کاربرد روش رگرسیون بردار پشتیبان در تخمین و مدلسازی پارامترهای سیال درگیر در کانسار مس پورفیری سونگون | ||
| پژوهشهای دانش زمین | ||
| دوره 12، شماره 3 - شماره پیاپی 47، 1400، صفحه 22-39 اصل مقاله (1.28 M) | ||
| نوع مقاله: مقاله پژوهشی | ||
| شناسه دیجیتال (DOI): 10.48308/esrj.2021.100905 | ||
| نویسندگان | ||
| ملیحه عباس زاده* 1؛ اردشیر هزارخانی2؛ سعید سلطانی محمدی3 | ||
| 1گروه مهندسی معدن، دانشکده مهندسی، دانشگاه کاشان، کاشان، ایران | ||
| 2دانشکده معدن، دانشگاه صنعتی امیرکبیر، تهران، ایران | ||
| 3دانشکده معدن، دانشگاه صنعتی امیرکبیر، تهران، ایرانن | ||
| چکیده | ||
| مطالعه سیالات درگیر اغلب به صورت آزمایشگاهی و با هدف ارتقا صحت و دقت تجزیههای صورت گرفته انجام میشود. از آنجا که استفاده کاربردی از دادههای حاصل از این مطالعات آزمایشگاهی میتواند در فرآیند اکتشاف کانسارها و یا دستیابی به اطلاعات اکتشافی تکمیلی از کانسارهای کشف شده سودمند باشد، در این مطالعه تخمین و مدلسازی پارامترهای ترمودینامیکی سیال درگیر (دمای همگنی، دمای یوتکتیک و شوری) در کانسار مس پورفیری سونگون انجام و در گام نخست، با استفاده از تخمینگر رگرسیون بردار پشتیبان، مدل سهبعدی این پارامترها تهیه شده است. دقت مدلسازی صورت گرفته جهت تخمین دادههای سیالات درگیر شامل دمای همگنی، دمای یوتکتیک و شوری سیال درگیر به ترتیب برابر 76، 71 و 93 درصد میباشد. سپس براساس شرایط ترمودینامکی مساعد برای نهشت کالکوپیریت (بازه دمایی 300 تا 400 درجه سانتیگراد و شوری متوسط تا بالا)، از این مدل سه بعدی برای تهیه مدل پیشگویانه کانیزایی استفاده شده است. مقایسه مدل پیشگویانه با مدل بلوکی زمینشناسی عیار مس در محدوده کانسار نشان داد که تطابق مطلوبی بین این دو مدل وجود دارد. در نتیجه میتوان 1) از مدل تهیه شده در ادامه فرآیند اکتشاف و با هدف اکتشافات تکمیلی بهرهمند شد و 2) از این روش، برای شناسایی مناطق پرپتانسیل کانسارهایی که هنوز در مراحل اکتشافات مقدماتی هستند استفاده کرد. | ||
| کلیدواژهها | ||
| الگوریتم یادگیری ماشین؛ رگرسیون بردار پشتیبان؛ سیالات درگیر؛ کانسار مس پورفیری سونگون؛ مدل پیش-گویانه | ||
| عنوان مقاله [English] | ||
| Application of support vector regression method in estimating and modeling of fluid inclusion parameters in Sungun porphyry copper deposit | ||
| نویسندگان [English] | ||
| Maliheh Abbaszadeh1؛ Ardeshir Hezarkhani2؛ Saeid Soltani Mohammadi3 | ||
| 1Department of Mining Engineering, University of Kashan, Iran | ||
| 2Department of Mining Engineering, Amirkabir University of Technology, Tehran, Iran | ||
| 3Department of Mining Engineering, Amirkabir University of Technology, Tehran, Iran | ||
| چکیده [English] | ||
| Extended abstract Introduction The background of 3D modeling of fluid inclusion data goes back to use of inverse distance weighting (IDW) method in the Caixiashan Pb and Zn deposit (Sun et al., 2011). This method in spite of having some advantages such as simplicity in basis is associated with disadvantages such as uncertainty in selection of weighting function and ignoring data distribution. Today, new methods have been proposed for estimation including the support vector machine method (Dutta et al., 2010). One of this method’s capabilities is in dealing with small data sets (Dutta, 2006; Zhang et al., 1998). In this study, fluid inclusion thermodynamic parameters have been estimated using support vector regression method. Predictive model of mineralization has been provided acording to 3D models resulted for fluid inclusion data and also assumption of proper thermodynamic conditions for chalcopyrite deposition in the Sungun porphyry copper deposit. Material and Methods In this study, a total of 173 data sets of fluid inclusions were obtained from 59 locations. This dataset using genetic algorithm method divided into training and testing sets (80% and 20%, respectively). Modeling of fluid inclusion thermodynamic parameters has been done by support vector regression method. The SVR is based on the statistical learning