Cu-bearing signatures from multi-element geochemical data, a correct strategy to implement a Convolutional Autoencoder Algorithm

Document Type : Research Paper

Authors

1 Department of Mining Engineering, Amirkabir University of Technology, Tehran, Iran.

2 School of Mining Engineering, College of Engineering, University of Tehran, Tehran, Iran.

3 Department of Mining and Metallurgy, Amirkabir University of Technology, Tehran, Iran.

10.22059/ijmge.2024.381037.595190

Abstract

Recent advancements in autoencoders and their variants have notably enhanced the detection of multi-element geochemical signatures linked to ore occurences. This research employed a convolutional autoencoder algorithm (CAE) to identify geochemical anomalies, leveraging the algorithm’s ability into account the spatial correlation within the geochemical dataset. In this framework, two stream sediment datasets were generated in the Feizabad district using a conceptual modelling approach alongside a big data analysis strategy. These datasets were individually fed into the CAE model to identify multi-element geochemical anomalies based on the reconstruction error in an unsupervised manner. A comparative analysis of two geochemical prospectivity models and the simplified geological map of Feizabad demonstrates a strong spatial correlation between the identified anomaly regions and known mineral occurrences, which are distributed across andesite, tuff, and Eocene-Oligocene intrusive rocks. However, a quantitative assessment using prediction-area plots indicates that the multi-element geochemical map derived from the conceptual model exhibits a higher prediction rate (72%) compared to the geochemical prospectivity map generated through the big data approach (63%).

