Building a Random Forest predictive modeling of mineral perspectivity and Mapping gold mineral prospects in Tam Ky - Phuoc Son, Quang Nam
- Authors: Tinh Thanh Bui 1*, Dung Tien Nguyen 1, Khang Quang Luong 1, Bac Hoang Bui 1, Sang Viet Bui 2
Affiliations:
1 Hanoi University of Mining and Geology, Hanoi, Vietnam
2 Intergeo Devision, Hanoi, Vietnam
- *Corresponding:This email address is being protected from spambots. You need JavaScript enabled to view it.
- Keywords: Gold, Mapping, Random Forest, Tam Ky - Phuoc Son The predictive modeling of mineral prospectivity.
- Received: 23rd-Apr-2022
- Revised: 17th-Aug-2022
- Accepted: 21st-Sept-2022
- Online: 31st-Oct-2022
- Section: Geology - Mineral
Abstract:
Tam Ky - Phuoc Son area has great potential for gold mineral with 98 gold occurrences, but the evaluation of the entire gold-mineralization potential of the area is still very limited, while this is considered as a basis for planning, exploration, and mining. The paper uses an Artificial Intelligence model which has a name Random Forest to build predictive modeling of mineral perspectivity and to map the gold mineral prospect of the study area. 12 influencing factors are selected to build the dataset for model training and mapping gold minerals prospect, including Geology, fault systems (NE-SW faults, NW-SE faults, sub meridian faults, sub-latitude faults), Bouguer geophysical anomaly, a geochemical anomaly of silver (Ag), gold ( Au), lead (Pb), zinc (Zn), copper (Cu) and distance to the geologic boundary of complexes related to gold mineralization. The data which are generated from these factors are 12 fuzzy maps. This data combines with 98 occurrences’ locations to create a dataset that is used to train a model of mineral perspectivity using the Random Forest algorithm. After training the model is evaluated by validation. The results of the Random Forest predictive modeling of mineral prospects are well trained with an accuracy of 95.99% on the training set and 83.05 on the validation set, the performance of the model is excellent on both datasets with AUC of 0.993 and 0.95, respectively. Finally, a mineral perspectivity map is built using the trained model. The study area is divided into 3 types of areas: high, medium, and low prospects. The area of high prospect is 982.8 km2, covering 71% of the gold occurrences.
Bonham-Carter, G.F., (2014). Geographic information systems for geoscientists: modelling with GIS. No. 13. Elsevier.
Breiman, L., (2015). Random forests leo breiman and adele cutler. Random Forests-Classification Description, Vol. 106.
Breiman, L., (2002). Manual on setting up, using, and understanding random forests v3. 1. Statistics Department University of California Berkeley, CA, USA, Vol. 1, No. 58, pp. 3-42.
Bradter, U., Kunin, W.E., Altringham, J.D., Thom, T.G., Benton, T.G., (2013). Identifying appropriate spatial scales of predictors in species distribution models with the random forest algorithm. Methods in Ecology Benton and Evolution, Vol. 4, No. 2, pp. 167-174.
Bui, M., (1986). Report on general prospecting of gold deposits in the Tam Ky – Phuoc Son area, Quang Nam-Da Nang. Center for Information, Archives and Journal of Geology, General Department of Geology and Mineral Resources. (in Vietnamese).
Cantor, S.B., and Kattan, M.W., (2000). Determining the area under the ROC curve for a binary diagnostic test. Medical Decision Making, Vol. 20, pp. 468-470.
Carranza, E.J.M., and Alice, G., (2015a). Data-driven predictive mapping of gold prospectivity, Baguio district, Philippines: Application of Random Forests algorithm. Ore Geology Reviews Laborte, Vol. 71, pp. 777-787.
Carranza, E.J.M., and Alice, G., (2015b). Random forest predictive modeling of mineral prospectivity with small number of prospects and data with missing values in Abra (Philippines). Computers Laborte and Geosciences, Vol. 74, pp. 60-70.
Cracknell, M.J., and Anya, M., (2013). The upside of uncertainty: Identification of lithology contact zones from airborne geophysics and satellite data using random forests and support vector machines. Geophysics Reading, Vol. 78, No. 3, pp. WB113-WB126.
Cracknell, M.J., and Anya, M., (2014). Geological mapping using remote sensing data: A comparison of five machine learning algorithms, their response to variations in the spatial distribution of training data and the use of explicit spatial information. Computers Reading and Geosciences, Vol. 63, pp. 22-33.
Cat, N.H., (1999). Report on geological mapping and mineral prospecting of the Tam Ky-Hiep Duc sheet groups at 1:50,000 scale. Center for Information, Archives and Journal of Geology, General Department of Geology and Mineral Resources. (in Vietnamese).
Zhang, C., and Ma, Y., (2012). Ensemble machine learning: methods and applications. Springer.
Steinberg, D., Golovnya, M., Scott, N. S., (2004). A brief overview to random forests. Salford Systems Cardell.
