The integration of artificial neural networks and geostatistical 3D geological block modelling: A case study on a mineral sand deposit

A. B. Jalloh, K. Sasaki, Yaguba Jalloh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this research, an Artificial Neural Network model was developed to predict metal content from drillhole data using the back propagation algorithm. For validation purposes, results between the actual and predicted mineral grades were compared, and regression analysis of the compared results indicate that the predicted mineral grades were in close proximity to the actual grades. The validated model was used to predict mineral grades at unsampled locations in order to determine the feasibility of drilling in those areas. The optimum results obtained from the neural network were fed to geostatistical techniques for developing a geological 3D block model for mine design. The generalized data from the Neural Network show that Artificial Neural Networks can be used to complement exploration activities and is an effective approach for mineral reserve estimation without worrying about spatial variability or other assumptions.

Original languageEnglish
Title of host publicationProceedings of the 24th International Mining Congress of Turkey, IMCET 2015
EditorsMehmet Karadeniz, Mehtap Gulsun Kilic, Elif Torun Bilgic, Hakan Basarir, Oznur Onel
PublisherTMMOB Maden Muhendisleri Odasi
Pages257-263
Number of pages7
ISBN (Electronic)9786050107050
Publication statusPublished - Jan 1 2015
Event24th International Mining Congress of Turkey, IMCET 2015 - Antalya, Turkey
Duration: Apr 14 2015Apr 17 2015

Publication series

NameProceedings of the 24th International Mining Congress of Turkey, IMCET 2015

Other

Other24th International Mining Congress of Turkey, IMCET 2015
CountryTurkey
CityAntalya
Period4/14/154/17/15

Fingerprint

artificial neural network
Sand
Minerals
Deposits
Neural networks
sand
mineral
modeling
Backpropagation algorithms
back propagation
Regression analysis
Drilling
regression analysis
drilling
metal
Metals

All Science Journal Classification (ASJC) codes

  • Geotechnical Engineering and Engineering Geology

Cite this

Jalloh, A. B., Sasaki, K., & Jalloh, Y. (2015). The integration of artificial neural networks and geostatistical 3D geological block modelling: A case study on a mineral sand deposit. In M. Karadeniz, M. Gulsun Kilic, E. Torun Bilgic, H. Basarir, & O. Onel (Eds.), Proceedings of the 24th International Mining Congress of Turkey, IMCET 2015 (pp. 257-263). (Proceedings of the 24th International Mining Congress of Turkey, IMCET 2015). TMMOB Maden Muhendisleri Odasi.

The integration of artificial neural networks and geostatistical 3D geological block modelling : A case study on a mineral sand deposit. / Jalloh, A. B.; Sasaki, K.; Jalloh, Yaguba.