Keywords

Main Subjects


[1]  Ayari, J., M. Barbieri, A. Barhoumi, W. Belkhiria, A. Braham, F. Dhaha, and A. Charef. (2022). A regional-scale geochemical survey of stream sediment samples in Nappe zone, northern Tunisia: Implications for mineral exploration. Journal of Geochemical Exploration, 235,106956.
[2]  Saremi, M., S. Yousefi, and M. Yousefi. (2024). Combination of geochemical and structural data to determine the exploration target of copper hydrothermal deposits in the Feizabad district. Journal of Mining and Environment, 15(3), 1089-1101.
[3] Carranza, E.J.M. and M. Hale. (1997). A catchment basin approach to the analysis of reconnaissance geochemical-geological data from Albay Province, Philippines. Journal of Geochemical Exploration, 60(2),157-171.
[4] Yousefi, M., E.J.M. Carranza, and A. Kamkar-Rouhani. (2013). Weighted drainage catchment basin mapping of geochemical anomalies using stream sediment data for mineral potential modeling. Journal of Geochemical Exploration, 128,88-96.
[5] Ranasinghe, P., G. Fernando, C. Dissanayake, and M. Rupasinghe. (2008). Stream sediment geochemistry of the Upper Mahaweli River Basin of Sri Lanka—Geological and environmental significance. Journal of Geochemical Exploration, 99(1-3),1-28.
[6]  Yousefi, M., A. Kamkar-Rouhani, and E.J.M. Carranza. (2014). Application of staged factor analysis and logistic function to create a fuzzy stream sediment geochemical evidence layer for mineral prospectivity mapping. Geochemistry: Exploration, Environment, Analysis, 14(1),45-58.
[7] Yousefi, M., A. Kamkar-Rouhani, and E.J.M. Carranza. (2012). Geochemical mineralization probability index (GMPI): a new approach to generate enhanced stream sediment geochemical evidential map for increasing probability of success in mineral potential mapping. Journal of Geochemical Exploration, 115,24-35.
[8] Daviran, M., R. Ghezelbash, and A. Maghsoudi. (2023). GWOKM: A novel hybrid optimization algorithm for geochemical anomaly detection based on Grey wolf optimizer and K-means clustering. Geochemistry,126036.
[9] Chen, Z., Y. Xiong, B. Yin, S. Sun, and R. Zuo. (2023). Recognizing geochemical patterns related to mineralization using a self-organizing map. Applied Geochemistry, 151,105621.
[10] Zuo, R., J. Wang, Y. Xiong, and Z. Wang. (2021). The processing methods of geochemical exploration data: Past, present, and future. Applied Geochemistry, 132,105072.
[11] Wang, J., Y. Zhou, and F. Xiao. (2020). Identification of multi-element geochemical anomalies using unsupervised machine learning algorithms: A case study from Ag–Pb–Zn deposits in north-western Zhejiang, China. Applied Geochemistry, 120,104679.
[12] Chen, Y., L. Lu, and X. Li. (2014). Application of continuous restricted Boltzmann machine to identify multivariate geochemical anomaly. Journal of Geochemical Exploration, 140,56-63.
[13] Zuo, R. and J. Wang. (2016). Fractal/multifractal modeling of geochemical data: A review. Journal of Geochemical Exploration, 164,33-41.
[14] Grunsky, E. and P.d. Caritat. (2020). State-of-the-art analysis of geochemical data for mineral exploration. Geochemistry: Exploration, Environment, Analysis, 20(2),217-232.
[15] Hawkes, H. and J. Webb. (1963). Geochemistry in mineral exploration. Soil Science, 95(4),283.
[16] Reimann, C., H. Kürzl, and F. Wurzer, Applications of exploratory data analysis to regional geochemical mapping, in Geochemistry and Health (1988). 2017, CRC Press. p. 21-28.
[17] Zuo, R. (2011). Identifying geochemical anomalies associated with Cu and Pb–Zn skarn mineralization using principal component analysis and spectrum–area fractal modeling in the Gangdese Belt, Tibet (China). Journal of Geochemical Exploration, 111(1-2),13-22.
[18] Saremi, M., M. Yousefi, and S. Yousefi. (2023). Separation of geochemical anomalies related to hydrothermal copper mineralization using staged factor analysis in Feyzabad geological map. Journal of Analytical and Numerical Methods in Mining Engineering.
[19] Hoseinzade, Z. and A.R. Mokhtari. (2017). A comparison study on detection of key geochemical variables and factors through three different types of factor analysis. Journal of African Earth Sciences, 134,557-563.
[20] Liu, Q., G. Wu, Z. Liu, X. Mao, J. Yang, and M. Deng. (2024). Local phase-constrained convolutional autoencoder network for identifying multivariate geochemical anomalies. Computers & Geosciences,105679.
[21] Esmaeiloghli, S., S.H. Tabatabaei, E.J.M. Carranza, S. Hosseini, and Y. Deville. (2021). Spatially-weighted factor analysis for extraction of source-oriented mineralization feature in 3D coordinates of surface geochemical signal. Natural Resources Research, 30(6),3925-3953.