theory and the structural risk minimization. Results and discussion After preparing and determination of training and test datasets, radial basis kernel function (RBF) was selected in order to estimate and model the fluid inclusion thermodynamic parameters using the support vector regression method. Better functionality was the main reason of using this kernel. In the next step, parameters were needed to be carefully determined to obtain a model with high generalization ability. In this regard, the grid search method with cross validation was used to determine optimal values for the model parameters. Model was then trained using the training dataset and finally evaluated on the test dataset. Then fluid inclusion thermodynamic parameters for each block of deposit were estimated using support vector regression method. According to mineralogical and fluid inclusion studies in the Sungun porphyry copper deposit, it has been determined that chalcopyrite deposition is related to fluids with moderate to high salinity and temperatures of 300-400 °C. The predictive model was prepared based on these conditions and estimated thermodynamic Parameters in block model. In this model, each arbitrary block has been labeled on a scale of 1 to 4 (based on the favorable conditions for chalcopyrite deposition). These labels are possibility index for copper deposition. According to possibility index, proper zones have been determined in 3D model. In order to performance evaluation of support vector regression method, the predictive model was compared with 3D model of copper grade. The results of this comparison showed that prepared predictive 3D model has high consistent with copper grade block model. Conclusion In this study, 3D modeling of fluid inclusion data was performed to estimate the thermodynamic parameters affecting mineralization (homogenization and eutectic temperatures and salinity) using support vector regression method to determine potential mineralization points in the area. Using the 3D models, we found the homogenization and eutectic temperatures and fluids salinity (in different ranges of these factors) in the Sungun porphyry copper deposit. To evaluate the 3D modeling efficiency in advancing the exploration process of the porphyry deposits, the conformity between mineralization and thermodynamic variations of the fluid inclusions was investigated and, based on it; a tool called “Predictive Model” was presented for the evaluation of the occurrence of mineralization in different parts of the region. A comparison of the SVR-based predictive model and the copper grade block model shows acceptable conformity in low, medium, and high-grade regions. | ||
| کلیدواژهها [English] | ||
| Machine learning algorithm, Support vector regression, Fluid inclusion, Sungun porphyry copper deposit, Predictive model | ||
| مراجع | ||
|
-اصغری، ا.، 1386. تفکیک دگرسانی در کانسار مس پورفیری سونگون براساس شبیهسازی زمین آماری با استفاده از دادههای سیالات درگیر، رساله دکتری، دانشگاه صنعتی امیرکبیر.
-رمضانی، ط.، معانی جو، م.، اسدی، س.، لنتز، د. و پیروزنیا، ن.، 1397. مقایسه سیستمهای مس پورفیری سونگون و کیقال، شمال غرب ایران: با تأکید بر مطالعه سیالات درگیر. زمینشناسی اقتصادی، دوره 10، شماره 2، ص 403-424.
-شفیعی، ز.، عباس زاده، م.، سلطانی محمدی، س. و دهقانی جوزم، م.، 1398. مقایسه عملکرد شبکه عصبی مصنوعی و ماشین بردار پشتیبان در تهیه مدل سه بعدی زونهای کانیسازی (مطالعه موردی: کانسار مس پورفیری میدوک، ایران، نشریه مهندسی معدن، دوره 14، شماره 45، ص 13-24.
-شهرابی، ج. و ذوالقدر شجاعی، ع.، 1390. داده کاوی پیشرفته: مفاهیم و الگوریتمها، انتشارات جهاد دانشگاهی واحد دانشگاه امیرکبیر، 472 ص.
-عباسزاده، م.، 1393. مدلسازی سهبعدی دادههای حاصل از مطالعات سیالات درگیر با استفاده از الگوریتمهای یادگیری ماشین، رساله دکتری، دانشگاه صنعتی امیرکبیر.
