☆ 4.7 Article

A Novel Scheme for Mapping of MVT-Type Pb-Zn Prospectivity: LightGBM, a Highly Efficient Gradient Boosting Decision Tree Machine Learning Algorithm

NATURAL RESOURCES RESEARCH (2023)

Related references

Note: Only part of the references are listed.

Article Energy & Fuels

Predicting shale mineralogical brittleness index from seismic and elastic property logs using interpretable deep learning

Jaewook Lee et al.

Summary: The mineralogical brittleness index (MBI) is an important parameter for identifying optimal production well locations and optimizing hydraulic fracturing in organic-rich shale formations. However, the exact physical relationship between MBI and seismic properties is not well understood. In this study, we developed a deep learning approach to obtain a more reliable MBI model from seismic properties and enhance interpretability with Shapley values. We analyzed the statistical relationship between MBI and eight seismic properties from well logs, identified influential input variables, and used a deep neural network technique to derive a nonlinear estimation model. Our approach was tested and verified on field data, demonstrating its potential for enhancing unconventional shale reservoir characterization.

GEOENERGY SCIENCE AND ENGINEERING (2023)

Add to Collection

Article Computer Science, Artificial Intelligence

Genetic algorithm to optimize the SVM and K-means algorithms for mapping of mineral prospectivity

Reza Ghezelbash et al.

Summary: In this study, unsupervised clustering and supervised machine learning methods were used to construct mineral prospectivity maps and genetic algorithm was incorporated to optimize model performance. The results showed that the genetic-based SVM model outperformed other models in detecting favorable areas associated with porphyry-type Cu mineralization.

NEURAL COMPUTING & APPLICATIONS (2023)

Add to Collection

Article Geology

Mineral prospectivity mapping using attention-based convolutional neural network

Quanke Li et al.

Summary: This paper proposes an ensemble method for mineral prospectivity mapping (MPM) based on Convolutional Neural Network (CNN) and Attention model. The method, ATT-CNN, enhances the extraction of key channel features related to mineralization, leading to improved prediction accuracy and geological generalization.

ORE GEOLOGY REVIEWS (2023)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Mineral prospectivity mapping using a joint singularity-based weighting method and long short-term memory network

Ziye Wang et al.

Summary: The successful application of GIS-based mineral prospectivity mapping (MPM) relies on reasonable evidential layers and excellent models; a joint workflow was developed in this study that combines a rational evidence layer weighting method with a deep learning MPM model, considering the spatial and genetic associations of geological features.

COMPUTERS & GEOSCIENCES (2022)

Add to Collection

Article Geosciences, Multidisciplinary

Mineral Prospectivity Mapping based on Isolation Forest and Random Forest: Implication for the Existence of Spatial Signature of Mineralization in Outliers

Shuai Zhang et al.

Summary: This study investigated the efficacy of outlier-based training samples in data-driven mineral prospectivity mapping compared to traditional practices of using known mineralized locations. Results from RF modeling using different sets of training samples revealed a bias towards known mineralized locations in data-driven MPM. The proposed outlier-based training samples involved unsupervised learning for outlier detection and supervised learning using the resulting outliers as positive training samples, resulting in narrowing down prospective target areas effectively.

NATURAL RESOURCES RESEARCH (2022)

Add to Collection

Article Mathematics, Interdisciplinary Applications

Analysis and visualization of accidents severity based on LightGBM-TPE

Kun Li et al.

Summary: In recent years, road traffic accidents have been receiving increasing attention as a leading cause of accidental deaths across multiple disciplines. Studying the severity of accidents can help identify the causal relationship between different risk factors and road accidents, thereby improving road traffic safety. However, the application of data visualization in traffic safety investigations is still lacking. In this study, we propose a hybrid algorithm called LightGBM-TPE that incorporates data visualization into machine learning to analyze the UK's traffic accidents data in 2017. The algorithm outperforms other typical machine learning algorithms in terms of f1, accuracy, recall, and precision metrics. By calculating the SHAP value of each feature using LightGBM-TPE, we find that Longitude, Latitude, Hour, and Day_of_Week are the four risk factors most closely related to accident severity. The visualization of the data further confirms this conclusion. Overall, our research explores an innovative way to understand and evaluate the importance of features in road traffic accidents, which can contribute to suggesting effective solutions for improving traffic safety.

