Abstract
This paper presents a new machine learning feature extraction methodology for the identification of material transitions in a lateritic bauxite deposit using ground penetrating radar (GPR). This meth-odology allows for model results that quantitatively outperform typical feature extraction processes whilst providing qualitatively useful results. The geological domain in which this process was applied has a relatively large transition zone, which weakens the GPR characteristics that the typical feature extraction processes rely upon. While training on depth (92% accuracy), time and frequency (50–68% accuracy), wavelet decomposition (69% accuracy), and multi-signal fusion (50% accuracy) feature spaces produces results of varying quantitative success, all of them result in qualitatively poor results, often with results looking like white noise. Our proposed feature, Gaussian Ridge Extraction (GRE), achieves an accuracy of 83% while producing an estimate that is qualitatively reasonable. Combining GRE with a reduced set of features from the originally explored feature sets improves model accuracy to 87% and further strengthens the visual, qualitative estimate of the boundary transition.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Altın, C., Er, O.: Comparison of different time and frequency domain feature extraction methods on elbow gesture’s EMG. Eur. J. Interdisc. Stud. 2(3), 35–44 (2016)
Baili, J., Lahouar, S., Hergli, M., Amimi, A., Besbes, K.: Application of the discrete wavelet transform to denoise GPR signals. In: 2nd International Symposium on Communications, Control and Signal Processing, Marrakech, Morocco, p. 11 (2006)
Ball, A., O’Connor, L.: Geologist in the loop: a hybrid intelligence model for identifying geological boundaries from augmented ground penetrating radar. Geosciences 11(7), 284 (2021)
Bao, Q.-Z., Li, Q.-C., Chen, W.-C.: GPR data noise attenuation on the curvelet transform. Appl. Geophys. 11(3), 301–310 (2013). https://doi.org/10.1007/s11770-014-0444-2
Bhattacharya, A., Sarkar, A., Basak, P.: Time domain multi-feature extraction and classification of human hand movements using surface EMG. In: 2017 4th International Conference on Advanced Computing and Communication Systems (ICACCS), pp. 1–5. IEEE (2017)
Breiman, L.: Bagging predictors. Mach. Learn. 24(2), 123–140 (1996)
Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)
Dietterich, T.G.: An experimental comparison of three methods for constructing ensembles of decision trees: bagging, boosting, and randomization. Mach. Learn. 40(2), 139–157 (2000)
Erten, O., Kizil, M.S., Topal, E., McAndrew, L.: Spatial prediction of lateral variability of a laterite-type bauxite horizon using ancillary ground-penetrating radar data. Nat. Resour. Res. 22(3), 207–227 (2013)
Erten, O., McAndrew, L., Kizil, M.S., Topal, E.: Incorporating fine-scale ground-penetrating radar data into the mapping of lateral variability of a laterite-type bauxite horizon. Min. Technol. 124(1), 1–15 (2015)
Francke, J.: Applications of GPR in mineral resource evaluations. In: Proceedings of the XIII International Conference on Ground Penetrating Radar, pp. 1–5. IEEE (2010)
Francke, J.: A review of selected ground penetrating radar applications to mineral resource evaluations. J. Appl. Geophys. 81, 29–37 (2012)
Frigui, H., Gader, P.: Detection and discrimination of land mines in ground-penetrating radar based on edge histogram descriptors and a possibilistic \( k \)-nearest neighbor classifier. IEEE Trans. Fuzzy Syst. 17(1), 185–199 (2008)
Gow, N.N., Lozej, G.P.: Bauxite. Geoscience Canada (1993)
Ho, T.K.: Random decision forests. In: Proceedings of 3rd International Conference on Document Analysis and Recognition, vol. 1, pp. 278–282. IEEE (1995)
Khushaba, R., Phinyomark, A., Al-Timemy, A., Scheme, E.: Recursive multi-signal temporal fusions with attention mechanism improves EMG feature extraction. IEEE Trans. Artif. Intell. 1(2), 139–150 (2020). https://doi.org/10.1109/TAI.2020.3046160
Khushaba, R.N., Al-Ani, A., Al-Jumaily, A.: Differential evolution based feature subset selection. In: 2008 19th International Conference on Pattern Recognition, pp. 1–4. IEEE (2008)
Kim, K.S., Choi, H.H., Moon, C.S., Mun, C.W.: Comparison of k-nearest neighbor, quadratic discriminant and linear discriminant analysis in classification of electromyogram signals based on the wrist-motion directions. Curr. Appl. Phys. 11(3), 740–745 (2011)
Lotte, F.: A new feature and associated optimal spatial filter for EEG signal classification: waveform length. In: Proceedings of the 21st International Conference on Pattern Recognition (ICPR 2012), pp. 1302–1305. IEEE (2012)
Lundberg, S.M., Lee, S.I.: A unified approach to interpreting model predictions. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems 30, pp. 4765–4774. Curran Associates, Inc. (2017)
Morgan, M.: An investigation into the application of ground penetrating radar to the Weipa mining operation. Weipa, Comalco Minerals and Alumina (1995)
Narayan, Y., Mathew, L., Chatterji, S.: SEMG signal classification with novel feature extraction using different machine learning approaches. J. Intell. Fuzzy Syst. 35(5), 5099–5109 (2018)
Negi, S., Kumar, Y., Mishra, V.: Feature extraction and classification for EMG signals using linear discriminant analysis. In: 2016 2nd International Conference on Advances in Computing, Communication, and Automation (ICACCA) (Fall), pp. 1–6. IEEE (2016)
Phinyomark, A., Limsakul, C., Phukpattaranont, P.: A novel feature extraction for robust EMG pattern recognition. arXiv preprint arXiv:0912.3973 (2009)
Ralston, J.C., Strange, A.D.: An industrial application of ground penetrating radar for coal mining horizon sensing. In: 2015 International Symposium on Antennas and Propagation (ISAP), pp. 1–4. IEEE (2015)
Rio Tinto Group - Pacific Operations: Changes to Rio Tinto Aluminium Pacific Operations Ore Reserve and Mineral Resource Estimates, February 2021
Soltani, S., Hezarkhani, A.: Determination of realistic and statistical value of the information gathered from exploratory drilling. Nat. Resour. Res. 20(4), 207–216 (2011)
Talebi, S.: The wavelet transform. Towards Data Science (2020)
Taylor, G., Eggleton, R., Foster, L., Morgan, C.: Landscapes and regolith of Weipa, northern Australia. Aust. J. Earth Sci. 55(S1), S3–S16 (2008)
Travassos, X.L., Avila, S.L., Ida, N.: Artificial neural networks and machine learning techniques applied to ground penetrating radar: a review. Appl. Comput. Inform. (2020)
Zhang, D.: Wavelet Transform. In: Zhang, D. (ed.) Fundamentals of Image Data Mining. TCS, pp. 35–44. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-17989-2_3
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Fleming, O., Ball, A., Khushaba, R.N. (2022). Predicting Geological Material Types Using Ground Penetrating Radar. In: Long, G., Yu, X., Wang, S. (eds) AI 2021: Advances in Artificial Intelligence. AI 2022. Lecture Notes in Computer Science(), vol 13151. Springer, Cham. https://doi.org/10.1007/978-3-030-97546-3_22
Download citation
DOI: https://doi.org/10.1007/978-3-030-97546-3_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-97545-6
Online ISBN: 978-3-030-97546-3
eBook Packages: Computer ScienceComputer Science (R0)