Scientific- Research Quarterly of Geographical Data (SEPEHR)

Scientific- Research Quarterly of Geographical Data (SEPEHR)

Comparison of efficiency of random forest and support vector machine methods for mineral potential mapping of copper deposits, - Case study: Dahaj-Bazman

Document Type : Research Paper

Authors
Mohammad Karimi 1
Parastoo Pilehforooshha 2
Ali Safari 3
1 Associate Professor, Faculty of Geodesy and Geomatic, K.N.Toosi University of Technology
2 Assistant Professor, Faculty of Geodesy and Geomatic, K.N.Toosi University of Technology
3 Master of Science in GIS, Faculty of Geodesy and Geomatic, K.N.Toosi University of Technology
10.22131/sepehr.2024.2012344.3023
Abstract
Extended Abstract
 Introduction:
The exploration and preparation of the potential map of mineral reserves requires the use of various methods and techniques, based on the geological and mining knowledge of the investigated area, and the use of predictive models of mineral potential (Bonham-Carter, 1994; Carranza et al., 2008a). According to the investigations, the common models of map integration that are used in the discovery of mineral reserves in the initial exploration stage include index overlap model, fuzzy operators, weighted indicators and smart methods such as random forests and artificial networks. Determining the values of weights and scores that show the relative importance of the effective factors is the primary requirement in combining the maps and preparing the mineral potential map (Agterberg, 1992; Brown et al., 2000).
The purpose of this research is to prepare a potential map of copper deposits in Dehj-Bazman region using two methods of random forest and support vector machine. In addition, in order to compare the potential map of porphyry copper reserves resulting from the random forest method, the support vector machine method and the knowledge-based methods of index overlap and fuzzy logic were used.
Materials & Methods:
The area studied in this research is a part of the magmatic belt of Kerman region, known as the Dehj-Sardouye belt. The information layers controlling mineralization in Dehj-Bazman area include rock units, structures, alterations, geochemistry, geophysics and copper deposits. In practical applications of machine learning algorithms, mineral potential mapping is essentially a bimodal classification problem, such that each undiscovered area is classified as prospective or non-prospective according to some combination of mapping criteria (Zuo, 2011). The final results are a set of predictive maps that show target areas with high ore formation potential.
In order to model, training was done. Before training the random forest model, the input data set and the target variable should be prepared and then the model should be trained. The target variables for entering the random forest model and support vector machine were determined as deposit points (values of 1) and non-deposit points (values of 0). Then the genetic algorithm was used to adjust the parameters.
Evaluation of the predictive performance of random forest model and support vector machine can be described by the ambiguity matrix. In this matrix, there are four components, which are defined as: (1) a deposit sample that is correctly classified as a deposit (TP); (2) a deposit sample incorrectly classified as a non-deposit sample (FN), (3) a non-deposit sample correctly classified as a non-deposit sample (TN), and (4) a non-deposit sample that is wrongly classified as a deposit sample (FP) (Liu et al., 2005; Tien Bui et al., 2016):
 




(8)

 



(9)

 



(10)

 



(11)

 



(12)

 