CHAOS SOLITONS & FRACTALS (2022)

Add to Collection

Article Geosciences, Multidisciplinary

Three-Dimensional Mineral Prospectivity Mapping by XGBoost Modeling: A Case Study of the Lannigou Gold Deposit, China

Quanping Zhang et al.

Summary: This study applied the 3DMPM approach to explore the deep mineral resources of the Lannigou gold deposit in Guizhou. A prediction model based on the XGBoost algorithm was built, which outperformed traditional methods in terms of prediction accuracy.

NATURAL RESOURCES RESEARCH (2022)

Add to Collection

Article Geosciences, Multidisciplinary

A Geologically Constrained Variational Autoencoder for Mineral Prospectivity Mapping

Renguang Zuo et al.

Summary: In this study, a geologically constrained variational autoencoder (VAE) was proposed to map prospectivity for gold mineralization in the Baguio District of the Philippines. The geologically constrained VAE can enhance the probabilities in areas with high potential for mineralization and increase the interpretability of the obtained results compared to traditional VAE methods.

NATURAL RESOURCES RESEARCH (2022)

Add to Collection

Article Geosciences, Multidisciplinary

Mineral Prospectivity Prediction by Integration of Convolutional Autoencoder Network and Random Forest

Na Yang et al.

Summary: This paper proposes the use of convolutional autoencoder networks to solve the issue of mixed feature extraction in mineral prospectivity prediction. By mining latent high-level features for each predictor variable, the feature mapping outcomes of each channel are enhanced. The random forest model outperforms other models according to comprehensive evaluations. The proposed integrated method is proven to be effective and reliable in predicting gold deposits in the Fengxian region of Southern Qinling in China.

NATURAL RESOURCES RESEARCH (2022)

Add to Collection

Article Geosciences, Multidisciplinary

Visual Interpretable Deep Learning Algorithm for Geochemical Anomaly Recognition

Zijing Luo et al.

Summary: Deep learning algorithms have outperformed traditional methods in multivariate geochemical anomaly recognition due to their ability to extract features from nonlinear data. However, most DLAs are black-box approaches due to the high nonlinearity of the hidden layer. This study improves the interpretability of the model by visualizing features and integrating geological domain knowledge into the loss function. The addition of penalty terms and the integration of spatiotemporal and genetic relationships enhance the geological interpretability of the network. A case study demonstrates strong spatial correlation between the results of the geologically constrained AAE and the geological features in the study area.

NATURAL RESOURCES RESEARCH (2022)

Add to Collection

Article Geosciences, Multidisciplinary

Random-Drop Data Augmentation of Deep Convolutional Neural Network for Mineral Prospectivity Mapping

Tong Li et al.

Summary: The study utilized a CNN for mineral prospectivity mapping in southwestern Fujian Province, China, addressing limitations in applying CNN to geological prospecting big data. A random-drop data augmentation method was used to generate sufficient training samples, determining a suitable CNN architecture for MPM. The findings suggest that CNN is a promising tool for integrating multi-source geoscience data for mineral exploration.

NATURAL RESOURCES RESEARCH (2021)

Add to Collection

Article Computer Science, Interdisciplinary Applications

A new strategy for spatial predictive mapping of mineral prospectivity: Automated hyperparameter tuning of random forest approach

Mehrdad Daviran et al.

Summary: This study proposed a hybrid genetic-based RF model that automatically adjusts the hyperparameters of RF with excellent predictive accuracy. By comparing the proposed GRF model with traditional RF using authentic validation measures, it was found that the GRF model outperformed RF in accuracy.

COMPUTERS & GEOSCIENCES (2021)

Add to Collection

Article Geochemistry & Geophysics

Using logistic regression model selection towards interpretable machine learning in mineral prospectivity modeling

Samuel Kost et al.

Summary: Regression models are commonly used in mineral prospectivity modeling, with logistic regression providing a well understood statistical foundation and newly proposed model selection procedures. The comparison shows performance similar to neural networks but with faster speed and fewer variables selected. The explicit model in logistic regression can aid in the model building process and bridge the gap between statistical and machine learning methods.

GEOCHEMISTRY (2021)

Add to Collection

Article Geosciences, Multidisciplinary

Data-driven Mineral Prospectivity Mapping by Joint Application of Unsupervised Convolutional Auto-encoder Network and Supervised Convolutional Neural Network

Shuai Zhang et al.