Proceedings of the 24th International Mining Congress of Turkey, IMCET 2015. ed. / Mehmet Karadeniz; Mehtap Gulsun Kilic; Elif Torun Bilgic; Hakan Basarir; Oznur Onel. TMMOB Maden Muhendisleri Odasi, 2015. p. 257-263 (Proceedings of the 24th International Mining Congress of Turkey, IMCET 2015).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Jalloh, AB, Sasaki, K & Jalloh, Y 2015, The integration of artificial neural networks and geostatistical 3D geological block modelling: A case study on a mineral sand deposit. in M Karadeniz, M Gulsun Kilic, E Torun Bilgic, H Basarir & O Onel (eds), Proceedings of the 24th International Mining Congress of Turkey, IMCET 2015. Proceedings of the 24th International Mining Congress of Turkey, IMCET 2015, TMMOB Maden Muhendisleri Odasi, pp. 257-263, 24th International Mining Congress of Turkey, IMCET 2015, Antalya, Turkey, 4/14/15.
Jalloh AB, Sasaki K, Jalloh Y. The integration of artificial neural networks and geostatistical 3D geological block modelling: A case study on a mineral sand deposit. In Karadeniz M, Gulsun Kilic M, Torun Bilgic E, Basarir H, Onel O, editors, Proceedings of the 24th International Mining Congress of Turkey, IMCET 2015. TMMOB Maden Muhendisleri Odasi. 2015. p. 257-263. (Proceedings of the 24th International Mining Congress of Turkey, IMCET 2015).
Jalloh, A. B. ; Sasaki, K. ; Jalloh, Yaguba. / The integration of artificial neural networks and geostatistical 3D geological block modelling : A case study on a mineral sand deposit. Proceedings of the 24th International Mining Congress of Turkey, IMCET 2015. editor / Mehmet Karadeniz ; Mehtap Gulsun Kilic ; Elif Torun Bilgic ; Hakan Basarir ; Oznur Onel. TMMOB Maden Muhendisleri Odasi, 2015. pp. 257-263 (Proceedings of the 24th International Mining Congress of Turkey, IMCET 2015).
@inproceedings{b677b611c39b4bf88765c76984d9a039,
title = "The integration of artificial neural networks and geostatistical 3D geological block modelling: A case study on a mineral sand deposit",
abstract = "In this research, an Artificial Neural Network model was developed to predict metal content from drillhole data using the back propagation algorithm. For validation purposes, results between the actual and predicted mineral grades were compared, and regression analysis of the compared results indicate that the predicted mineral grades were in close proximity to the actual grades. The validated model was used to predict mineral grades at unsampled locations in order to determine the feasibility of drilling in those areas. The optimum results obtained from the neural network were fed to geostatistical techniques for developing a geological 3D block model for mine design. The generalized data from the Neural Network show that Artificial Neural Networks can be used to complement exploration activities and is an effective approach for mineral reserve estimation without worrying about spatial variability or other assumptions.",
author = "Jalloh, {A. B.} and K. Sasaki and Yaguba Jalloh",
year = "2015",
month = "1",
day = "1",
language = "English",
series = "Proceedings of the 24th International Mining Congress of Turkey, IMCET 2015",
publisher = "TMMOB Maden Muhendisleri Odasi",
pages = "257--263",
editor = "Mehmet Karadeniz and {Gulsun Kilic}, Mehtap and {Torun Bilgic}, Elif and Hakan Basarir and Oznur Onel",
booktitle = "Proceedings of the 24th International Mining Congress of Turkey, IMCET 2015",

}

TY - GEN

T1 - The integration of artificial neural networks and geostatistical 3D geological block modelling

T2 - A case study on a mineral sand deposit

AU - Jalloh, A. B.

AU - Sasaki, K.

AU - Jalloh, Yaguba

PY - 2015/1/1

Y1 - 2015/1/1

N2 - In this research, an Artificial Neural Network model was developed to predict metal content from drillhole data using the back propagation algorithm. For validation purposes, results between the actual and predicted mineral grades were compared, and regression analysis of the compared results indicate that the predicted mineral grades were in close proximity to the actual grades. The validated model was used to predict mineral grades at unsampled locations in order to determine the feasibility of drilling in those areas. The optimum results obtained from the neural network were fed to geostatistical techniques for developing a geological 3D block model for mine design. The generalized data from the Neural Network show that Artificial Neural Networks can be used to complement exploration activities and is an effective approach for mineral reserve estimation without worrying about spatial variability or other assumptions.

AB - In this research, an Artificial Neural Network model was developed to predict metal content from drillhole data using the back propagation algorithm. For validation purposes, results between the actual and predicted mineral grades were compared, and regression analysis of the compared results indicate that the predicted mineral grades were in close proximity to the actual grades. The validated model was used to predict mineral grades at unsampled locations in order to determine the feasibility of drilling in those areas. The optimum results obtained from the neural network were fed to geostatistical techniques for developing a geological 3D block model for mine design. The generalized data from the Neural Network show that Artificial Neural Networks can be used to complement exploration activities and is an effective approach for mineral reserve estimation without worrying about spatial variability or other assumptions.

UR - http://www.scopus.com/inward/record.url?scp=84934300356&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84934300356&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84934300356

T3 - Proceedings of the 24th International Mining Congress of Turkey, IMCET 2015

SP - 257

EP - 263

BT - Proceedings of the 24th International Mining Congress of Turkey, IMCET 2015

A2 - Karadeniz, Mehmet

A2 - Gulsun Kilic, Mehtap

A2 - Torun Bilgic, Elif

A2 - Basarir, Hakan

A2 - Onel, Oznur

PB - TMMOB Maden Muhendisleri Odasi

ER -