Recurrent neural network approach to mineral deposit modelling

Singh, Rahul Kumar; Ray, Dipankar; Sarkar, B. C.

doi:10.1109/rait.2018.8389063

Cited by 11 publications

(6 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SVR uses a penalty term for evaluating the parameters of the model. It is possible to describe the objective function in its whole may be represented as Equation (9).…”

Section: Support Vector Regression (Svr)mentioning

confidence: 99%

“…Many studies have attempted to estimate the grade of various mineralizations by using multiple machine learning applications. For example, artificial neural networks (ANNs) [6][7][8][9], adaptive neuro fuzzy inference system (ANFIS) [10], random forest (RF) [11], and Gaussian process (GP) [11,12], support vector machines (SVM) [13,14] k-nearest neighbors (kNN) [15], and combined kNN-ANN methods [2] are the most popularly used algorithms. There have also been some studies that employ machine learning and deep learning approaches to identify the mineral grade and potential anomalies, according to the following publications: [16][17][18].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Approach for Resource Estimation of Highly Skewed Gold Using Machine Learning Algorithms

et al. 2022

View full text Add to dashboard Cite

With the complicated geology of vein deposits, their irregular and extremely skewed grade distribution, and the confined nature of gold, there is a propensity to overestimate or underestimate the ore grade. As a result, numerous estimation approaches for mineral resources have been developed. It was investigated in this study by using five machine learning algorithms to estimate highly skewed gold data in the vein-type at the Quartz Ridge region, including Gaussian Process Regression (GPR), Support Vector Regression (SVR), Decision Tree Ensemble (DTE), Fully Connected Neural Network (FCNN), and K-Nearest Neighbors (K-NN). The accuracy of MLA is compared to that of geostatistical approaches, such as ordinary and indicator kriging. Significant improvements were made during data preprocessing and splitting, ensuring that MLA was estimated accurately. The data were preprocessed with two normalization methods (z-score and logarithmic) to enhance network training performance and minimize substantial differences in the dataset’s variable ranges on predictions. The samples were divided into two equal subsets using an integrated data segmentation approach based on the Marine Predators Algorithm (MPA). The ranking shows that the GPR with logarithmic normalization is the most efficient method for estimating gold grade, far outperforming kriging techniques. In this study, the key to producing a successful mineral estimate is more than just the technique. It also has to do with how the data are processed and split.

show abstract

“…SVR uses a penalty term for evaluating the parameters of the model. It is possible to describe the objective function in its whole may be represented as Equation (9).…”

Section: Support Vector Regression (Svr)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Novel Approach for Resource Estimation of Highly Skewed Gold Using Machine Learning Algorithms

et al. 2022

View full text Add to dashboard Cite

show abstract

“…More recently, fuzzy uncertainties associated with geological data are being modeled with hybrid neural-fuzzy algorithms [74][75][76][77][78] to quantify uncertainties in evaluating mineral inventory parameters. Similar ANN-based mineral estimation models include Wavelet neural network (WNN) for copper deposit [79], recurrent neural network (RNN) for iron ore deposit [80], Kalman learning algorithm (modified back-propagation neural network) for lead (Pb), and zinc (Zn) deposit [81], local linear radial basis function (LLRBF) neural network for phosphate deposit [82], and radial basis function (RBF) network for offshore placer gold deposit [83,84]. Table 3 shows a summary of some ANN-based resource estimation models.…”

Section: Artificial Neural Network (Ann)mentioning

confidence: 99%

Machine Learning—A Review of Applications in Mineral Resource Estimation

Dumakor-Dupey

Arya

2021

Energies

View full text Add to dashboard Cite

Mineral resource estimation involves the determination of the grade and tonnage of a mineral deposit based on its geological characteristics using various estimation methods. Conventional estimation methods, such as geometric and geostatistical techniques, remain the most widely used methods for resource estimation. However, recent advances in computer algorithms have allowed researchers to explore the potential of machine learning techniques in mineral resource estimation. This study presents a comprehensive review of papers that have employed machine learning to estimate mineral resources. The review covers popular machine learning techniques and their implementation and limitations. Papers that performed a comparative analysis of both conventional and machine learning techniques were also considered. The literature shows that the machine learning models can accommodate several geological parameters and effectively approximate complex nonlinear relationships among them, exhibiting superior performance over the conventional techniques.

show abstract

“…The other researchers (Table 1) on the other hand did not clearly indicate the vein like nature of the deposit. However, some studies showed that their AI techniques were applied in heterogenous data sets (Samanta et al, 2004a;Jafrasteh et al, 2018;Gholamnejad et al, 2012;Tahmasebi and Hezarkhani, 2011;Badel et al, 2010;Tahmasebi and Hezarkhani, 2010b;Mahmoudabadi et al, 2008;Singh et al, 2018;Samanta et al, 2005b;Kapageridis, 2002;Wu and Zhou, 1993;Li et al, 2010;Kapageridis and Denby, 1998a;Al-Alawi and Tawo, 1998) which are common in vein deposits.…”

Section: Resources Usedmentioning

confidence: 99%

Assessment of Ore Grade Estimation Methods for Structurally Controlled Vein Deposits - A Review

Abuntori¹,

Al-Hassan²,

Mireku-Gyimah³

2021

View full text Add to dashboard Cite

Resource estimation techniques have upgraded over the past couple of years, thereby improving resource estimates. The classical method of estimation is less used in ore grade estimation than geostatistics (kriging) which proved to provide more accurate estimates by its ability to account for the geology of the deposit and assess error. Geostatistics has therefore been said to be superior over the classical methods of estimation. However, due to the complexity of using geostatistics in resource estimation, its time-consuming nature, the susceptibility to errors due to human interference, the difficulty in applying it to deposits with few data points and the difficulty in using it to estimate complicated deposits paved the way for the application of Artificial Intelligence (AI) techniques to be applied in ore grade estimation. AI techniques have been employed in diverse ore deposit types for the past two decades and have proven to provide comparable or better results than those estimated with kriging. This research aimed to review and compare the most commonly used kriging methods and AI techniques in ore grade estimation of complex structurally controlled vein deposits. The review showed that AI techniques outperformed kriging methods in ore grade estimation of vein deposits. Keywords: Artificial Intelligence, Neural Networks, Geostatistics, Kriging, Mineral Resource, Grade

show abstract

Recurrent neural network approach to mineral deposit modelling

Cited by 11 publications

References 4 publications

A Novel Approach for Resource Estimation of Highly Skewed Gold Using Machine Learning Algorithms

A Novel Approach for Resource Estimation of Highly Skewed Gold Using Machine Learning Algorithms

Machine Learning—A Review of Applications in Mineral Resource Estimation

Assessment of Ore Grade Estimation Methods for Structurally Controlled Vein Deposits - A Review

Contact Info

Product

Resources

About