A data mining approach to validating drill hole logging data in Pilbara iron ore exploration

Daniel Wedge, Andrew Lewan, Mark Paine, Eun Jung Holden, Thomas Green

Research output: Contribution to journalArticle

1 Citation (Scopus)
96 Downloads (Pure)

Abstract

Logging of exploration drill holes is a routine practice, and its accuracy is essential for resource evaluation and planning in the minerals industry. Logged compositions record a set of material types with standardized mineralogy and texture characteristics. The material types logged may vary due to diversity in mineralization and geology, but also due to subjective biases and human error, leading to significant challenges for the industry. Thus, there is a need to validate the field logging whereby the material types and their percentages are adjusted to reconcile with laboratory assay values while retaining the physical characteristics and geologic context. We introduce the auto-validation assistant (AVA) algorithm, which applies data mining methods to geologists' validation patterns recorded in a training process over hundreds of intervals of iron ore exploration drill holes. The AVA modifies the material types selected in the logged composition and their percentages according to geologic rules learned in the training process and proposes to the geologist a number of validated compositions with optimized geochemistry and mineralogical hardness, while also considering visible properties such as chip shape and color. Using the confidence value provided with each validated composition, the geologist can make informed validation decisions and remains in control of the validation process, while harnessing computational power. Experiments were conducted to evaluate the autovalidated compositions generated by AVA: one to analyze the acceptance rate of the AVA-generated compositions by geologists for 1,996 intervals in drill holes from different sites, and the other to compare manual and AVA-validated compositions using 14,600 drill holes from one entire deposit. The results showed the acceptance rate of AVA-validated compositions (without further change) of 74.3%, leading to significant time savings over tedious manual validation, while demonstrating that AVA provides comparable but more consistent results. The algorithm is fast and repeatable and can be adapted to different material types and training datasets, with potential applications beyond iron ore exploration.

Original languageEnglish
Pages (from-to)961-972
Number of pages12
JournalEconomic Geology
Volume113
Issue number4
DOIs
Publication statusPublished - 1 Jun 2018

Fingerprint

iron ores
data mining
Iron ores
iron ore
Data mining
Chemical analysis
minerals industry
education
hardness
acceptability
savings
mineralogy
texture
geochemistry
Geochemistry
Mineralogy
geology
material
assay
mineralization

Cite this

Wedge, Daniel ; Lewan, Andrew ; Paine, Mark ; Holden, Eun Jung ; Green, Thomas. / A data mining approach to validating drill hole logging data in Pilbara iron ore exploration. In: Economic Geology. 2018 ; Vol. 113, No. 4. pp. 961-972.
@article{c3123aab91e542d39ce9be4a5a95a7b8,
title = "A data mining approach to validating drill hole logging data in Pilbara iron ore exploration",
abstract = "Logging of exploration drill holes is a routine practice, and its accuracy is essential for resource evaluation and planning in the minerals industry. Logged compositions record a set of material types with standardized mineralogy and texture characteristics. The material types logged may vary due to diversity in mineralization and geology, but also due to subjective biases and human error, leading to significant challenges for the industry. Thus, there is a need to validate the field logging whereby the material types and their percentages are adjusted to reconcile with laboratory assay values while retaining the physical characteristics and geologic context. We introduce the auto-validation assistant (AVA) algorithm, which applies data mining methods to geologists' validation patterns recorded in a training process over hundreds of intervals of iron ore exploration drill holes. The AVA modifies the material types selected in the logged composition and their percentages according to geologic rules learned in the training process and proposes to the geologist a number of validated compositions with optimized geochemistry and mineralogical hardness, while also considering visible properties such as chip shape and color. Using the confidence value provided with each validated composition, the geologist can make informed validation decisions and remains in control of the validation process, while harnessing computational power. Experiments were conducted to evaluate the autovalidated compositions generated by AVA: one to analyze the acceptance rate of the AVA-generated compositions by geologists for 1,996 intervals in drill holes from different sites, and the other to compare manual and AVA-validated compositions using 14,600 drill holes from one entire deposit. The results showed the acceptance rate of AVA-validated compositions (without further change) of 74.3{\%}, leading to significant time savings over tedious manual validation, while demonstrating that AVA provides comparable but more consistent results. The algorithm is fast and repeatable and can be adapted to different material types and training datasets, with potential applications beyond iron ore exploration.",
author = "Daniel Wedge and Andrew Lewan and Mark Paine and Holden, {Eun Jung} and Thomas Green",
year = "2018",
month = "6",
day = "1",
doi = "10.5382/econgeo.2018.4578",
language = "English",
volume = "113",
pages = "961--972",
journal = "Economic Geology",
issn = "0361-0128",
publisher = "Society of Economic Geologists",
number = "4",

}

A data mining approach to validating drill hole logging data in Pilbara iron ore exploration. / Wedge, Daniel; Lewan, Andrew; Paine, Mark; Holden, Eun Jung; Green, Thomas.