Summary: This study tested the efficacy of using an unsupervised convolutional auto-encoder network (CAE) to support convolutional neural network (CNN) modeling for data-driven mineral prospectivity mapping by synthesizing multi-geoinformation. The results demonstrated the potential of this approach for accurately mapping prospective and non-prospective areas, with strong spatial correlation observed between CNN modeling results and known Au deposits in the study area.

NATURAL RESOURCES RESEARCH (2021)

Add to Collection

Article Geology

Mineral prospectivity mapping by deep learning method in Yawan-Daqiao area, Gansu

Yongyang Xu et al.

Summary: Mineral prospectivity mapping, utilizing multi-source geological data for probability prediction, was enhanced in this study with the use of a deep regression neural network. The neural network learned expert knowledge in mineral prospectivity mapping, did not require classified samples, and could be applied for predicting and evaluating mineral resources.

ORE GEOLOGY REVIEWS (2021)

Add to Collection

Article Geochemistry & Geophysics

A Comparative Study of Machine Learning Models with Hyperparameter Optimization Algorithm for Mapping Mineral Prospectivity

Nan Lin et al.

Summary: The study utilized the bat algorithm and firefly algorithm in combination with different machine learning models for mineral prospectivity mapping, demonstrating significant improvements in model accuracy.

MINERALS (2021)

Add to Collection

Article Geosciences, Multidisciplinary

Regional-Scale Mineral Prospectivity Mapping: Support Vector Machines and an Improved Data-Driven Multi-criteria Decision-Making Technique

Reza Ghezelbash et al.

Summary: Mapping mineral prospectivity is plagued by stochastic and systemic uncertainties, with this study focusing on reducing the latter for Cu-Au mineralization in NE Iran. By introducing efficient evidence layers and a data-driven SAW procedure, the study successfully delineated favorable exploration targets. Comparison with a SVM model showed that SVM was more reliable in predicting high-potential areas of mineralization.

NATURAL RESOURCES RESEARCH (2021)

Add to Collection

Article Geochemistry & Geophysics

Supervised mineral exploration targeting and the challenges with the selection of deposit and non-deposit sites thereof

Hossain Rahimi et al.

Summary: The study investigated the impact of changing the number of non-deposit sites on exploration targeting models and emphasized the importance of balancing the number of deposit and non-deposit sites for creating more reliable exploration targets.

APPLIED GEOCHEMISTRY (2021)

Add to Collection

Article Geosciences, Multidisciplinary

Mapping gold mineral prospectivity based on weights of evidence method in southeast Asmara, Eritrea

Changliang Fu et al.

Summary: Eritrea in Northeast Africa has many gold deposits, and the weights of evidence method is important in mapping gold mineral prospectivity, identifying gold occurrence types and ore-controlling factors. The study suggests that further mineral exploration in the Ewanet area is worthwhile based on the identified prospectivity areas.

JOURNAL OF AFRICAN EARTH SCIENCES (2021)

Add to Collection

Article Geology

Recognition of multivariate geochemical anomalies associated with mineralization using an improved generative adversarial network

Chunjie Zhang et al.

Summary: In this study, the ALAD algorithm, which combines the advantages of deep variational autoencoder and generative adversarial network, significantly improved the detection performance of geochemical anomalies. By conducting experiments to identify geochemical anomalies related to mineralization, a well-designed network structure was able to achieve high spatial consistency with discovered mineralization locations.

ORE GEOLOGY REVIEWS (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Impact of Hyperparameter Tuning in Classifying Highly Imbalanced Big Data

John Hancock et al.

Summary: The study shows that investing in computing resources for hyperparameter tuning pays off, especially when dealing with highly imbalanced Big Data. By comparing default and tuned hyperparameter values of CatBoost and LightGBM classifiers, it is found that tuned values result in better performance.

2021 IEEE 22ND INTERNATIONAL CONFERENCE ON INFORMATION REUSE AND INTEGRATION FOR DATA SCIENCE (IRI 2021) (2021)

Add to Collection

Article Engineering, Electrical & Electronic

Short-Term Load Forecasting for Industrial Customers Based on TCN-LightGBM

Yuanyuan Wang et al.