After training and evaluating different models, the best model was obtained by adjusting different parameters and it was used to integrate factor maps in order to predict areas with high potential of porphyry copper deposits. Also, knowledge-based methods of fuzzy logic and index overlap were used to combine factor maps to compare with the results of intelligent methods.
Results & Discussion:
At this stage, the desired information layers were collected and prepared in the GIS environment, and then factor maps were prepared. Accuracy, sensitivity, specificity, predicted positive value, predicted negative value, kappa index and OOB error were used to evaluate the performance of random forest model and support vector machine. Also, the importance of the predictor variables in the random forest model was evaluated through the mean decrease in accuracy and the mean decrease in node impurity or the Gini impurity index (Breiman, 2001). According to the results, the most important predictor in the random forest model is the geochemical map, while the structures factor has the least impact in predicting the preparation of the mineral potential map with the final random forest model.
In the potential maps of porphyry copper deposits obtained from two methods of random forest and support vector machine, the target areas cover 14% of the studied area, in which there are 92% and 87% of known deposits, respectively. Finally, the efficiency of machine learning methods and knowledge-based methods were compared. In order to produce porphyry copper potential map with knowledge-based methods, the judgment of expert experts was used to assign weights to each criterion map. For this purpose, weights of 0.3, 0.25, 0.25, 0.1, 0.1 were assigned to produce maps of alteration factor, geochemistry, geology, geophysics and structures respectively. In the potential map obtained from the method of index overlap and fuzzy logic (fuzzy sum), the areas predicted as copper mines cover 16 and 17 percent of the studied area, respectively, in which 83 and 79 percent of the existing mines are located.
Conclusion:
This research was conducted with the aim of evaluating and comparing the effectiveness of random forest method and support vector machine method and knowledge-based methods to prepare porphyry copper potential map of Dehaj-Bozman region of Kerman province. Based on the results, the random forest model works well in the field of porphyry copper potential map preparation with geochemical, geophysical, geological, alteration and structures datasets. In addition, the random forest algorithm can estimate the importance of factor maps.
The results of this research show that the geochemical factor map is the most important and the structure factor map is the least important in predicting the data-driven model of random forests. This estimate of importance is consistent with geological knowledge about porphyry copper mineralization in Dehj-Buzman region. In order to produce porphyry copper potential map with knowledge-based methods, the judgment of expert experts was used to assign weights to each criterion map. According to the obtained results, the performance of the random forest model is better than the vector machine model, and also, the performance of the support vector machine model is better than the knowledge-based methods.
Keywords
Geospatial Information System
Porphyry copper potential map
Random Forest
Support Vector Machine
Subjects
1- درویش‌زاده، علی، 1370، کتاب زمین‌شناسی ایران، انتشارات امیرکبیر،1370
2- علائی‌مقدم، کریمی، مسگری، صاحب‌الزمانی؛ ساناز، محمد، محمدسعدی، نادر؛ مدل‌سازی فرایند تهیه نقشه پتانسیل معدنی با استفاده از سیستم استنتاج‌گر فازی (منطقه مورد مطالعه : کانسار مس چاه فیروزه)، نشریه علوم زمین (سازمان زمین‌شناسی و اکتشاف معدنی کشور)، پاییز 1393, دوره 24، شماره 93- صفحه 53-66.
3- کریمی، ولدان‌زوج، عبادی، صاحب‌الزمانی؛ محمد، محمد جواد، حمید، نادر؛ تهیه نقشه پتانسیل دخایر مس با استفاده از سامانه اطلاعات جغرافیایی(GIS)، فصلنامه علوم زمین، شماره 68، 1387.
4- مؤمنی؛ سمانه؛ شناسایی مناطق امیدبخش از نظر وجود منابع فلزی با استفاده از تلفیق و تحلیل داده‌های ماهواره‌ای و فتوگرامتری، پایان‌نامه کارشناسی ارشد،1392
منابع و مآخذ
1- درویش‌زاده، علی، 1370، کتاب زمین‌شناسی ایران، انتشارات امیرکبیر،1370
2- علائی‌مقدم، کریمی، مسگری، صاحب‌الزمانی؛ ساناز، محمد، محمدسعدی، نادر؛ مدل‌سازی فرایند تهیه نقشه پتانسیل معدنی با استفاده از سیستم استنتاج‌گر فازی (منطقه مورد مطالعه : کانسار مس چاه فیروزه)، نشریه علوم زمین (سازمان زمین‌شناسی و اکتشاف معدنی کشور)، پاییز 1393, دوره 24، شماره 93- صفحه 53-66.
3- کریمی، ولدان‌زوج، عبادی، صاحب‌الزمانی؛ محمد، محمد جواد، حمید، نادر؛ تهیه نقشه پتانسیل دخایر مس با استفاده از سامانه اطلاعات جغرافیایی(GIS)، فصلنامه علوم زمین، شماره 68، 1387.
