Mineral Systems Analysis and Artificial Neural Network Modeling of Chromite Prospectivity in the Western Limb of the Bushveld Complex, South Africa

Tessema, Abera

doi:10.1007/s11053-017-9344-5

Cited by 39 publications

(16 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this layer, it obtains knowledge of previous nodes and performs computations using encoded by weights and yield net input. Subsequently, the net input has been processed to the output layer through an activation function [62]. In the output layer, it has received the previous process information from the hidden layer(s) and computes the desired output with less error and more accurate.…”

Section: Artificial Neural Network (Ann)mentioning

confidence: 99%

See 1 more Smart Citation

Toward a State-of-the-Art of Fly-Rock Prediction Technology in Open-Pit Mines Using EANNs Model

et al. 2019

View full text Add to dashboard Cite

Fly-rock induced by blasting is an undesirable phenomenon in quarries. It can be dangerous for humans, equipment, and buildings. To minimize its undesirable hazards, we proposed a state-of-the-art technology of fly-rock prediction based on artificial neural network (ANN) models and their robust combination, called EANNs model (ensemble of ANN models); 210 fly-rock events were recorded to develop and test the ANN and EANNs models. Of thi sample, 80% of the whole dataset was assigned to develop the models, the remaining 20% was assigned to confirm the models developed. Accordingly, five ANN models were designed and developed using the training dataset (i.e., 80% of the whole original data) first; then, their predictions on the training dataset were ensembled to generate a new training dataset. Subsequently, another ANN model was developed based on the new set of training data (i.e., EANNs model). Its performance was evaluated through a variety of performance indices, such as MAE (mean absolute error), MAPE (mean absolute percentage error), RMSE (root-mean-square error), R2 (correlation coefficient), and VAF (variance accounted for). A promising result was found for the proposed EANNs model in predicting blast-induced fly-rock with a MAE = 2.777, MAPE = 0.017, RMSE = 4.346, R2 = 0.986, and VAF = 98.446%. To confirm the performance of the proposed EANNs model, another ANN model with the same structure was developed and tested on the training and testing datasets. The findings also indicated that the proposed EANNs model yielded better performance than those of the ANN model with the same structure.

show abstract

Section: Artificial Neural Network (Ann)mentioning

confidence: 99%

“…activation function [62]. In the output layer, it has received the previous process information from the hidden layer(s) and computes the desired output with less error and more accurate.…”

Section: Combination Of Multiple Ann Modelsmentioning

confidence: 99%

Toward a State-of-the-Art of Fly-Rock Prediction Technology in Open-Pit Mines Using EANNs Model

et al. 2019

View full text Add to dashboard Cite

show abstract

“…There are various types of ANNs which differ from each other based on the number of neurons, neuron interconnection, activation type and learning algorithm. They include multi-layer perception [39], the radial basis function link network ( [30], [11]), Recurrent Neural Network (RNN), adaptive resonance theory network [39], and probabilistic neural network (PNN) [40], [41], [42] and [43] In this study, PNN is used to predict potential petroleum areas. The PNN was chosen because of its ability to train at high speed and also for being able to produce high confidence levels for classification decisions, unlike other neural networks training paradigms.…”

Section: Artificial Neural Network (Ann)mentioning

confidence: 99%

“…The selection of equal number of both training and non-training sites is to allow the model to perform efficient classification based on the input predictor maps. This is significant in optimizing network performance during both training and classification phase [40].…”

Section: Artificial Neural Network Model Constructionmentioning

confidence: 99%

A Pre-exploration Technique for Mapping Petroleum Potential Areas Based on Induced Surface Alterations and Possible Traps

