Classification of hydrothermal alteration types from thin section images using convolutional neural networks
Yıl 2024,
Cilt: 13 Sayı: 2, 528 - 539, 15.04.2024
Rıza Çenet
,
Emre Ünsal
,
Oktay Canbaz
Öz
Hydrothermal alteration is an important geological feature used in the exploration stages of precious minerals. This research focuses on two distinct deep-learning network structures created to identify hydrothermal alteration types in microscope images. A dataset of 2500 images, 70% of this data set was used to train, 20% to test, and 10% to measure the validity of the network. Convolutional Neural Network (CNN) and Xception models were trained using Adam, RMSprop and SGD optimization functions and the results are discussed. The Adam and SGD optimization functions for the CNN model performed the most successful classification with 96% accuracy. In the case of the Xception model, the highest accuracy value was 98% for the networks using the Adam and RMSprop optimization functions. Although the Xception model had higher accuracy values, it was observed that the CNN model completed the process significantly faster considering the training time of the network.
Kaynakça
- D. G. Tang, K. L. Milliken, ve K. T. Spikes, Machine learning for point counting and segmentation of arenite in thin section, Mar Pet Geol, 120, 2020. doi: https://doi.org/10.1016/j.marpetgeo.2020.104518.
- M. A. Abdelkader, Y. Watanabe, A. Shebl, H. A. El-Dokouny, M. Dawoud, and Á. Csámer, Effective delineation of rare metal-bearing granites from remote sensing data using machine learning methods: A case study from the Umm Naggat Area, Central Eastern Desert, Egypt, Ore Geol Rev, 150, 2022. https://doi.org/10.1016/j.oregeorev.2022.105184.
- U. Zidan, H. A. El Desouky, M. M. Gaber, and M. M. Abdelsamea, From pixels to deposits: porphyry mineralization with multispectral convolutional neural networks, IEEE J Sel Top Appl Earth Obs Remote Sens, 16, 9474-9486, 2023. https://doi.org/10.1109/JSTARS.2023.3321714
- S. Metlek and H. Cetiner, ResUNet+: A new convolutional and attention block-based approach for brain tumor segmentation, IEEE Access, 11,69884–69902, 2023. https://doi.org/10.1109/ACCESS.2023.3294179.
- H. Çetiner and S. Metlek, DenseUNet+: A novel hybrid segmentation approach based on multi-modality images for brain tumor segmentation, Journal of King Saud University-Computer and Information Sciences, 35(8), 2023. https://doi.org/10.1016/j.jksuci.2023.101663.
- F. Pirajno, Hydrothermal Processes and Wall Rock Alteration. 73-164, 2009.
- Ö. Polat, A. Polat, and T. Ekici, Automatic classification of volcanic rocks from thin section images using transfer learning networks, Neural Comput Appl, 33(18), 11531–11540, 2021. https://doi.org/10.1007/s00521-021-05849-3.
- R. A. Rubo, C. de Carvalho Carneiro, M. F. Michelon, ve R. dos S. Gioria, Digital petrography: Mineralogy and porosity identification using machine learning algorithms in petrographic thin section images, J Pet Sci Eng, 183, 2019. https://doi.org/10.1016/j.petrol.2019.106382.
- R. P. de Lima ve D. Duarte, Pretraining convolutional neural networks for mudstone petrographic thin-section image classification, Geosciences (Switzerland), 11(8), 2021. https://doi.org/10.3390/GEOSCIENCES11080336.
- C. Guojian ve L. Peisong, Rock thin-section image classification based on residual neural network, in 2021 IEEE 6th International Conference on Intelligent Computing and Signal Processing, ICSP 2021, Institute of Electrical and Electronics Engineers Inc., 521–524, 2021. https://doi.org/ 10.1109/ICSP51882.2021.9408983.
- Y. Xu, Z. Dai, ve Y. Luo, Research on application of image enhancement technology in automatic recognition of rock thin section, in IOP Conference Series: Earth and Environmental Science, IOP Publishing Ltd, 2020. https://doi.org/10.1088/1755-1315/605/1/012024.