[22] Cheng, Q., F. Agterberg, and S. Ballantyne. (1994). The separation of geochemical anomalies from background by fractal methods. Journal of Geochemical exploration, 51(2),109-130.
[23] Afzal, P., M. Mirzaei, M. Yousefi, A. Adib, M. Khalajmasoumi, A.Z. Zarifi, P. Foster, and A.B. Yasrebi. (2016). Delineation of geochemical anomalies based on stream sediment data utilizing fractal modeling and staged factor analysis. Journal of African Earth Sciences, 119,139-149.
[24] Meigoony, M.S., P. Afzal, M. Gholinejad, A.B. Yasrebi, and B. Sadeghi. (2014). Delineation of geochemical anomalies using factor analysis and multifractal modeling based on stream sediments data in Sarajeh 1: 100,000 sheet, Central Iran. Arabian Journal of Geosciences, 7,5333-5343.
[25] Ahmadi, F., H. Aghajani, and M. Abedi. (2021). Geochemical potential mapping of iron-oxide targets by Prediction-Area plot and Concentration-Number fractal model in Esfordi, Iran. International Journal of Mining and Geo-Engineering, 55(2),171-181.
[26] Shamseddin Meigooni, M., M. Lotfi, P. Afzal, N. Nezafati, and M.K. Razi. (2021). Application of multivariate geostatistical simulation and fractal analysis for detection of rare-earth element geochemical anomalies in the Esfordi phosphate mine, Central Iran. Geochemistry: Exploration, Environment, Analysis, 21(2),geochem2020-035.
[27] Zuo, R., Y. Xiong, J. Wang, and E.J.M. Carranza. (2019). Deep learning and its application in geochemical mapping. Earth-science reviews, 192,1-14.
[28] Hajihosseinlou, M., A. Maghsoudi, and R. Ghezelbash. (2024). A comprehensive evaluation of OPTICS, GMM and K-means clustering methodologies for geochemical anomaly detection connected with sample catchment basins. Geochemistry,126094.
[29] He, M.-Y., J.-B. Dong, Z. Jin, C.-Y. Liu, J. Xiao, F. Zhang, H. Sun, Z.-Q. Zhao, L.-F. Gou, and W.-G. Liu. (2021). Pedogenic processes in loess-paleosol sediments: Clues from Li isotopes of leachate in Luochuan loess. Geochimica et Cosmochimica Acta, 299,151-162.
[30] Afzal, P., S. Farhadi, M. Boveiri Konari, M. Shamseddin Meigooni, and L. Daneshvar Saein. (2022). Geochemical anomaly detection in the Irankuh District using Hybrid Machine learning technique and fractal modeling. Geopersia, 12(1),191-199.
[31] Xiong, Y. and R. Zuo. (2020). Recognizing multivariate geochemical anomalies for mineral exploration by combining deep learning and one-class support vector machine. Computers & geosciences, 140,104484.
[32] Esmaeiloghli, S., S.H. Tabatabaei, and E.J.M. Carranza. (2023). Infomax-based deep autoencoder network for recognition of multi-element geochemical anomalies linked to mineralization. Computers & Geosciences, 175,105341.
[33] Farhadi, S., S. Tatullo, M.B. Konari, and P. Afzal. (2024). Evaluating StackingC and ensemble models for enhanced lithological classification in geological mapping. Journal of Geochemical Exploration, 260,107441.
[34] Li, S., J. Chen, and J. Xiang. (2020). Applications of deep convolutional neural networks in prospecting prediction based on two-dimensional geological big data. Neural computing and applications, 32,2037-2053.
[35] Mirzabozorg, S.A.A.S., M. Abedi, and M. Yousefi. (2024). Enhancing training performance of convolutional neural network algorithm through an autoencoder-based unsupervised labeling framework for mineral exploration targeting. Geochemistry,126197.
[36] Zhao, J., S. Chen, and R. Zuo. (2016). Identifying geochemical anomalies associated with Au–Cu mineralization using multifractal and artificial neural network models in the Ningqiang district, Shaanxi, China. Journal of Geochemical Exploration, 164,54-64.
[37] Guan, Q., S. Ren, L. Chen, B. Feng, and Y. Yao. (2021). A spatial-compositional feature fusion convolutional autoencoder for multivariate geochemical anomaly recognition. Computers & Geosciences, 156,104890.
[38] Mirzabozorg, S.A.A.S. and M. Abedi. (2023). Recognition of mineralization-related anomaly patterns through an autoencoder neural network for mineral exploration targeting. Applied Geochemistry,105807.
[39] Chen, Y. and W. Wu. (2017). Application of one-class support vector machine to quickly identify multivariate anomalies from geochemical exploration data. Geochemistry: Exploration, Environment, Analysis, 17(3),231-238.
[40] Chen, Y., S. Wang, Q. Zhao, and G. Sun. (2021). Detection of multivariate geochemical anomalies using the bat-optimized isolation forest and bat-optimized elliptic envelope models. Journal of Earth Science, 32(2),415-426.