Summary: This paper proposes a short-term load forecasting model for industrial customers based on Temporal Convolutional Network (TCN) and Light Gradient Boosting Machine (LightGBM), which is demonstrated to provide accurate load forecasting results through experiments and comparisons with existing models.

IEEE TRANSACTIONS ON POWER SYSTEMS (2021)

Add to Collection

Article Geosciences, Multidisciplinary

Assessment of Various Fuzzy c-Mean Clustering Validation Indices for Mapping Mineral Prospectivity: Combination of Multifractal Geochemical Model and Mineralization Processes

Mehrdad Daviran et al.

NATURAL RESOURCES RESEARCH (2020)

Add to Collection

Article Geochemistry & Geophysics

Geodata science and geochemical mapping

Renguang Zuo et al.

JOURNAL OF GEOCHEMICAL EXPLORATION (2020)

Add to Collection

Article Environmental Sciences

Deep learning in environmental remote sensing: Achievements and challenges

Qiangqiang Yuan et al.

REMOTE SENSING OF ENVIRONMENT (2020)

Add to Collection

Article Geology

Sensitivity analysis of prospectivity modeling to evidence maps: Enhancing success of targeting for epithermal gold, Takab district, NW Iran

Reza Ghezelbash et al.

ORE GEOLOGY REVIEWS (2020)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Recognizing multivariate geochemical anomalies for mineral exploration by combining deep learning and one-class support vector machine

Yihui Xiong et al.

COMPUTERS & GEOSCIENCES (2020)

Add to Collection

Article Radiology, Nuclear Medicine & Medical Imaging

Dense-UNet: a novel multiphoton in vivo cellular image segmentation model based on a convolutional neural network

Sijing Cai et al.

QUANTITATIVE IMAGING IN MEDICINE AND SURGERY (2020)

Add to Collection

Review Geosciences, Multidisciplinary

Deep learning and its application in geochemical mapping

Renguang Zuo et al.

EARTH-SCIENCE REVIEWS (2019)

Add to Collection

Article Geochemistry & Geophysics

A Bat-Optimized One-Class Support Vector Machine for Mineral Prospectivity Mapping

Yongliang Chen et al.

MINERALS (2019)

Add to Collection

Article Mathematical & Computational Biology

A LightGBM-Based EEG Analysis Method for Driver Mental States Classification

Hong Zeng et al.

COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE (2019)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Performance evaluation of RBF- and SVM-based machine learning algorithms for predictive mineral prospectivity modeling: integration of S-A multifractal model and mineralization controls

Reza Ghezelbash et al.

EARTH SCIENCE INFORMATICS (2019)

Add to Collection

Article Geosciences, Multidisciplinary

An Improved Data-Driven Multiple Criteria Decision-Making Procedure for Spatial Modeling of Mineral Prospectivity: Adaption of Prediction-Area Plot and Logistic Functions

Reza Ghezelbash et al.

NATURAL RESOURCES RESEARCH (2019)

Add to Collection

Proceedings Paper Telecommunications

Research on Short-term Load Forecasting Using XGBoost Based on Similar Days

Liao Xiaoqun et al.

2019 INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION, BIG DATA & SMART CITY (ICITBS) (2019)

Add to Collection

Article Geochemistry & Geophysics

Prospectivity modeling of porphyry copper deposits: recognition of efficient mono- and multi-element geochemical signatures in the Varzaghan district, NW Iran

Reza Ghezelbash et al.

ACTA GEOCHIMICA (2019)

Add to Collection

Article Geosciences, Multidisciplinary

A hybrid AHP-VIKOR approach for prospectivity modeling of porphyry Cu deposits in the Varzaghan District, NW Iran

Reza Ghezelbash et al.

ARABIAN JOURNAL OF GEOSCIENCES (2018)

Add to Collection

Article Chemistry, Multidisciplinary

Automated Classification Analysis of Geological Structures Based on Images Data and Deep Learning Model

Ye Zhang et al.

APPLIED SCIENCES-BASEL (2018)

Add to Collection

Article Geosciences, Multidisciplinary

Application of fuzzy logic and fuzzy AHP to mineral prospectivity mapping of porphyry and hydrothermal vein copper deposits in the Dananhu-Tousuquan island arc, Xinjiang, NW China

Nannan Zhang et al.

