Bài viết Xây dựng mô hình rừng ngẫu nhiên dự báo tài nguyên và phân vùng triển vọng khoáng sản vàng khu vực Tam Kỳ - Phước Sơn, Quảng Nam nghiên cứu sử dụng mô hình rừng ngẫu nhiên (Random Forest) xây dựng mô hình dự báo tài nguyên khoáng sản vàng và phân vùng triển vọng khoáng sản vàng vùng nghiên cứu. | 82 Journal of Mining and Earth Sciences Vol. 63 Issue 5 2022 82 - 92 Building a Random Forest predictive modeling of mineral perspectivity and Mapping gold mineral prospects in Tam Ky - Phuoc Son Quang Nam Tinh Thanh Bui 1 Dung Tien Nguyen 1 Khang Quang Luong 1 Bac Hoang Bui 1 Sang Viet Bui 2 1 Hanoi University of Mining and Geology Hanoi Vietnam 2 Intergeo Devision Hanoi Vietnam ARTICLE INFO ABSTRACT Article history Tam Ky - Phuoc Son area has great potential for gold mineral with 98 gold Received 23rd Dec. 2021 occurrences but the evaluation of the entire gold-mineralization potential Revised 27th May 2022 of the area is still very limited while this is considered as a basis for planning Accepted 31st Oct. 2022 exploration and mining. The paper uses an Artificial Intelligence model Keywords which has a name Random Forest to build predictive modeling of mineral Gold 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 mapping gold minerals prospect including Geology fault systems NE-SW Random Forest faults NW-SE faults sub meridian faults sub-latitude faults Bouguer Tam Ky - Phuoc Son geophysical anomaly a geochemical anomaly of silver Ag gold Au lead The predictive modeling of Pb zinc Zn copper Cu and distance to the geologic boundary of mineral prospectivity. 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 on the training set and on the validation set the performance of the model is excellent on both datasets with AUC of and respectively. Finally a mineral .