Ouko¹,

Mutua²,

Mwaniki³

2018

ujg

View full text Add to dashboard Cite

The process of determining hydrocarbon potential areas for exploration requires numerous extensive studies of both surface and subsurface structures. Analysis and good understanding of these structures and surface expressions related to hydrocarbon formation provides a basis for identifying petroleum traps. The existence of favorable subsurface conditions for petroleum accumulation is always dependent on surface manifestation of petroleum traps. Identifying these areas prior to exploration allows for proper planning of seismic works so as to focus exploration and resources on relatively small areas. The main objective of this study was to locate and map petroleum potential areas in parts of Turkana by integrating spatial data derived from geology, gravity and remote sensing. Six predictor maps were developed including; alteration, lineament density, residual gravity anomaly, proximity to fault, lithology and regional gravity anomaly. The maps were analyzed using Artificial Neural Network (ANN) model to generate petroleum potential map. The map was further classified to high, moderate and low potential zones. The final petroleum potential map was validated by 9 existing wells that were not used in training. The final map demarcated an area of 8,994.41 Km 2 equivalent to 55.9% of the total study area as high potential.

show abstract

“…In recent years, artificial intelligence (AI) has become more popular and widely applied in many different fields. Review of literature showed that AI had been involved in many aspects such as mineralizing geochemical anomalies [33][34][35], optimizing operational mine planning [36], civil engineering [37,38], analyzing mineral systems [39], mineral potential mapping [40,41], resourcing future generations [42,43], predicting blast-induced problems [44][45][46][47]. In predicting blast-induced PPV, the feasibility of a support vector machine (SVM) algorithm was studied and applied by Hasanipanah et al [7] to predict blast-induced PPV in Bakhtiari Dam, Iran.…”

Section: Introductionmentioning

confidence: 99%

Support vector regression approach with different kernel functions for predicting blast-induced ground vibration: a case study in an open-pit coal mine of Vietnam

Nguyen

2019

SN Appl. Sci.

View full text Add to dashboard Cite

Blast-induced ground vibration (PPV) is one of the effects of the hazard in open-pit mines. It can make vibration of the structure, instability of slope and bench, impact on underground water, and the surrounding residential. Therefore, the precise prediction of blast-induced PPV is needed to minimize undesirable effects on the surrounding environment. Also, one of the most important objectives of this study is to determine the site characteristics for the application of controlled blasting techniques. In this study, the support vector regression (SVR) approach was considered and developed for predicting blast-induced PPV in an open-pit coal mine (Vietnam) as a case study. Three forms of the equation include linear (L), polynomial (P), and radius basis function (RBF) were applied to develop the SVR models. For comparison purpose, an empirical technique was also referred to as estimate blast-induced PPV in this study on the same training dataset. A database with 181 blasting events was used for this aim. Performance indicators such as root-mean-square error (RMSE) and the coefficient of determination (R 2 ) were used to compare and evaluate the performance of the predictive models. The results showed that SVR was an effective approach for predicting blast-induced PPV in this study. Among three forms of the equation, the SVR model with RBF was the most superior model for predicting blast-induced PPV in this study with an RMSE of 0.396, R 2 of 0.924, and MAE of 0.135, whereas the empirical model only obtained performance with an RMSE of 0.856, R 2 of 0.643, and MAE of 0.575. This study provided an overview of the SVR approach in predicting blast-induced PPV. A comparison of different kernel functions for the selection of the SVR model is needed to find out the best model for predicting blast-induced PPV.

show abstract

Mineral Systems Analysis and Artificial Neural Network Modeling of Chromite Prospectivity in the Western Limb of the Bushveld Complex, South Africa

Cited by 39 publications

References 47 publications

Toward a State-of-the-Art of Fly-Rock Prediction Technology in Open-Pit Mines Using EANNs Model

Toward a State-of-the-Art of Fly-Rock Prediction Technology in Open-Pit Mines Using EANNs Model

A Pre-exploration Technique for Mapping Petroleum Potential Areas Based on Induced Surface Alterations and Possible Traps

Support vector regression approach with different kernel functions for predicting blast-induced ground vibration: a case study in an open-pit coal mine of Vietnam

Contact Info

Product

Resources

About