JOURNAL OF AFRICAN EARTH SCIENCES (2017)

Add to Collection

Article Mathematical & Computational Biology

Deep Learning for Plant Identification in Natural Environment

Yu Sun et al.

COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE (2017)

Add to Collection

Article Geosciences, Multidisciplinary

Mapping mineral prospectivity by using one-class support vector machine to identify multivariate geological anomalies from digital geological survey data

Y. Chen et al.

AUSTRALIAN JOURNAL OF EARTH SCIENCES (2017)

Add to Collection

Article Geochemistry & Geophysics

Carbonate-hosted nonsulphide Zn-Pb mineralization of southern British Columbia, Canada

Suzanne Paradis et al.

MINERALIUM DEPOSITA (2015)

Add to Collection

Article Geology

Data-driven predictive mapping of gold prospectivity, Baguio district, Philippines: Application of Random Forests algorithm

Emmanuel John M. Carranza et al.

ORE GEOLOGY REVIEWS (2015)

Add to Collection

Article Computer Science, Interdisciplinary Applications

A method for mineral prospectivity mapping integrating C4.5 decision tree, weights-of-evidence and m-branch smoothing techniques: a case study in the eastern Kunlun Mountains, China

Cuihua Chen et al.

EARTH SCIENCE INFORMATICS (2014)

Add to Collection

Article Geosciences, Multidisciplinary

Interpretation of Na-Cl-Br Systematics in Sedimentary Basin Brines: Comparison of Concentration, Element Ratio, and Isometric Log-ratio Approaches

Mark A. Engle et al.

MATHEMATICAL GEOSCIENCES (2013)

Add to Collection

Review Geology

Recognition of the regional lineaments of Iran: Using geospatial data and their implications for exploration of metallic ore deposits

Seyed Ahmad Meshkani et al.

ORE GEOLOGY REVIEWS (2013)

Add to Collection

Article Geology

Metallogeny of Cretaceous carbonate-hosted Zn-Pb deposits of Iran: geotectonic setting and data integration for future mineral exploration

Abdorrahman Rajabi et al.

INTERNATIONAL GEOLOGY REVIEW (2012)

Add to Collection

Review Geochemistry & Geophysics

Exploring the effects of cell size in geochemical mapping

Renguang Zuo

JOURNAL OF GEOCHEMICAL EXPLORATION (2012)

Add to Collection

Article Environmental Sciences

The concept of compositional data analysis in practice - Total major element concentrations in agricultural and grazing land soils of Europe

Clemens Reimann et al.

SCIENCE OF THE TOTAL ENVIRONMENT (2012)

Add to Collection

Article Computer Science, Interdisciplinary Applications

A spatially weighted principal component analysis for multi-element geochemical data for mapping locations of felsic intrusions in the Gejiu mineral district of Yunnan, China

Qiuming Cheng et al.

COMPUTERS & GEOSCIENCES (2011)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Support vector machine: A tool for mapping mineral prospectivity

Renguang Zuo et al.

COMPUTERS & GEOSCIENCES (2011)

Add to Collection

Article Geosciences, Multidisciplinary

A Modified Weights-of-Evidence Method for Regional Mineral Resource Estimation

Frits Agterberg

Natural Resources Research (2011)

Add to Collection

Article Geosciences, Multidisciplinary

Emarat carbonate-hosted Zn-Pb deposit, Markazi Province, Iran: A geological, mineralogical and isotopic (S, Pb) study

Farhad Ehya et al.

JOURNAL OF ASIAN EARTH SCIENCES (2010)

Add to Collection

Article Remote Sensing

Knowledge-guided data-driven evidential belief modeling of mineral prospectivity in Cabo de Gata, SE Spain

E. J. M. Carranza et al.

INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION (2008)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Finding the right pixel size

Tomislav Hengl

COMPUTERS & GEOSCIENCES (2006)

Add to Collection

Article Computer Science, Artificial Intelligence

Random forests

L Breiman

MACHINE LEARNING (2001)

Add to Collection

Article Geosciences, Multidisciplinary

Artificial neural networks: a new method for mineral prospectivity mapping

WM Brown et al.

AUSTRALIAN JOURNAL OF EARTH SCIENCES (2000)

Add to Collection

© Peeref 2019-2024. All rights reserved.