-عباس زاده، م.، هزارخانی، ا. و سلطانی محمدی، س.، 1398. مرزبندی زونهای دگرسانی پتاسیک و فیلیک براساس نتایج حاصل از مدلسازی سهبعدی دادههای سیالات درگیر به روش شبکههای عصبی مصنوعی، فصلنامه علمی پژوهشی علوم زمین، دوره 29، شماره 113، ص 115-122.
-عباس زاده، م.، 1398. تخمین عیار کانسار فسفات اسفوردی با روش رگرسیون بردار پشتیبان، نشریه مهندسی منابع معدنی، دوره 4، شماره 4، ص 1-16.
-Abbaszadeh, M., Hezarkhani, A. and Soltani-Mohammadi, S., 2013. An SVM Based Machine Learning Method for the Separation of Alteration Zones in Sungun Porphyry Copper Deposit: Chem Erde-Geochem, v. 73, p. 545-554.
-Abbaszadeh, M., Hezarkhani, A. and Soltani-Mohammadi, S., 2015. Classification of Alteration Zones Based on Whole- Rock Geochemical Data Using Support Vector Machine: Journal of the Geological Society of India., v. 85, p. 500-508.
-Abbaszadeh, M., Hezarkhani, A. and Soltani Mohammadi, S., 2016. Proposing Drilling Locations Based on the 3D Modeling Results of fluid Inclusion Data Using the Support Vector Regression Method: Journal of Geochemical Exploration, v. 165, p. 23-34.
-Aghazadeh, M., Hou, Z., Badrzadeh, Z. and Zhou, L., 2015. Temporal–Spatial Distribution and Tectonic Setting of Porphyry Copper Deposits in Iran: Constraints from Zircon U–Pb and Molybdenite Re-Os Geochronology: Ore Geology Reviews, v. 70, p. 385-406.
-Allahkarami, E., Nuri, O., Abdollahzadeh, A.A., Rezai, B. and Chegini, M., 2016. Estimation of Copper and Molybdenum Grades and Recoveries in the Industrial Flotation Plant Using the Artificial Neural Network: International Journal of Nonferrous Metallurgy, v. 5, p. 23-32.
-Asgharı, O. and Hezarkhanı, A., 2010. Investigations of alteration zones based on fluid inclusion microthermometry at Sungun porphyry copper deposit, Iran: Bulletin of the Mineral Research and Exploration , v. 140, p. 19-34.
-Baldwin, J.T., Swain, H.D. and Clark, G.H., 1978. Geology and Grade Distribution of the Panguna Porphyry Copper Deposit, Bougainville, Papua New Guinea: Economic Geology, v. 73, p. 690-702.
-Barnes, H.L., 1997. Geochemistry of Hydrothermal Ore Deposits, 3rd Edition: John Wiley Publications, New York.
-Calagari, A.A. and Hosseinzadeh, G., 2006. The Mineralogy of Copper-Bearing Skarn to the East of the Sungun-Chay River, East-Azarbaidjan, Iran: Journal of Asian Earth Sciences,v. 28, p. 423-438.
-Calagari, A.A., 1997. Geochemical, Stable Isotope, Noble Gas, and Fluid Inclusion Studies of Mineralization and Alteration at Sungun Porphyry Copper Deposit, East-Azarbaidjan, Iran: Implication for Genesis: Ph.D. Thesis, Manchester University.
-Calagari, A.A., 2004. Fluid Inclusion Studies in Quartz Veinlets in the Porphyry Copper Deposit at Sungun, East-Azarbaidjan, Iran: Journal of Asian Earth Sciences, v. 23, p. 179-189.
-Chatterjee, S., Bandopadhyay, S. and Machuca, D., 2010. Ore Grade Prediction Using a Genetic Algorithm and Clustering Based Ensemble Neural Network Model: Mathematical Geosciences, v. 42, p. 309-326.
-Dutta, S., 2006. Predictive Performance of Machine Learning Algorithms for Ore Reserve Estimation in Sparse and Imprecise Data: Ph.D. Thesis, University of Alaska Fairbanks.