[41] Shahrestani, S. and E.J.M. Carranza. (2024). Effectiveness of LOF, iForest, and OCSVM in detecting anomalies in stream sediment geochemical data. Geochemistry: Exploration, Environment, Analysis,geochem2024-009.
[42] Bigdeli, A., A. Maghsoudi, and R. Ghezelbash. (2022). Application of self-organizing map (SOM) and K-means clustering algorithms for portraying geochemical anomaly patterns in Moalleman district, NE Iran. Journal of Geochemical Exploration, 233,106923.
[43] Rezapour, M.J., M. Abedi, A. Bahroudi, and H. Rahimi. (2020). A clustering approach for mineral potential mapping: A deposit-scale porphyry copper exploration targeting. Geopersia, 10(1),149-163.
[44] Agha Seyyed Mirzabozorg, S., M. Abedi, and F. Ahmadi. (2023). Clustering of Areas Prone to Iron Mineralization in Esfordi Range based on a Hybrid Method of Knowledge-and Data-Driven Approaches. Journal of Mineral Resources Engineering, 8(4),1-26.
[45] Aryafar, A., H. Moeini, and V. Khosravi. (2020). CRFA-CRBM: a hybrid technique for anomaly recognition in regional geochemical exploration; case study: Dehsalm area, east of Iran. International Journal of Mining and Geo-Engineering, 54(1),33-38.
[46]  Aryafar, A. and H. Moeini. (2017). Application of continuous restricted Boltzmann machine to detect multivariate anomalies from stream sediment geochemical data, Korit, East of Iran. Journal of Mining and Environment, 8(4),673-682.
[47] Xiong, Y. and R. Zuo. (2016). Recognition of geochemical anomalies using a deep autoencoder network. Computers & Geosciences, 86,75-82.
[48] Xiong, Y. and R. Zuo. (2021). Robust feature extraction for geochemical anomaly recognition using a stacked convolutional denoising autoencoder. Mathematical Geosciences,1-22.
[49] Saremi, M., Z. Hoseinzade, S.A.A.S. Mirzabozorg, A.B. Pour, B. Zoheir, and A. Almasi. (2024). Integrated remote sensing and geochemical studies for enhanced prospectivity mapping of porphyry copper deposits: a case study from the Pariz district, Urmia-Dokhtar metallogenic belt, southern Iran. Remote Sensing Applications: Society and Environment,101343.
[50] Xiong, Y., R. Zuo, and E.J.M. Carranza. (2018). Mapping mineral prospectivity through big data analytics and a deep learning algorithm. Ore Geology Reviews, 102,811-817.
[51] Yu, X., P. Yu, K. Wang, W. Cao, and Y. Zhou. (2024). Data-Driven Mineral Prospectivity Mapping Based on Known Deposits Using Association Rules. Natural Resources Research,1-24.
[52] Chen, L., Q. Guan, B. Feng, H. Yue, J. Wang, and F. Zhang. (2019). A multi-convolutional autoencoder approach to multivariate geochemical anomaly recognition. Minerals, 9(5),270.
[53] Maghsoudi, A., M. Rahmani, and B. Rashidi, Gold deposits and indications of Iran. 2005.
[54] Behroozi, A. (1987). Geological map of Iran 1: 100,000 series, Feizabad. Geological Survey of Iran, Tehran.
[55] Karimpour, M.H., A.M. Shafaroudi, A.M. Bajestani, R.K. Schader, C.R. Stern, L. Farmer, and M. Sadeghi. (2017). Geochemistry, geochronology, isotope and fluid inclusion studies of the Kuh-e-Zar deposit, Khaf-Kashmar-Bardaskan magmatic belt, NE Iran: Evidence of gold-rich iron oxide–copper–gold deposit. Journal of Geochemical Exploration, 183,58-78.
[56] Taghadosi, H. and A. Malekzadeh Shafaroudi. (2018). Evidences of probable porphyry Cu-Au mineralization in Namegh area, Northeast of Kashmar: geology, Alteration, mineralization, geochemistry, and fluids inclusion studies. Scientific Quarterly Journal of Geosciences, 27(108),105-114.
[57] Yousefi, M. and V. Nykänen. (2016). Data-driven logistic-based weighting of geochemical and geological evidence layers in mineral prospectivity mapping. Journal of Geochemical Exploration, 164,94-106.
[58] Zhang, Y. A better autoencoder for image: Convolutional autoencoder. in ICONIP17-DCEC. 2018.
[59] Zhao, B., D. Zhang, P. Tang, X. Luo, H. Wan, and L. An. (2023). Recognition of multivariate geochemical anomalies using a geologically-constrained variational autoencoder network with spectrum separable module–A case study in Shangluo District, China. Applied Geochemistry, 156,105765.
[60] Zeiler, M.D. and R. Fergus. Visualizing and understanding convolutional networks. in Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part I 13. 2014. Springer.
[61] Yousefi, M. (2017). Recognition of an enhanced multi-element geochemical signature of porphyry copper deposits for vectoring into mineralized zones and delimiting exploration targets in Jiroft area, SE Iran. Ore Geology Reviews, 83,200-214.