Dinh, Đ.H., (2013). Report on primary gold exploration in the Ho Ray area, Bong Mieu gold mine, Tam Lanh, Phuc Ninh, Quang Nam. Center for Information, Archives and Journal of Geology, General Department of Geology and Mineral Resources. (in Vietnamese).
Dinh, T.H., (2014). Report on the investigation, additional assessment, and identification of the remaining resources of the original gold mine in slot 39, Phuoc Hoa commune, Phuoc Son district, Quang Nam province. Center for Information, Archives and Journal of Geology, General Department of Geology and Mineral Resources. (in Vietnamese).
Do, Q.B., (2001). Report on the evaluating potential and other minerals related to the green and black shale formations in the Quang Nam zone. Center for Information, Archives and Journal of Geology, General Department of Geology and Mineral Resources. (in Vietnamese).
Do, V.C., (1998). Report on results of geological mapping and mineral deposits at 1:50,000 scale for the Dakglei - Kham Duc sheet groups. Center for Information, Archives and Journal of Geology, General Department of Geology and Mineral Resources. (in Vietnamese).
Hoang, Q.L., (2015). Report on the results of additional investigation and assessment to determine the remaining resources of the original gold mine in village 1, Tien Lap commune, Tien Phuoc district, Quang Nam province. Center for Information, Archives and Journal of Geology, General Department of Geology and Mineral Resources. (in Vietnamese).
Laborte, A.G., Maunahan, A.A., Hijmans, R.J., (2012). Opportunities for expanding paddy rice production in Laos: spatial predictive modeling using Random Forest. Journal of Land Use Science Hijmans, Vol. 7, No. 1, pp. 21-33.
Livington, F., (2005). Implementation of Breiman’s random forest machine learning algorithm. ECE591Q Machine Learning Journal Paper Livingston, pp. 1-13.
Le, D.H., (1985). Prospective assessment report of Bong Mieu primary gold mine, Quang Nam - Da Nang. Center for Information, Archives and Journal of Geology, General Department of Geology and Mineral Resources. (in Vietnamese).
Le, V.D., (2002a). Report on assessment results of gold minerals and other minerals associated with Tra Nu, Tra Thuy, and Quang Nam. Center for Information, Archives and Journal of Geology, General Department of Geology and Mineral Resources. (in Vietnamese).
Le, V.H., (2002b). Report on geological exploration results in Bai Dat and Bai Go areas of Dak Sa gold mine, Phuoc Son district, Quang Nam province. Center for Information, Archives and Journal of Geology, General Department of Geology and Mineral Resources. (in Vietnamese).
Le, V.H., (1999). Report on gold exploration results in Tien Ha area, Tien Phuoc district, Hiep Duc, Que Son, Quang Nam province. Center for Information, Archives and Journal of Geology, General Department of Geology and Mineral Resources. (in Vietnamese).
Le, V.H., (2011). Primary gold prospecting report in Phuoc Son area, Phuoc Duc and Phuoc Xuan communes, Phuoc Son district, Quang Nam province.. Center for Information, Archives and Journal of Geology, General Department of Geology and Mineral Resources. (in Vietnamese).
Pham, V.T., (2001). Report on assessment results of gold and other minerals in Phuoc Thanh - Phuoc Son area, Quang Nam province. Center for Information, Archives and Journal of Geology, General Department of Geology and Mineral Resources. (in Vietnamese).
Reddy, R.K.T., and Bonham-Carter, G.F., (1991). A decision - tree approach to mineral potential mapping in Snow Lake area, Manitoba. Canadian Journal of Remote Sensing Bonham-Carter, Vol. 17, No. 2, pp. 191-200.
Rodriguez-Galiano, V.F., Ghimire, B., Rogan, J., Chica-Olmo, M., Rigol-Sanchez, J.P., (2012). An assessment of the effectiveness of a random forest classifier for land-cover classification. ISPRS Journal of Photogrammetry Rigol-Sanchez and Remote Sensing, Vol. 67, pp. 93-104.
Rodriguez-Galiano, V.F., Chica-Olmo, M. and Chica-Rivas, M., (2014). Predictive modelling of gold potential with the integration of multisource information based on random forest: a case study on the Rodalquilar area, Southern Spain. International Journal of Geographical Information Science Chica-Rivas, Vol. 28, No. 7, pp. 1336-1354.
Tran, V.T., and Vu, K., (2009). Geology and Natural Resources of Vietnam. Natural Science and Technics Publishing House, Hanoi, 589 pp. (in Vietnamese).
Vo, Q.B., (2018). The research report, forecasting the potential of gold minerals hidden deep in gold ore fields in the Tam Ky - Phuoc Son zone in central Vietnam. Center for Information, Archives and Journal of Geology, General Department of Geology and Mineral Resources. (in Vietnamese).
Other articles
Journal of Mining and Earth Sciences
Publishing Office - Hanoi University of Mining and Geology
No.18 Vien Street - Duc Thang Ward - Bac Tu Liem District - Ha Noi
Tel: (+84-24) 3219 1509 Fax: (+84-24) 3838 9633 
Email: jmes@humg.edu.vn