- X. L. Zhang, Z. J. Wang, D. T. Liu, Q. Sun, and J. Wang, Rock thin section image classification based on depth residuals shrinkage network and attention mechanism, Earth Sci Inform, 16(2),1449–1457, 2023. https://doi.org/10.1007/s12145-023-00981-1.
- J. C. Á. Iglesias, R. B. M. Santos, and S. Paciornik, Deep learning discrimination of quartz and resin in optical microscopy images of minerals, Miner Eng, 138, 79–85, 2019, https://doi.org/10.1016/j.mineng.2019.04.032.
- C. L. Bérubé, R. Gema, B. Olivo, C. Chouteau, P. Perrouty, S. Pejman, J. J. Enkin, M.A. William, F. Leonardo, T. Raphaël, Predicting rock type and detecting hydrothermal alteration using machine learning and petrophysical properties of the Canadian Malartic ore and host rocks, Pontiac Subprovince, Québec, Canada, Ore Geol Rev, 96, 130–145, 2018, https://doi.org/10.1016/j.oregeorev.2018.04.011.
- V. Kůrková, Y. Manolopoulos, B. Hammer, L. Iliadis, ve I. Maglogiannis, Eds., Artificial Neural Networks and Machine Learning – ICANN 2018, 11141, Cham: Springer International Publishing, 2018. https://doi.org/10.1007/978-3-030-01424-7.
- Artificial Neural Networks and Machine Learning-ICANN 2018. [Online]. Available: http://www.springer.com/series/7407
- S. Kızılok, Fizik Tabanlı Yeni Hibrit Optimizasyon Algoritmalarının Geliştirilmesi ve Veri Madenciliğinde Uygulamaları. Doktora Tezi, Fırat Üniversitesi, Elazığ, Türkiye, 2017.
- M. Beşkirli ve M. F. Tefek, Gradyan Tabanlı Optimize Edici Algoritmasının Parametre Ayarlaması, European Journal of Science and Technology, 2021. https://doi.org/10.31590/ejosat.1010813.
- M. R. Öner, Derin öğrenme algoritmaları kullanılarak dış ve orta kulak hastalıklarının tespit edilmesi, Konya Teknik Üniversitesi Lisansüstü Eğitim Enstitüsü, 2023.
- Ö. İnik, E. Ülker, Derin öğrenme ve görüntü analizinde kullanılan derin öğrenme modelleri Gaziosmanpaşa Bilimsel Araştırma Dergisi (GBAD), 6 (3), 85- 104, 2017.
- E. Seyyarer F. Ayata, T. Uçkan, A. Karcı, Derin öğrenmede kullanilan optimizasyon algoritmalarının uygulanması ve kıyaslanması, Anatolian Journal of Computer Sciences, 5 (2), 90-98, 2020.
- D. P. Kingma ve J. Ba, Adam: A method for stochastic optimization, 2014. [Online]. Available: http://arxiv.org/abs/1412.6980
- H. Badem, Parkinson hastalığının ses sinyalleri üzerinden makine öğrenmesi teknikleri ile tanımlanması, Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi, 2019. https://doi.org/10.28948/ngumuh.524658.
- M. Hossin ve M.N. Sulaiman, A Review on Evaluation Metrics for Data Classification Evaluations, International Journal of Data Mining & Knowledge Management Process, 5 (2), 01–11, 2015. https://doi.org/10.5121/ijdkp.2015.5201.
- F. Chollet, Xception: Deep learning with depthwise separable convolutions Proceedings of the IEEE conference on computer vision and pattern recognition. 2017.