-Dutta, S., Bandopadhyay, S., Ganguli, R. and Misra, D., 2010. Machine Learning Algorithms and Their Application to Ore Reserve Estimation of Sparse and Imprecise Data: Journal of Intelligent Learning Systems & Applications, v. 2, p.86-96.
-Etminan, H., 1977. The Discovery of Porphyry Copper-Molybdenum Mineralization Adjacent to Songun Village in the Northwest of Ahar (Eastern Azerbaijan, Iran) and a Proposed Program for its Detailed Exploration. Geological Survey of Iran: Confidential Report, Ministry of Industries and Mines.
-Frohlich, H. and Zell, A., 2005. Efficient Parameterselection for Support Vector Machines in Classification and Regression via Model-Based Global Optimization: Proceedings. 2005 IEEEInternational Joint Conference on Neural Networks, Montreal, Que., v. 3, p. 1431-1436.
-Hassanpour, S., 2017. The Sungun porphyry magma resource and the 120,000-year difference in age between the main stock and the first dike: New evidence from 87Sr/86Sr, 143Nd/144Nd and Pb, SHRIMP U–Pb zircon dating in NW Iran: Iranian Journal of Earth Sciences, v. 9(2), p. 94-104.
-Henrique, B.M., Sobreiro, V.A. and Kimura, H., 2018. Stock Price Prediction Using Support Vector Regression on Daily and up to the Minute Prices: The Journal of Finance and Data Science, v.4, p.183-201.
-Hezarkhani, A., 1997. Physicochemical Controls on Alteration and Copper Mineralization in the Sungun Porphyry Copper System, Iran: Ph.D. Thesis, University of Mcgill.
-Hezarkhani, A. and Williams-Jones, A.E., 1998. Controls of Alteration and Mineralization in the Sungun Porphyry Copper Deposit, Iran: Evidence from Fluid Inclusions and Stable Isotopes: Economic Geology, v. 93, p. 651-670
-Hosseinzadeh, M., Alavi, S. and Moayyed, M., 2014. Petrography and petrology of the Sungun porphyry copper deposit and post mineralization dykes with a view to Skarn mineralization (north of Varzeghan, East Azarbaijan): Iranian Journal of Petrology, v. 5(17), p. 17-32.
-Hsu, C.W., Chang, C.C. and Lin, C.J., 2010. A Practical Guide to Support Vector Classification: Technical Report, Department of Computer Science and Information Engineering, University of National Taiwan, Taipei, p. 1-12.
-Jafrasteh, B., Fathianpour, N. and Suárez, A., 2018. Comparison of machine learning methods for copper ore grade estimation: Computers & Geosciences ,v. 22, p. 1371-1388.
-Kaplan, U.E. and Topal, E., 2020. A New Ore Grade Estimation Using Combine Machine Learning Algorithms: Minerals, v. 10(10), 847 p.
-Kecman, V., 2000. Learning and Soft Computing: Support Vector Machines, Neural Network and Fuzzy Logic Models: Mit Publishers, 576 p.
-Kecman, V., 2004. Support Vector Machines Basics, the University of Auckland, School of Engineering, 616 p.
-Lescuyer, J.L., Riou, R., Babakhani, A., Alavi Tehrani, N., Nogol, M.A., Dido, J. and Gemain, Y.M., 1978. Geological Map of the Ahar Area: Geological Survey of Iran.
-Manthira Moorthi, S., Misra, I., Kaur, R., Darji, N.P. and Ramakrishnan, R., 2011. Kernel-Based Learning Approach for Satellite Image Classification Using Support Vector Machine: IEEE Recent Advances in Intelligent Computational Systems, p. 107-110.
-Matias, J.M., Vaamonde, A., Taboada, J. and Gonzalez-Manteiga, W., 2004. Support Vector Machines and Gradient Boosting for Graphical Estimation of a Slate Deposit: Stochenvir Res and Risk Ass, v. 18, p. 309-323.
-Mehrpartou, M., 1993. Contributions to the Geology, Geochemistry, Ore Genesis and Fluid Inclusion Investigations on Sungun Cu-Mo Porphyry Deposit, (North-West of Iran): Ph.D. Thesis, Hamburg University, Hamburg, Germany.
