Application of neural networks to predict net present value in mining projects

Sayadi, Ahmad Reza; Tavassoli, Sara; Monjezi, Masoud; Rezaei, Mohammad

doi:10.1007/s12517-012-0750-z

Cited by 32 publications

(19 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To compute the output, a function, which is often a sigmoid function, was used in the hidden layers (Sayadi et al . ). The network had to be trained to check the relation between parameters.…”

Section: Methodsmentioning

confidence: 97%

See 1 more Smart Citation

Investigating the applicability of induced polarization method in ore modelling and drilling optimization: a case study from Abassabad, Iran

Mostafaei

Ramazi

2019

Near Surface Geophysics

View full text Add to dashboard Cite

The main issue in mineral exploration is to obtain as much information as possible in a time‐ and cost‐efficient manner. This may be achieved through a combination of geophysical methods including the induced polarization method. The induced polarization is the most applicable method in case of metal exploration through drilling. We argue that the relationship between induced polarization, electrical resistivity and ore grade data may be used in resource estimation. This argument is tested in the active copper mine of Madan Bozorg, Abassabad, which is located in the Miami‐Sabzevar mineralization belt in NW Iran. Within the borehole locations, geophysical profiles of induced polarization and electrical resistivity were designed and surveyed using combined resistivity sounding and profiling array. Two‐dimensional models of induced polarization and electrical resistivity were prepared through inversion of geophysical data, after the primary processing. The three‐dimensional block models of induced polarization and electrical resistivity were also compiled using geostatistical methods. Obtained two‐dimensional and three‐dimensional models of induced polarization and electrical resistivity were checked using exploratory boreholes to investigate the relationship among induced polarization, electrical resistivity and copper grade. The three‐dimensional block model of the copper ore was prepared using cokriging and artificial neural network, using a combination of induced polarization and drilling data. In the cases where borehole data were unavailable, the presence of copper ore was predicted by artificial neural network and cokriging methods, and the three‐dimensional models of ore body were constructed in all of the study area. Obtained models based on the predicted copper ore distribution were checked and compared with ore distribution model compiled using drilling data. The results indicate a good agreement between predicted and real results. This led to reduction of borehole number to about 45% and the optimization of boreholes locations. Finally, an optimized drilling plan has been prepared and presented for the Abassabad copper mine.

show abstract

Section: Methodsmentioning

confidence: 97%

“…So, the output results are a combination of input, weights, biases and hidden layers. To compute the output, a function, which is often a sigmoid function, was used in the hidden layers (Sayadi et al 2012). The network had to be trained to check the relation between parameters.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Investigating the applicability of induced polarization method in ore modelling and drilling optimization: a case study from Abassabad, Iran

Mostafaei

Ramazi

2019

Near Surface Geophysics

View full text Add to dashboard Cite

show abstract

“…The cosine amplitude method (CAM) was used here [62][63][64]. In this method, all of the data pairs are expressed in common X-space.…”

Section: Sensitivity Analysismentioning

confidence: 99%

Prediction of representative deformation modulus of longwall panel roof rock strata using Mamdani fuzzy system

Rezaei

Asadizadeh

Majdi

et al. 2015

International Journal of Mining Science and Technology

View full text Add to dashboard Cite

a b s t r a c tDeformation modulus is the important parameter in stability analysis of tunnels, dams and mining structures. In this paper, two predictive models including Mamdani fuzzy system (MFS) and multivariable regression analysis (MVRA) were developed to predict deformation modulus based on data obtained from dilatometer tests carried out in Bakhtiary dam site and additional data collected from longwall coal mines. Models inputs were considered to be rock quality designation, overburden height, weathering, unconfined compressive strength, bedding inclination to core axis, joint roughness coefficient and fill thickness. To control the models performance, calculating indices such as root mean square error (RMSE), variance account for (VAF) and determination coefficient (R 2 ) were used. The MFS results show the significant prediction accuracy along with high performance compared to MVRA results. Finally, the sensitivity analysis of MFS results shows that the most and the least effective parameters on deformation modulus are weathering and overburden height, respectively.

show abstract

“…Pao [11] states that artificial neural networks are nowadays used to solve possible future obstacles, especially for the forecasting of values. According to Sayadi et al [12], the main advantages of ANNs are the ability to generalize and the ability to learn. The main disadvantages of ANNs, according to the Rowland and Vrbka [13], include the possibility of illogical network behaviour and that they demand very high-quality data.…”

Section: Introductionmentioning

confidence: 99%

Machine learning forecasting of USA and PRC balance of trade in context of mutual sanctions

2020

View full text Add to dashboard Cite

The USA decided to regulate the trade more by imposing tariffs on specific types of traded goods. It is therefore more interesting to find out whether the current technologies based on artificial intelligence with time series influenced by extraordinary factors such as the trade war between two powers are able to work. The objective of the contribution is to examine and subsequently equalize two time series – the USA import from the PRC and the USA export to the PRC. The dataset shows the course of the time series at monthly intervals between January 2000 and July 2019. 10,000 multilayer perceptron networks (MLP) are generated, out of which 5 with the best characteristics are retained. It has been proved that multilayer perceptron networks are a suitable tool for forecasting the development of the time series if there are no sudden fluctuations. Mutual sanctions of both states did not affect the result of machine learning forecasting.

show abstract

Application of neural networks to predict net present value in mining projects

Cited by 32 publications

References 34 publications

Investigating the applicability of induced polarization method in ore modelling and drilling optimization: a case study from Abassabad, Iran

Investigating the applicability of induced polarization method in ore modelling and drilling optimization: a case study from Abassabad, Iran

Prediction of representative deformation modulus of longwall panel roof rock strata using Mamdani fuzzy system

Machine learning forecasting of USA and PRC balance of trade in context of mutual sanctions

Contact Info

Product

Resources

About