Measure while drilling (MWD) data collected from production holes can provide information on the location of stratigraphic units in banded iron formation-hosted iron ore deposits. Stratigraphic modelling in these deposits is typically based on data from exploration holes, and adding more densely spaced production data can potentially increase model detail at the bench scale. Previous MWD classification methods struggle to differentiate between neighbouring ore units. In this paper, multivariate Gaussian Processes (GPs) were applied to locate the contact between two iron ore units in the Dales Gorge Member in the Brockman Iron Ore Formation. Production MWD points were then labelled based on the GP output. By altering parameters of the labelling process, 24.4–49.4% of the test data were labelled, with accuracies from 81.4 to 86.8%. Classifications from the same hole were compared to ensure MWD label consistency. The results demonstrate that the proposed method can improve geological unit classification from MWD data.
ArmstrongM, GalliA, BeucherH, Le Loc'hG, RenardD, DoligezB, EschardR, GeffroyF (2011). Plurigaussian simulations in geosciences. 2nd ed., Berlin Heidelberg: Springer-VerlagSage UK: London, England.
2.
BasarirH, KarpuzC.2016. Preliminary estimation of rock mass strength using diamond bit drilling operational parameters.Int J Mining, Reclama Environ. 30(2):145–164.
3.
BeattieNCM.2009. Monitoring-while-drilling for open-pit mining in a hard rock environment: An investigation of pattern recognition techniques applied to rock identification [master's thesis]. Department of Mining Engineering, Queen's University.
DalstraHJ, RosiereCA. Structural controls on high-grade iron ores hosted by banded iron formation: a global perspective. Littleton, CO: Society of Econimic Geologists, INC. (Reviews in Economic Geology; vol. 15), p. 73–106.
6.
De-VitryC, VannJ, ArvidsonH.2010. Multivariate iron ore deposit resource estimation – a practitioner's guide to selecting methods.Trans Inst Mining Metallurgy Sect B. 119(3):154–165.
7.
ErsoyA, WallerM.1995. Prediction of drill-bit performance using multivariable linear regression analysis.Trans Inst Mining Metallurgy Sect B. 104:A101–A114.
8.
FaliveneO, CabelloP, ArbuésP, MuñozJA, CabreraL.2009. A geostatistical algorithm to reproduce lateral gradual facies transitions: description and implementation.Comput Geosci. 35(8):1642–1651.
9.
HarmsworthRA, KneeshawM, MorrisRC, RobinsonCJ, ShrivastavaPK.1990. Bif-derived iron ores of the hamersley province, Melbourne.Australasian Inst Mining Metall. 1:617–642.
10.
HowarthD, AdamsonW, BerndtJ.1986. Correlation of model tunnel boring and drilling machine performances with rock properties.Int J Rock Mech Min Sci. 23:171–175.
11.
JonesH, WalravenF, KnottGG.1973. Natural gamma logging as an aid to iron ore exploration in the pilbara region of western australia. In: Australasian Institute of Mining and Metallurgy Annual Conference, Perth, Australia.
12.
KahramanS.2002. Correlation of tbm and drilling machine performances with rock brittleness.Eng Geol. 65:269–286.
13.
KirkpatrickS, GelattCDJr, VecchiMP.1983. Optimization by simulated annealing.Sciences. 220(4598):671–680.
14.
LaBelleD, BaresJ, NourbakhshI.2000. Material classification by drilling. Proceedings of the 17th International Symposium on Automation and Robotics in Construction. September, Taipei, Taiwan: International Association for Automation and Robotics in Construction (IAARC).
15.
LeungR, SchedingS.2015. Automated coal seam detection using a modulated specific energy measure in a monitor-while-drilling context.Int J Rock Mech Mining Sci. 75:196–209.
16.
MorrisRC.1993. Genetic modelling for banded iron-formation of the hamersley group, pilbara craton, western australia.Precambrian Res. 60:243–286.
17.
