Применение алгоритмов машинного обучения для прогнозирования золоторудной минерализации Верхнеамгинского щелочного массива, Алдано-Становой щит = Application of machine learning algorithms to predict gold mineralizationin the Verkhneamginsky alkaline massif, Aldan-Stanovoy Shield
Статья в журнале
Русский
553.411:004(571.56)
10.31242/2618-9712-2025-30-2-205-219
машинное обучение; золоторудная минерализация; геохимические данные; поисковые работы; Верхнеамгинский щелочной массив; Алдано-Становой щит; machine learning; gold mineralization; geochemical data; exploration; Verkhneamginsky alkaline massif; Aldan-Stanovoy Shield
С. 205-219
Природные ресурсы Арктики и Субарктики = Arctic and Subarctic natural resources: научный журнал
Якутск, Академия наук Республики Саха (Якутия)
Основан в 1996 г.
Выходит 4 раза в год
2618-9712 (print), 2686-9683 (online)
Природные ресурсы Арктики и Субарктики : научный журнал / главный редактор И. И. Колодезников ; Академия наук РС (Я), Якутский научный центр СО РАН, Северо-Восточный федеральный университет им. М. К. Аммосова, Министерство образования и науки РС (Я). - Якутск : Академия наук Республики Саха (Якутия), 2018-. - 2025, Т. 30, (N 2). - 171-346 с.
The study reports on the application of machine learning methods for predicting gold mineralization in the prospecting phase of geological exploration. It focuses on the Verkhneamginsky alkaline massif, situated within the Aldan-Stanovoy Shield, as a case study. The investigation included the analysis of 403 ore samples, which were evaluated through Inductively Coupled Plasma Atomic Emission Spectroscopy (ICP-AES) to determine the concentrations of 25 chemical elements. A total of eight classification algorithms were assessed in this investigation, including Random Forest, Support Vector Machine, Neural Network (Multilayer Perceptron), Boosting (AdaBoost), Decision Tree, K-Nearest Neighbors, Linear Discriminant Analysis, and Naive Bayes. The Random Forest and Support Vector Machine algorithms demonstrated the highest accuracy, achieving 89.6%, by identifying the relationships among ore elements (Au,Ag, As, Cu, Sb) and those elements that displayed negative correlations (Mg, Ca, Ti). These results were further validated through Receiver Operating Characteristic (ROC) analysis. In the process of developing the machine learning model, the values corresponding to the “ore” factor for each sample were designated as the target variable, while serving as predictors. To enable a comparative analysis between the parameters of established entities and the predicted regions, anomalous fields of the “ore” factor values were constructed. Additionally, machine learning methods enable the rapid and reliable interpretation of virtually any geochemical analytical data in the field, including data obtained through modern spectrometry methods and portable X-ray fluorescence (XRF) analyzers. The research further underscores the significance of integrating traditional statistical approaches, such as cluster and factor analysis,with contemporary machine learning algorithms to improve the accuracy of predictions.
Чудинов, П. Л.
Применение алгоритмов машинного обучения для прогнозирования золоторудной минерализации Верхнеамгинского щелочного массива, Алдано-Становой щит / П. Л. Чудинов, В. Ю. Фридовский ; АО "Полюс Алдан", Институт геологии алмаза и благородных металлов СО РАН // Природные ресурсы Арктики и Субарктики. - 2025. - N 2, Т. 30. - С. 205-219. - DOI: 10.31242/2618-9712-2025-30-2-205-219
DOI: 10.31242/2618-9712-2025-30-2-205-219
Войдите в систему, чтобы открыть документ