[62] Yousefi, M., A. Kamkar-Rouhani, and M. Alipoor. (2014). Increasing the Exploration Success and Intensify of Stream Sediment Geochemical Halos Using Recognizing and Omitting the Non-Predictive Factors, Case Studies: Fluorite and Copper Mineralization. Scientific Quarterly Journal of Geosciences, 24(93),85-92.
[63] Parsa, M., A. Maghsoudi, M. Yousefi, and M. Sadeghi. (2016). Recognition of significant multi-element geochemical signatures of porphyry Cu deposits in Noghdouz area, NW Iran. Journal of Geochemical Exploration, 165,111-124.
[64] Shahrestani, S., D.R. Cohen, and A.R. Mokhtari. (2024). A comparison of PCA and ICA in geochemical pattern recognition of soil data: The case of Cyprus. Journal of Geochemical Exploration, 264,107539.
[65] Hajihosseinlou, M., A. Maghsoudi, and R. Ghezelbash. (2024). Regularization in machine learning models for MVT Pb-Zn prospectivity mapping: applying lasso and elastic-net algorithms. Earth Science Informatics,1-15.
[66] Pirdadeh Beyranvand, D., M.A. Arian, T. Farhadinejad, and A. Ashja Ardalan. (2021). Identification of Geochemical Distribution of REEs Using Factor Analysis and Concentration-Number (CN) Fractal Modeling in Granitoids, South of Varcheh 1: 100000 Sheet, Central Iran. Iranian Journal of Earth Sciences, 13(4),288-289.
[67] Saadati, H., P. Afzal, H. Torshizian, and A. Solgi. (2020). Geochemical exploration for lithium in NE Iran using the geochemical mapping prospectivity index, staged factor analysis, and a fractal model. Geochemistry: Exploration, Environment, Analysis, 20(4),461-472.
[68] Saremi, M., A. Maghsoudi, Z. Hoseinzade, and A.R. Mokhtari. (2024). Data-driven AHP: a novel method for porphyry copper prospectivity mapping in the Varzaghan District, NW Iran. Earth Science Informatics,1-16.
[69] Koohzadi, F., P. Afzal, D. Jahani, and M. Pourkermani. (2021). Geochemical exploration for Li in regional scale utilizing Staged Factor Analysis (SFA) and Spectrum-Area (SA) fractal model in north central Iran. Iranian Journal of Earth Sciences, 13(4),299-307.
[70] Saremi, M., A. Maghsoudi, R. Ghezelbash, M. Yousefi, and A. Hezarkhani. (2024). Targeting of porphyry copper mineralization using a continuous-based logistic function approach in the Varzaghan district, north of Urumieh-Dokhtar magmatic arc. Journal of Mining and Environment.
[71] Zuo, R. and Y. Xiong. (2018). Big data analytics of identifying geochemical anomalies supported by machine learning methods. Natural Resources Research, 27,5-13.
[72] Zhang, C., R. Zuo, and Y. Xiong. (2021). Detection of the multivariate geochemical anomalies associated with mineralization using a deep convolutional neural network and a pixel-pair feature method. Applied Geochemistry, 130,104994.
[73] Zhang, S., E.J.M. Carranza, H. Wei, K. Xiao, F. Yang, J. Xiang, S. Zhang, and Y. Xu. (2021). Data-driven mineral prospectivity mapping by joint application of unsupervised convolutional auto-encoder network and supervised convolutional neural network. Natural Resources Research, 30,1011-1031.
[74] Yousefi, M. and E.J.M. Carranza. (2015). Prediction–area (P–A) plot and C–A fractal analysis to classify and evaluate evidential maps for mineral prospectivity modeling. Computers & Geosciences, 79,69-81.
[75] Roshanravan, B., H. Aghajani, M. Yousefi, and O. Kreuzer. (2019). An improved prediction-area plot for prospectivity analysis of mineral deposits. Natural Resources Research, 28,1089-1105.
[76] Hoseinzade, Z., A. Zavarei, and K. Shirani. (2021). Application of prediction–area plot in the assessment of MCDM methods through VIKOR, PROMETHEE II, and permutation. Natural Hazards, 109,2489-2507.
[77] Afzal, P., A. Khakzad, P. Moarefvand, N.R. Omran, B. Esfandiari, and Y.F. Alghalandis. (2010). Geochemical anomaly separation by multifractal modeling in Kahang (Gor Gor) porphyry system, Central Iran. Journal of Geochemical Exploration, 104(1-2),34-46.
[78] Afzal, P., M. Abdideh, and L. Daneshvar Saein. (2023). Separation of productivity index zones using fractal models to identify promising areas of fractured reservoir rocks. Journal of Petroleum Exploration and Production Technology, 13(9),1901-1910.
[79] Li, H., X. Li, F. Yuan, S.M. Jowitt, M. Zhang, J. Zhou, T. Zhou, X. Li, C. Ge, and B. Wu. (2020). Convolutional neural network and transfer learning based mineral prospectivity modeling for geochemical exploration of Au mineralization within the Guandian–Zhangbaling area, Anhui Province, China. Applied Geochemistry, 122,104747.