-Nezamolhosseini, S.A., Mojtahedzadeh, S.H. and Gholamnejad, J., 2017. The Application of Artificial Neural Networks to Ore Reserve Estimation at Choghart Iron Ore Deposit: Analytical and Numerical Methods in Mining Engineering, v. 6, p. 73-83.
-Pars Olang Engineering Consultant Company, 2006. Pars Olang Modeling and Reserve Estimation Report of Sungun Copper Mine, Tehran.
-Pozdnoukhov, A., 2005. Support Vector Regression for Automated Robust Spatial Mapping of Neural Radioactivity: Journal of Applied Gis, v. 1)2), p. 75-93.
-Simmonds, V., Moazzen, M. and Mathur, R., 2017. Constraining the timing of porphyry mineralization in northwest Iran in relation to Lesser Caucasus and Central Iran; Re–Os age data for Sungun porphyry Cu–Mo deposit: International Geology Review, v. 59, p. 25-37.
-Smola, A.J. and Scholkopf, B., 1998. A Tutorial on Support Vector Regression: NeuroCOLT Technical Report NC-TR-98-030, Royal Holloway College, University of London, UK.
-Smola, A.J. and Scholkopf, B., 2004. A Tutorial on Support Vector Regression: Statistics and Computing, v. 14, p. 199-222.
-Soliman, O.S. and Mahmoud, A.S., 2012. A Classification System for Remote Sensing Satellite Images Using Support Vector Machine with Non-Linear Kernel Functions: 8th International Conference on Informatics and Systems (INFOS), p. 181-187.
-Soliman, O.S., Mahmoud, A.S. and Hassan, S.M., 2012. Remote Sensing Satellite Images Classification Using Support Vector Machine and Particle Swarm Optimization: Third International Conference on Innovations in Bio-Inspired Computing and Applications, p. 280-285.
-Soltani, S., Bakhshandeh Amnieh, H. and Bahadori, M., 2012. Investigating Ground Vibration to Calculate the Permissible Charge Weight for Blasting Operations of Gotvand-Olya Dam Underground Structures: Archives of Mining Science, v. 56, p. 701-710.
-Son, Y.J., Kim, H.G., Kim, E.H., Choi, S. and Lee, S.K., 2010. Application of Support Vector Machine for Prediction of MedicationAdherence in Heart Failure Patients: Healthcare Informatics Research, v. 16, p. 253-259.
-Sugumaran, V. and Ramachandran, K.I., 2011. Effect of Number of Features on Classification of Roller Bearing Faults Using SVMand PSVM: Expert Systems with Applications, v. 38, p. 4088-4096.
-Sun, L., Xiao, K., Gao, Y., Wang, R. and Xing, S., 2011. 3D Modeling of Fluids Inclusion Data of Caixiashan Pb-Zn Deposit, East Tianshan Area, China: IAMG, Austria.
Twarakavi, N. C. Misra, D. and Bandopadhayay, S., 2006. Prediction of Arsenic in Bedrock Derived Stream Sediments at a Gold Mine Site under Conditions of Sparse Data: Natural Resources Research, v. 15, p.15-26.
-Yu, P.S., Chen, S.T. and Chang, I.F., 2006. Support Vector Regression for Real-Time Flood Stage Forecasting: Journal of Hydrology, v. 328, p. 704-716.
-Zendehboudi, A., Baseer, M.A. and Saidur, R., 2018. Application of Support Vector Machine Models for Forecasting Solar and Wind Energy Resources: A Review: Journal of Cleaner Production, v. 199, p. 272-285.
-Zhang, G.P., Patuwo, B.E. and Hu, M.Y., 1998. Forecasting with Artificial Neural Networks: the State of the art: International Journal of Forecasting, v. 1)14(, p. 35-62.
-Zhen-Yuan, J., Jian-Wei, M., Fu-Ji, W. and Wei, L., 2011. Hybrid of Simulated Annealing and SVMfor Hydraulic Valve Characteristics Prediction: Expert Systems with Applications,v. 38, p. 8030-8036.
-Zuo, R. and M.Carranza, E.J., 2011. Support Vector Machine: A Tool for Mapping Mineral Prospectivity: Computers & Geosciences, v. 37, p. 1967-1975. | ||
|
آمار تعداد مشاهده مقاله: 9,923 تعداد دریافت فایل اصل مقاله: 5,943 |
||
