Deep convolutions for in-depth automated rock typing

2019/09/25 by Evgeny E. Baraboshkin, E. E. Baraboshkin, L. S. Ismailova +11 · 2 citations
Computer Science · Engineering · #Archaeology #Architecture #Artificial intelligence #Artificial neural network #Computer science #Convolutional neural network #Feature (linguistics) #Feature extraction #Focus (optics) #Geologist #Geology #Geophysical Methods and Applications #Mineral Processing and Grinding #Paleontology #Pattern recognition (psychology) #Residual neural network #Rock Mechanics and Modeling #Set (abstract data type) #cs.CV #cs.LG

paper · pdf · doi:10.1016/j.cageo.2019.104330

25 pages, 9 figures, 3 tables, submitted to Computers and Geosciences Journal. Keywords: Core Image; Description; Convolutional Neural Networks; Representation; Geology; Lithotypes

openalex publication_date 2019/09/25 · arxiv created 2019/09/26 · arxiv updated 2019/09/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/06

Abstract

The description of rocks is one of the most time-consuming tasks in the everyday work of a geologist, especially when very accurate description is required. We here present a method that reduces the time needed for accurate description of rocks, enabling the geologist to work more efficiently. We describe the application of methods based on color distribution analysis and feature extraction. Then we focus on a new approach, used by us, which is based on convolutional neural networks. We used several well-known neural network architectures (AlexNet, VGG, GoogLeNet, ResNet) and made a comparison of their performance. The precision of the algorithms is up to 95% on the validation set with GoogLeNet architecture. The best of the proposed algorithms can describe 50 m of full-size core in one minute.

Citations

• Probabilistic Interpretation of Feedforward Classification Network Outputs, with Relationships to Statistical Pattern Recognition
• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• A Stochastic Approximation Method
• A Scale of Grade and Class Terms for Clastic Sediments
• Matplotlib: A 2D Graphics Environment
• Backpropagation Applied to Handwritten Zip Code Recognition
• An introduction to ROC analysis
• ImageNet classification with deep convolutional neural networks
• An overview of gradient descent optimization algorithms
• Improved Regularization of Convolutional Neural Networks with Cutout
• Adapting Convolutional Neural Networks for Geographical Domain Shift
• "Why Should I Trust You?": Explaining the Predictions of Any Classifier

Cited by

• Machine learning for drill core image analysis: A review
• Core Box Image Recognition and its Improvement with a New Augmentation Technique