatistical method (universal kriging), the average accuracy of estimation points via ArcGIS software is calculated to be 75%. At the end of this study, the performances of numerical modeling using convolutional neural network and universal kriging as well as the support vector machine and its integration with the continuous genetic algorithm, which was studied in the previous article, are compared. The evaluation results show that machine learning algorithms are more accurate in identifying promising mineral districts compared to traditional methods. It is important to note that the results of this study are in good agreement with the results of field studies and mineralized sampling. | |
| کلیدواژهها [English] | |
| Numerical modeling, Geochemical exploration, Convolutional neural network, Khorasan Razavi, Iran | |
| مراجع | |
|
[1] Haohan Wang, and Bhiksha Raj, “On the Origin of Deep Learning,” ArXiv: 1702.07800v4 [cs.LG] 3 Mar 2017.
[2] Leon F. Palafox, Christopher W. Hamilton, Stephen P. Scheidt, and Alexander M. Alvarez, “Automated detection of geological landforms on Mars using Convolutional Neural Networks,” Computers & Geosciences, vol. 101, pp. 48-56, 2017.
[3] Rafael Pires de Lima, Alicia Bonar, David Duarte Coronado, Kurt Marfurt, and Charles Nicholson, “Deep convolutional neural networks as a geological image classification tool,” The Sedimentary Record, pp. 4-9, 2019.
[4] E.E. Baraboshkin, L.S. Ismailova, D.M. Orlov, E.A. Zhukovskaya, G.A. Kalmykov, O.V. Khotylev, E.Yu. Baraboshkin, and D.A. Koroteev, “Deep Convolutions for In-Depth Automated Rock Typing,” arXiv:1909.10227v3 [cs.CV] 27 Sep 2019.
[5] Nzurumike Obianuju Lynda, “Systematic survey of convolutional neural network in satellite image classification for geological mapping,” IEEE, DOI: 10.1109/ICE CCO48375.2019.9043261 [2019 15th International Conference on Electronics, Computer and Computation (ICECCO)], 2019.
[6] Julien Maitre, Kévin Bouchard, and L. Paul Bédard, “Mineral grains recognition using computer vision and machine learning,” Computers & Geosciences, vol.130, pp. 84–93, 2019.
[7] Hayder Hasan, Helmi Z.M.Shafri, and Mohammed Habshi, “A comparison between support vector machine (SVM) and convolutional neural network (CNN) models for hyperspectral image classification,” Earth and Environmental Science, vol.357, pp. 1-10, 2019.
[8] Xiaobo Liu, Yuwei Zhang, Hongdi Jing, Liancheng Wang and Sheng Zhao, “Ore image segmentation method using U-Net and Res_Unet convolutional networks,” Royal society of chemistry, vol.10, pp. 9396-9406, 2020.
[9] Guangpeng Fan, Feixiang Chen, Danyu Chen, Yan Li, and Yanqi Dong, “A deep learning model for quick and accurate rock,” Hindawi Recognition with Smartphones, vol.2020, pp.1-14, 2020.
[10] Lei Si, Xiangxiang Xiong, Zhongbin Wang, and Chao Tan, “A deep convolutional neural network model for intelligent discrimination between coal and rocks in coal mining face,” Hindawi Mathematical Problems in Engineering, Vol. 2020, pp.1-12, 2020.
[11] Syamil Mohd Razak, and Behnam Jafarpour, “Convolutional neuralnetworks (CNN) forfeature-based modelcalibration underuncertain geologicscenarios,” Computational Geosciences, vol.24, pp.1625–1649, 2020.
[12] L. Madhuanand, P. Sadavarte, A.J.H. Visschedijk, H.A.C. Denier Van Der Gon, I. Aben and F.B. Osei, “Deep convolutional neural networks forsurface coal mines determination fromsentinel-2 images,” European Journal of Remote Sensing, vol. 54, pp. 296-309, 2021.
[13] M. Pryshliak, S. Subbotin, and A. Oliinyk, “Constructing a method for the conversion of numerical data in order to train the deep neural networks,” Journal of Enterprise Technologies, vol.95, pp.1-7, 2018.
[14] Alok Sharma, Edwin Vans, Daichi Shigemizu, Keith A. Boroevich and Tatsuhiko Tsunoda, “DeepInsight: A methodology to transform a non-image data to an image for convolution neural network architecture,” Scientific Reports, vol. 9, pp. 1-7, 2019.
