Simulation-based mineral prospectivity modeling and Gray Wolf optimization algorithm for delimiting exploration targets

Ore Geology Reviews, Год журнала: 2025, Номер unknown, С. 106458 - 106458

Опубликована: Янв. 1, 2025

Язык: Английский

---

Translation of mineral system components into time step-based ore-forming events and evidence maps for mineral exploration: Intelligent mineral prospectivity mapping through adaptation of recurrent neural networks and random forest algorithm

Ore Geology Reviews, Год журнала: 2025, Номер unknown, С. 106537 - 106537

Опубликована: Фев. 1, 2025

Язык: Английский

---

Pan-Canadian Predictive Modeling of Lithium–Cesium–Tantalum Pegmatites with Deep Learning and Natural Language Processing

Natural Resources Research, Год журнала: 2025, Номер unknown

Опубликована: Фев. 7, 2025

Abstract The discovery of new lithium resources is essential because plays a vital role in the manufacturing green technology. Along with brines and volcano–sedimentary deposits, approximately one-third share global associated lithium-cesium-tantalum (LCT) pegmatites, Canada hosting numerous examples. This research applied generative adversarial networks, natural language processing, convolutional neural networks to generate mineral prospectivity models support exploration targeting for Canadian LCT pegmatites. Geoscientific text data included within public bedrock geology maps processing were used convert conceptual criteria into evidence layers that complement more traditional, geophysical geochronological modeling (MPM). A multilayer architecture including an attention mechanism, was designed modeling. trained validated using variable synthetically generated class labels, input image sizes, hyperparameters, resulting ensemble 1000 models. uncertainty analyzed risk–return analysis, yielding bivariate choropleth plot facilitates interpretation downstream applications. further complemented by employing post hoc interpretability algorithms translate black-box nature comprehensible content. low-risk high return our reduces search space discovering pegmatites 88%, delineating 99% known Canada. results this study suggest workflow (i.e., combining synthetic generation, propagation MPM) decision-making regional-scale could also be other systems.

Язык: Английский

---

Interpretability Analysis of Data Augmented Convolutional Neural Network in Mineral Prospectivity Mapping Using Black-Box Visualization Tools

Natural Resources Research, Год журнала: 2025, Номер unknown

Опубликована: Янв. 31, 2025

Язык: Английский

---

Advanced deep learning models for predicting elemental concentrations in iron ore mine using XRF data: a cost-effective alternative to ICP-MS methods

Environmental Geochemistry and Health, Год журнала: 2025, Номер 47(4)

Опубликована: Март 5, 2025

Язык: Английский

---

A semi-supervised learning framework for intelligent mineral prospectivity mapping: Incorporation of the CatBoost and Gaussian mixture model algorithms

Journal of Geochemical Exploration, Год журнала: 2025, Номер unknown, С. 107755 - 107755

Опубликована: Март 1, 2025

Язык: Английский

---

Predicting Geothermal Heat Flow in the Bohai Bay Basin Based on Machine Learning Methods

Mathematical Geosciences, Год журнала: 2025, Номер unknown

Опубликована: Март 26, 2025

Язык: Английский

---

Mineral Prospectivity Modeling of Graphite Deposits and Occurrences in Canada

Natural Resources Research, Год журнала: 2025, Номер unknown

Опубликована: Март 26, 2025

Язык: Английский

---

Geological Knowledge-Embedding Transfer-Learning Architecture for Geochemical Anomaly Identification

Mathematical Geosciences, Год журнала: 2025, Номер unknown

Опубликована: Апрель 22, 2025

Язык: Английский

---

Interpretable machine learning for mineral prospectivity mapping in the Qulong–Jiama district, Tibet, China

Ore Geology Reviews, Год журнала: 2025, Номер 182, С. 106659 - 106659

Опубликована: Май 6, 2025

Язык: Английский

---