4- مؤمنی؛ سمانه؛ شناسایی مناطق امیدبخش از نظر وجود منابع فلزی با استفاده از تلفیق و تحلیل داده‌های ماهواره‌ای و فتوگرامتری، پایان‌نامه کارشناسی ارشد،1392
5- Abedi, M., Norouzi, G.H., Bahroudi, A., 2012. Support vector machine for multi-classification of mineral prospectivity areas, Comput. Geosci., vol. 46, pp. 272–283, doi: 10.1016/j.cageo.2011.12.014.
6- Agterberg, F. P., 1992. Combining indicator patterns in weights of evidence modeling for resource evaluation. Nonrenewable Resources, 1, 39–50.
7- Alaei Moghadam, S., Karimi, M., Sadi Mesgari, M. Application of a fuzzy inference system to mapping prospectivity for the Chahfiroozeh copper deposit, Kerman, Iran, Journal of Spatial Science, 2015. 60(2), pp.233-255 DOI:10.1080/14498596.2015.1004653.
8- Asadi, H.H., Hale, M., 2001. A predictive GIS model for mapping potential gold and base metal mineralization in Takab area, Iran. Comput. Geosci. 27, 901-912.
9- Bonham-Carter, G. F, 1994, Geographic Information Systems for Geoscientist: Modeling With GIS, Pergamon Press, Ontario, Canada.
10- Bonham-Carter, G. F., Agterberg, F. P., & Wright, D. F., 1988. Integration of geological datasets for gold exploration in Nova Scotia. Photogrammetric Engineering and Remote Sensing, 54, 1585–1592.
11- Bonham-Carter, G. F., Agterberg, F. P., & Wright, D. F., 1989. Weights of evidence modelling: A new approach to mapping mineral potential. In F. P. Agterberg & G.F. Bonham-Carter (Eds.), Statistical applications in the earth sciences. Geological Survey of Canada, Paper 89-9 (pp. 171–183).
12- Bonham-Carter, Graeme F., “ Geographical Information Systems for geoscientists: modeling whit GIS”, Pergamon Press, Ontario, Canada, Chapter9, 1994.
13- Breiman, L., 2001. Random forests. Machine learning, 45, 5-32.
14- Breiman, L., 2017. Classification and regression trees. Routledge.
15- Brown, W. M., Gedeon, T. D., Groves, D. I., & Barnes, R. G., 2000. Artificial neural networks: A new method for mineral prospectivity mapping. Australian Journal of Earth Sciences, 47, 757–770.
16- Burges, C.J.C., 1998. A tutorial on support vector machines for pattern recognition, Data Min. Knowl. Discov., pp. 121–167.
17- Carranza, E. J. M., van Ruitenbeek, F. J. A., Hecker, C., van der Meijde, M., van der Meer,F. D., 2008a. Knowledge-guided data-driven evidential belief modeling of mineral prospectivity in Cabo de Gata, SE Spain. Int. J. Appl. Earth Obs. 10, 374–387.
18- Carranza, E. J. M., & Hale, M., 2000. Geologically constrained probabilistic mapping of gold potential, Baguio District, Philippines. Natural Resources Research, 9, 237–253.
19- Carranza, E. J. M., Woldai, T., & Chikambwe, E. M., 2005. Application of data-driven evidential belief functions to prospectivity mapping for aquamarine-bearing pegmatites, Lundazi District, Zambia. Natural Resources Research, 14, 47–63.
20- Carranza, E. J. M., & Hale, M. (2003). Evidential belief functions for data-driven geologically constrained mapping of gold potential, Baguio district, Philippines. Ore Geology Reviews, 22, 117–132.
21- Carranza, E. J. M., Laborte, A. G., 2015. “Data-driven predictive mapping of gold prospectivity, Baguio district, Philippines: Application of Random Forests algorithm,” Ore Geol. Rev., vol. 71, pp. 777–787.
22- Carranza, E. J. M., Laborte, A. G., 2015. “Random forest predictive modeling of mineral prospectivity with small number of prospects and data with missing values in Abra (Philippines),” Comput. Geosci., vol. 74, pp. 60–70, doi: 10.1016/j.cageo.2014.10.004.
23- Carranza, E. J. M., Laborte, A. G.  2016. “Data-Driven Predictive Modeling of Mineral Prospectivity Using Random Forests: A Case Study in Catanduanes Island (Philippines),” Nat. Resour. Res., vol. 25, no. 1, pp. 35–50, doi: 10.1007/s11053-015-9268-x.
24- Chen, J., Wang, G., & Hou, C, 2005. Quantitative prediction and evaluation of mineral resources based on GIS: A case study in Sanjiang region, southwestern China. Natural Resources Research, 15, 285–294.
25- Chen, Y., Wu, W., 2017. Mapping mineral prospectivity by using one-class support vector machine to identify multivariate geological anomalies from digital geological survey data, Australian Journal of Earth Sciences, 64:5, 639-65.
26- Geranian, H., Tabatabaei, S. H., Asadi, H. H., Carranza, E. J. M., 2016. Application of discriminant analysis and support vector machine in mapping gold potential areas for further drilling in the Sari-Gunay gold deposit, NW Iran. Natural Resources Research, 25, 145–159.