[15] Timea Bezdan, Nebojsa Bacanin, “Convolutional neural network layers and architectures,” Data science and digital broadcasting systems, international scientific conference on information technology and data related research, DOI: 10.15308/Sinteza-2019-445-451, 2019.
[16] S H Shabbeer Basha, Shiv Ram Dubey, Viswanath Pulabaigari, and Snehasis Mukherjee, “Impact of fully connected layers on performance of convolutional neural networks for image Classification,” Indian Institute of Information Technology Sri City, Andhra Pradesh- 517646, India. arXiv:1902.02771v3 [cs.CV] 19 Nov 2019.
[17] Jiayao Chen, Tongjun Yang, Dongming Zhang, Hongwei Huang, and Yu Tian, “Deep learning based classification of rock structure of tunnel face,” Geoscience Frontiers, vol. 12, pp. 395-404, 2021.
[18] Abhijit Roy, “An introduction to gradient descent and backpropagation,” https:// towardsdatascience.com/an-introduction-to-gradient-descent-and-backpropagation-81648bdb19b2.
[20] Umut Ozkaya, Saban Ozturk, and Mucahid Barstugan, “Coronavirus (COVID-19) Classification using Deep Features Fusion and Ranking Technique,” https:// arxiv.org/pdf/2004.03698.
[21] Shengping Yang, and Gilbert Berdine, “The receiver operating characteristic (ROC) curve,” The Southwest Respiratory and Critical Care Chronicles, vol. 5, pp. 34–36, 2017.
[22] Ibrahem Kandel, Mauro Castelli, “The effect of batch size on the generalizability of the convolutional neural networks on a histopathology dataset,” The Korean Institute of Communications and Information Sciences, pp. 1-4, 2020.
[23] Olaf Berke, “Methodology Exploratory disease mapping: kriging the spatial risk function from regional count data,” International Journal of Health Geographics, vol.3, pp.1-11, 2004.
[24] Farhad Misaghi, Shadi Dayyanidardashti, Kourosh Mohammadi, and M.R. Ehsani, “Application of Artificial Neural Network and Geostatistical Methods in Analyzing Strawberry Yield Data,” 2004 ASAE/CSAE Annual International Meeting Sponsored by ASAE/CSAE Fairmont Chateau Laurier, The Westin, Government Centre Ottawa, Ontario, Canada 1 - 4 August 2004.
[25] Marco Bezzi, and Alfonso Vitti, “A comparison of some kriging interpolation methods for the production of solar radiation maps,” Geomatics Workbooks, pp.1-5, 2005.
[26] Ibrahim L. Olokodana, Saraju P. Mohanty,and Elias Kougianos, “Krig-Detect: Exploring Alternative Kriging Methods for Real-Time Seizure Detection from EEG Signals,” DOI: 10.1109/WF-IoT48130.2020.9221260, 2020.
[27] Kemal Sulhi Gundogdu, and Ibrahim Guney, “Spatial analysis of groundwater levels using universal kriging,” Journal of Earth System Science, vol.116, pp. 49–55, 2007.
[28] Feridon Ghadimi, Mohammad Ghomi, and Mojtaba Aref Sedigh, “Identification of Ti-Anomaly in Stream Sediment Geochemistry using Stepwise Factor Analysis and Multifractal Model in Delijan District, Iran,” IJMGE Int. J. Min. & Geo-Eng, Vol. 50, No.1, pp77-95, 2016.
[29] Mandana Tahmooresi, Behnam Babaei, and Saeed Dehghan, “Intelligent geochemical exploration modeling using multiclass support vector machine and integration it with continuous genetic algorithm in Gonabad region, Khorasan Razavi, Iran,” Arabian Journal of Geosciences, 141012 (2021). https://doi.org/10.1007 /s12517-021-07306-w
[30] Mandana Tahmooresi, Data mining and intelligent optimization of support vector machine and convolutional neural network using genetic algorithm in order to modeling for mineral potential exploration (Case study: Gonabad arena), Ph.D. Dissertation, Mahallat Branch, Islamic Azad University, Mahallat, IRAN. 2022 (Note: Final defend) [In Persian].
|
|
آمار
تعداد مشاهده مقاله: 402
تعداد دریافت فایل اصل مقاله: 442