In: Economic Geology, Vol. 113, No. 4, 01.06.2018, p. 961-972.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A data mining approach to validating drill hole logging data in Pilbara iron ore exploration

AU - Wedge, Daniel

AU - Lewan, Andrew

AU - Paine, Mark

AU - Holden, Eun Jung

AU - Green, Thomas

PY - 2018/6/1

Y1 - 2018/6/1

N2 - Logging of exploration drill holes is a routine practice, and its accuracy is essential for resource evaluation and planning in the minerals industry. Logged compositions record a set of material types with standardized mineralogy and texture characteristics. The material types logged may vary due to diversity in mineralization and geology, but also due to subjective biases and human error, leading to significant challenges for the industry. Thus, there is a need to validate the field logging whereby the material types and their percentages are adjusted to reconcile with laboratory assay values while retaining the physical characteristics and geologic context. We introduce the auto-validation assistant (AVA) algorithm, which applies data mining methods to geologists' validation patterns recorded in a training process over hundreds of intervals of iron ore exploration drill holes. The AVA modifies the material types selected in the logged composition and their percentages according to geologic rules learned in the training process and proposes to the geologist a number of validated compositions with optimized geochemistry and mineralogical hardness, while also considering visible properties such as chip shape and color. Using the confidence value provided with each validated composition, the geologist can make informed validation decisions and remains in control of the validation process, while harnessing computational power. Experiments were conducted to evaluate the autovalidated compositions generated by AVA: one to analyze the acceptance rate of the AVA-generated compositions by geologists for 1,996 intervals in drill holes from different sites, and the other to compare manual and AVA-validated compositions using 14,600 drill holes from one entire deposit. The results showed the acceptance rate of AVA-validated compositions (without further change) of 74.3%, leading to significant time savings over tedious manual validation, while demonstrating that AVA provides comparable but more consistent results. The algorithm is fast and repeatable and can be adapted to different material types and training datasets, with potential applications beyond iron ore exploration.

AB - Logging of exploration drill holes is a routine practice, and its accuracy is essential for resource evaluation and planning in the minerals industry. Logged compositions record a set of material types with standardized mineralogy and texture characteristics. The material types logged may vary due to diversity in mineralization and geology, but also due to subjective biases and human error, leading to significant challenges for the industry. Thus, there is a need to validate the field logging whereby the material types and their percentages are adjusted to reconcile with laboratory assay values while retaining the physical characteristics and geologic context. We introduce the auto-validation assistant (AVA) algorithm, which applies data mining methods to geologists' validation patterns recorded in a training process over hundreds of intervals of iron ore exploration drill holes. The AVA modifies the material types selected in the logged composition and their percentages according to geologic rules learned in the training process and proposes to the geologist a number of validated compositions with optimized geochemistry and mineralogical hardness, while also considering visible properties such as chip shape and color. Using the confidence value provided with each validated composition, the geologist can make informed validation decisions and remains in control of the validation process, while harnessing computational power. Experiments were conducted to evaluate the autovalidated compositions generated by AVA: one to analyze the acceptance rate of the AVA-generated compositions by geologists for 1,996 intervals in drill holes from different sites, and the other to compare manual and AVA-validated compositions using 14,600 drill holes from one entire deposit. The results showed the acceptance rate of AVA-validated compositions (without further change) of 74.3%, leading to significant time savings over tedious manual validation, while demonstrating that AVA provides comparable but more consistent results. The algorithm is fast and repeatable and can be adapted to different material types and training datasets, with potential applications beyond iron ore exploration.

UR - http://www.scopus.com/inward/record.url?scp=85047348436&partnerID=8YFLogxK

U2 - 10.5382/econgeo.2018.4578

DO - 10.5382/econgeo.2018.4578

M3 - Article

VL - 113

SP - 961

EP - 972

JO - Economic Geology

JF - Economic Geology

SN - 0361-0128

IS - 4

ER -