PaoneJ, BruceW, VirciglioP.1969. Drillability studies: Statistical regression analysis of diamond drilling. U.S. Dept. of the Interior, Bureau of Mines.
18.
PaoneJ, MadsonD.1966. Drillability studies: Impregnated diamond bits. Washington: U.S. Dept. of the Interior, Bureau of Mines.
19.
PasolliE, MelganiF, DonelliM.2010. Gaussian process approach to buried object size estimation in gpr images.IEEE Geosci Remote Sensing Lett. 7(1):141–145.
20.
RasmussenCE, WilliamsCKI. 2006. Gaussian processes for machine learning. Cambridge, MA: MIT PressSage UK: London, England.
21.
RostamiJ, KahramanS, NaeimipourA, CollinsC.2015. Rock characterization while drilling and application of roof bolter drilling data for evaluation of ground conditions.J Rock Mech Geotech Eng. 7:273–281.
22.
SilversidesKL, BallA, MelkumyanA.2019. Geological unit identification from measure while drilling data with multistep uncertainty and continuity based post-processing. In: IAMG2019.
23.
SilversidesK, MelkumyanA.2019. Multivariate Gaussian process for distinguishing geological units using measure while drilling data. In: Application of Computers and Operations Research in the Mineral Industry (APCOM), Poland.
24.
SilversidesKL, MelkumyanA.2017. Automatic analysis of measure while drilling data to facilitate manual boundary updates. In: IAMG2017.
25.
SilversidesKL, MelkumyanA.2018. Characterising measure while drilling data responses to changes in rock hardness. In: Hron K, Bábek O, Fišerová E, van den Boogaart R (eds), The 19th Annual Conference of the International Association for Mathematical Geosciences (IAMG2018), Olomouc, Czech Republic. p. 58–59.
26.
SilversidesKL, MelkumyanA.2020. Boundary identification and surface updates using mwd.Math Geosci. doi:10.1007/s11004-020-09891-0.
27.
TalebiH, AsghariO, EmeryX.2013. Application of plurigaussian simulation to delineate the layout of alteration domains in sungun copper deposit.Central Eur J Geosci. 5(4):514–522.
28.
TealeR.1965. The concept of specific energy in rock drilling.Int J Rock Mech Mining Sci. 2(1):57–73.
29.
ThorneW, HagemannS, WebbA, CloutJ (2008). Banded iron formation-related iron ore deposits of the hammersley province, western australia. Vol. 15, Westminster, CO: Society of Economic GeologistsSage UK: London, England. p. 197–221. $<$Go to ISI>$://WOS:000265047200005.
30.
TodoeschuckJP, JensenOG, LabonteS.1990. Gaussian scaling noise model of seismic reflection sequences: evidence from well logs.Geophysics. 55(4):480–484.
31.
TrendallAF, BlockleyJG.1968. Stratigraphy of the dales gorge member of the brockman iron formation, in the precambrian hamersley group of western australia. Western Australia Geological Survey. Report.
32.
TrendallAF, BlockleyJG.1970. The iron formations of the precambrian hamersley group, western australia with special reference to the associated crocidolite. Perth: Geological Survey of Western Australia. (Bulletin; vol. 119).
33.
UttWK.1999. Neural network technology for strata strength characterization. In: Neural Networks, 1999. International Joint Conference on IJCNN ‘99; vol. 6. p. 3806–3809.
34.
XuC, Torres-VerdínC.2013. Pore system characterization and petrophysical rock classification using a bimodal gaussian density function.Math Geosci. 45:753–771.
35.
YagizS.2008. Utilizing rock mass properties for predicting tbm performance in hard rock condition.Tunnelling Underground Space Technol. 23:326–339.
36.
ZhouH, HatherlyP, RamosF, NettletonE.2011. An adaptive data driven model for characterizing rock properties from drilling data. In: 2011 IEEE International Conference on Robotics and Automation (ICRA), Shanghai, China. p. 1909–1915.