27- Ghezelbash, R., Maghsoudi, A., Shamekhi, M., Pradhan, B. and Daviran, M., 2023. Genetic algorithm to optimize the SVM and K-means algorithms for mapping of mineral prospectivity. Neural Computing and Applications, 35(1), pp.719-733.
28- Hengl, T., 2006. Finding the right pixel size,” Comput. Geosci., vol. 32, no. 9, pp. 1283–1298.
29- Huang, C., Davis, L.S., Townshend, J.R.G., 2002, An assessment of support vector machines for land cover classification, Int. J. Remote Sens., 725–749.
30- Lachaud, A., Adam, M. and Mišković, I., 2023. Comparative Study of Random Forest and Support Vector Machine Algorithms in Mineral Prospectivity Mapping with Limited Training Data. Minerals, 13(8), p.1073.
31- Lary, D. J., Alavi, A. H., Gandomi, A. H., and Walker, A. L. Machine learning in geosciences and remote sensing, Geosci. Front., vol. 7, no. 1, pp. 3–10, Jan. 2016, doi: 10.1016/j.gsf.2015.07.003.
32- Li, Y., Li, J.W., Li, X.H., Selby, D., Huang, G.H., Chen, L.J. and Zheng, K., 2017. An Early Cretaceous carbonate replacement origin for the Xinqiao stratabound massive sulfide deposit, Middle-Lower Yangtze metallogenic belt, China. Ore Geology Reviews, 80, 985-1003.
33- Li, S., Chen, J. and Liu, C., 2022. Overview on the Development of Intelligent Methods for Mineral Resource Prediction under the Background of Geological Big Data. Minerals, 12(5), p.616.
34- McKay, G., Harris, J. R., 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, Nat. Resour. Res., vol. 25, no. 2, pp. 125–143, 2016, doi: 10.1007/s11053-015-9274-z.
35- Micheletti, N., Foresti, L., Robert, S., Leuenberger, M., Pedrazzini, A., Jaboyedoff, M. and Kanevski, M., 2014. Machine learning feature selection methods for landslide susceptibility mapping. Mathematical geosciences, 46, 33-57.
36- Mohammadi, M., Hezarkhani, M., 2018. Application of support vector machine for the separation of mineralised zones in the Takht-e-Gonbad porphyry deposit, SE Iran. J. Afr. Earth. Sci. 143, 301-308.
37- Porwal, A., Carranza, E. J. M., & Hale, M. 2003a. Artificial neural networks for mineral-potential mapping: A case study from Aravalli Province, Western India. Natural Resources Research, 12, 155–171.
38- Rigol-Sanchez, J. P., Chica-Olmo, M., & Abarca-Hernandez, F., 2003. Artificial neural networks as a tool for mineral potential mapping with GIS. International Journal of Remote Sensing, 24, 1151–1156.
39- Rodriguez-Galiano, V.F., Chica-Olmo, M., and M. Chica-Rivas, “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., vol. 28, no. 7, pp. 1336–1354, 2014.
40- Rodriguez-Galiano, V., , Sanchez-Castillo, M., Chica-Olmo, M., and Chica-Rivas, M. “Machine learning predictive models for mineral prospectivity: An evaluation of neural networks, random forest, regression trees and support vector machines,” Ore Geol. Rev., vol. 71, pp. 804–818, 2015.
41- Saljoughi, B.S., Hezarkhani, A. A., 2018, comparative analysis of artificial neural network (ANN), wavelet neural network (WNN), and support vector machine (SVM) data-driven models to mineral potential mapping for copper mineralizations in the Shahr-e-Babak region, Kerman, Iran. Appl Geomat 10, 229–256. https://doi.org/10.1007/s12518-018-0229-z
42- 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., vol. 109, pp. 26–49, doi: 10.1016/j.oregeorev.2019.04.003.
43- Tien Bui, D., Ho, T.C., Pradhan, B., Pham, B.T., Nhu, V.H. and Revhaug, I., 2016. GIS-based modeling of rainfall-induced landslides using data mining-based functional trees classifier with AdaBoost, Bagging, and MultiBoost ensemble frameworks. Environmental Earth Sciences, 75, pp.1-22.
44- Tien Bui, D., Tuan, T.A., Klempe, H., Pradhan, B. and Revhaug, I., 2016. Spatial prediction models for shallow landslide hazards: a comparative assessment of the efficacy of support vector machines, artificial neural networks, kernel logistic regression, and logistic model tree. Landslides, 13, 361-378.
45- Zhang, N., Zhou, K., Li, D., 2018. Back-propagation neural network and support vector machines for gold mineral prospectivity mapping in the Hatu region, Xinjiang, China, Earth Sci. Informatics, vol. 11, no. 4, pp. 553–566.
46- Zheng, C., Yuan, F., Luo, X., Li, X., Liu, P., Wen, M., Chen, Z. and Albanese, S., 2023. Mineral prospectivity mapping based on Support vector machine and Random Forest algorithm-A case study from Ashele copper-zinc deposit, Xinjiang, NW China. Ore Geology Reviews, p.105567.
47- Zuo, R. Machine Learning of Mineralization-Related Geochemical Anomalies: A Review of Potential Methods, Natural Resources Research, vol. 26, no. 4. Springer New York LLC, pp. 457–464, Oct. 01, 2017, doi: 10.1007/s11053-017-9345-4.
48- Zuo, R., Carranza, E.J.M., 2011. Support vector machine: A tool for mapping mineral prospectivity. Comput. Geosci. 37, 1967-1975.