Evrişimli sinir ağları kullanılarak ince kesit görüntülerden hidrotermal alterasyon türlerinin sınıflandırılması
Yıl 2024,
Cilt: 13 Sayı: 2, 528 - 539, 15.04.2024
Rıza Çenet
,
Emre Ünsal
,
Oktay Canbaz
Öz
Hidrotermal alterasyon, değerli madenlerin arama aşamalarında kullanılan önemli bir jeolojik özelliktir. Bu araştırma, mikroskop görüntülerinde hidrotermal alterasyon türlerini tanımlamak için oluşturulan iki farklı derin öğrenme ağı yapısına odaklanmaktadır. 2500 görüntüden oluşan veri setinin, %70’i ağın eğitilmesinde, %20’si ağın test edilmesinde ve %10’u ağın geçerliliğinin ölçülmesinde kullanılmıştır. Evrişimli Sinir Ağı (ESA) ve Xception modelleri, Adam, RMSprop ve SGD optimizasyon fonksiyonları kullanılarak eğitilmiş ve sonuçları karşılaştırılmıştır. ESA modeli için Adam ve SGD optimizasyon fonksiyonları %96 doğru sınıflandırma yaparak, en başarılı sınıflandırmayı gerçekleştirmiştir. Xception modeli için en yüksek doğruluk değeri %98 ile Adam ve RMSprop optimizasyon fonksiyonları kullanılan ağlarda gerçekleşmiştir. Her ne kadar Xception modeli daha yüksek doğruluk değerlerine sahip olsa da ağın eğitim süresi göz önüne alındığında ESA modelinin işlemi çok daha hızlı tamamladığı görülmüştür.
Kaynakça
- D. G. Tang, K. L. Milliken, ve K. T. Spikes, Machine learning for point counting and segmentation of arenite in thin section, Mar Pet Geol, 120, 2020. doi: https://doi.org/10.1016/j.marpetgeo.2020.104518.
- M. A. Abdelkader, Y. Watanabe, A. Shebl, H. A. El-Dokouny, M. Dawoud, and Á. Csámer, Effective delineation of rare metal-bearing granites from remote sensing data using machine learning methods: A case study from the Umm Naggat Area, Central Eastern Desert, Egypt, Ore Geol Rev, 150, 2022. https://doi.org/10.1016/j.oregeorev.2022.105184.
- U. Zidan, H. A. El Desouky, M. M. Gaber, and M. M. Abdelsamea, From pixels to deposits: porphyry mineralization with multispectral convolutional neural networks, IEEE J Sel Top Appl Earth Obs Remote Sens, 16, 9474-9486, 2023. https://doi.org/10.1109/JSTARS.2023.3321714
- S. Metlek and H. Cetiner, ResUNet+: A new convolutional and attention block-based approach for brain tumor segmentation, IEEE Access, 11,69884–69902, 2023. https://doi.org/10.1109/ACCESS.2023.3294179.
- H. Çetiner and S. Metlek, DenseUNet+: A novel hybrid segmentation approach based on multi-modality images for brain tumor segmentation, Journal of King Saud University-Computer and Information Sciences, 35(8), 2023. https://doi.org/10.1016/j.jksuci.2023.101663.
- F. Pirajno, Hydrothermal Processes and Wall Rock Alteration. 73-164, 2009.
- Ö. Polat, A. Polat, and T. Ekici, Automatic classification of volcanic rocks from thin section images using transfer learning networks, Neural Comput Appl, 33(18), 11531–11540, 2021. https://doi.org/10.1007/s00521-021-05849-3.
- R. A. Rubo, C. de Carvalho Carneiro, M. F. Michelon, ve R. dos S. Gioria, Digital petrography: Mineralogy and porosity identification using machine learning algorithms in petrographic thin section images, J Pet Sci Eng, 183, 2019. https://doi.org/10.1016/j.petrol.2019.106382.
- R. P. de Lima ve D. Duarte, Pretraining convolutional neural networks for mudstone petrographic thin-section image classification, Geosciences (Switzerland), 11(8), 2021. https://doi.org/10.3390/GEOSCIENCES11080336.
- C. Guojian ve L. Peisong, Rock thin-section image classification based on residual neural network, in 2021 IEEE 6th International Conference on Intelligent Computing and Signal Processing, ICSP 2021, Institute of Electrical and Electronics Engineers Inc., 521–524, 2021. https://doi.org/ 10.1109/ICSP51882.2021.9408983.
- Y. Xu, Z. Dai, ve Y. Luo, Research on application of image enhancement technology in automatic recognition of rock thin section, in IOP Conference Series: Earth and Environmental Science, IOP Publishing Ltd, 2020. https://doi.org/10.1088/1755-1315/605/1/012024.
- X. L. Zhang, Z. J. Wang, D. T. Liu, Q. Sun, and J. Wang, Rock thin section image classification based on depth residuals shrinkage network and attention mechanism, Earth Sci Inform, 16(2),1449–1457, 2023. https://doi.org/10.1007/s12145-023-00981-1.
- J. C. Á. Iglesias, R. B. M. Santos, and S. Paciornik, Deep learning discrimination of quartz and resin in optical microscopy images of minerals, Miner Eng, 138, 79–85, 2019, https://doi.org/10.1016/j.mineng.2019.04.032.
- C. L. Bérubé, R. Gema, B. Olivo, C. Chouteau, P. Perrouty, S. Pejman, J. J. Enkin, M.A. William, F. Leonardo, T. Raphaël, Predicting rock type and detecting hydrothermal alteration using machine learning and petrophysical properties of the Canadian Malartic ore and host rocks, Pontiac Subprovince, Québec, Canada, Ore Geol Rev, 96, 130–145, 2018, https://doi.org/10.1016/j.oregeorev.2018.04.011.
- V. Kůrková, Y. Manolopoulos, B. Hammer, L. Iliadis, ve I. Maglogiannis, Eds., Artificial Neural Networks and Machine Learning – ICANN 2018, 11141, Cham: Springer International Publishing, 2018. https://doi.org/10.1007/978-3-030-01424-7.
- Artificial Neural Networks and Machine Learning-ICANN 2018. [Online]. Available: http://www.springer.com/series/7407
- S. Kızılok, Fizik Tabanlı Yeni Hibrit Optimizasyon Algoritmalarının Geliştirilmesi ve Veri Madenciliğinde Uygulamaları. Doktora Tezi, Fırat Üniversitesi, Elazığ, Türkiye, 2017.
- M. Beşkirli ve M. F. Tefek, Gradyan Tabanlı Optimize Edici Algoritmasının Parametre Ayarlaması, European Journal of Science and Technology, 2021. https://doi.org/10.31590/ejosat.1010813.
- M. R. Öner, Derin öğrenme algoritmaları kullanılarak dış ve orta kulak hastalıklarının tespit edilmesi, Konya Teknik Üniversitesi Lisansüstü Eğitim Enstitüsü, 2023.
- Ö. İnik, E. Ülker, Derin öğrenme ve görüntü analizinde kullanılan derin öğrenme modelleri Gaziosmanpaşa Bilimsel Araştırma Dergisi (GBAD), 6 (3), 85- 104, 2017.
- E. Seyyarer F. Ayata, T. Uçkan, A. Karcı, Derin öğrenmede kullanilan optimizasyon algoritmalarının uygulanması ve kıyaslanması, Anatolian Journal of Computer Sciences, 5 (2), 90-98, 2020.
- D. P. Kingma ve J. Ba, Adam: A method for stochastic optimization, 2014. [Online]. Available: http://arxiv.org/abs/1412.6980
- H. Badem, Parkinson hastalığının ses sinyalleri üzerinden makine öğrenmesi teknikleri ile tanımlanması, Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi, 2019. https://doi.org/10.28948/ngumuh.524658.
- M. Hossin ve M.N. Sulaiman, A Review on Evaluation Metrics for Data Classification Evaluations, International Journal of Data Mining & Knowledge Management Process, 5 (2), 01–11, 2015. https://doi.org/10.5121/ijdkp.2015.5201.
- F. Chollet, Xception: Deep learning with depthwise separable convolutions Proceedings of the IEEE conference on computer vision and pattern recognition. 2017.