Deep learning of rock microscopic images for intelligent lithology identification: Neural network comparison and selection

An intelligent lithology identification method is proposed based on deep learning of the rock microscopic images.Based on the characteristics of rock images in the dataset,we used Xception,MobileNet_v2,Inception_ResNet_v2,Inception_v3,Densenet121,ResNet101_v2,and ResNet-101 to develop microscopic image classification models,and then the network structures of seven different convolutional neural networks(CNNs)were compared.It shows that the multi-layer representation of rock features can be represented through convolution structures,thus better feature robustness can be achieved.For the loss function,cross-entropy is used to back propagate the weight parameters layer by layer,and the accuracy of the network is improved by frequent iterative training.We expanded a self-built dataset by using transfer learning and data augmentation.Next,accuracy(acc)and frames per second(fps)were used as the evaluation indexes to assess the accuracy and speed of model identification.The results show that the Xception-based model has the optimum performance,with an accuracy of 97.66%in the training dataset and 98.65%in the testing dataset.Furthermore,the fps of the model is 50.76,and the model is feasible to deploy under different hardware conditions and meets the requirements of rapid lithology identification.This proposed method is proved to be robust and versatile in generalization performance,and it is suitable for both geologists and engineers to identify lithology quickly.

Optimal Classification of Minerals by Microscopic Image Analysis Based on Seven-State “Deep Learning” Combined with Optimizers

The development of artificial intelligence (AI), particularly deep learning, has made it possible to accelerate and improve the processing of data collected in different fields (commerce, medicine, surveillance or security, agriculture, etc.). Most related works use open source consistent image databases. This is the case for ImageNet reference data such as coco data, IP102, CIFAR-10, STL-10 and many others with variability representatives. The consistency of its images contributes to the spectacular results observed in its fields with deep learning. The application of deep learning which is making its debut in geology does not, to our knowledge, include a database of microscopic images of thin sections of open source rock minerals. In this paper, we evaluate three optimizers under the AlexNet architecture to check whether our acquired mineral images have object features or patterns that are clear and distinct to be extracted by a neural network. These are thin sections of magmatic rocks (biotite and 2-mica granite, granodiorite, simple granite, dolerite, charnokite and gabbros, etc.) which served as support. We use two hyper-parameters: the number of epochs to perform complete rounds on the entire data set and the “learning rate” to indicate how quickly the weights in the network will be modified during optimization. Using Transfer Learning, the three (3) optimizers all based on the gradient descent methods of Stochastic Momentum Gradient Descent (sgdm), Root Mean Square Propagation (RMSprop) algorithm and Adaptive Estimation of moment (Adam) achieved better performance. The recorded results indicate that the Momentum optimizer achieved the best scores respectively of 96.2% with a learning step set to 10−3 for a fixed choice of 350 epochs during this variation and 96, 7% over 300 epochs for the same value of the learning step. This performance is expected to provide excellent insight into image quality for future studies. Then they participate in the development of an intelligent system for the identification and classification of minerals, seven (7) in total (quartz, biotite, amphibole, plagioclase, feldspar, muscovite, pyroxene) and rocks.

Dynamic analysis of granite rockburst based on the PIV technique

This paper describes the deep rockburst simulation system to reproduce the granite instantaneous rockburst process.Based on the PIV(Particle Image Velocimetry)technique,quantitative analysis of a rockburst,the images of tracer particle,displacement and strain fields can be obtained,and the debris trajectory described.According to the observation of on-site tests,the dynamic rockburst is actually a gas–solid high speed flow process,which is caused by the interaction of rock fragments and surrounding air.With the help of analysis on high speed video and PIV images,the granite rockburst failure process is composed of six stages of platey fragment spalling and debris ejection.Meanwhile,the elastic energy for these six stages has been calculated to study the energy variation.The results indicate that the rockburst process can be summarized as:an initiating stage,intensive developing stage and gradual decay stage.This research will be helpful for our further understanding of the rockburst mechanism.

Remote Sensing Geological Exploration Model for Copper and Gold Deposits in the East Tianshan, Xinjiang

Based on the identification and enhancive processing of information about strata, structure, magmatite, and alteration in ore-concentrated area in the eastern Tianshan, an exploration mode of remote sensing geology is established. The mode covers basic images composed of TM (7, 4, 1), Munsell space transformation for recognizing rock type, directional matched filtering for enhancing structures, multi-layer separating and extracting weak alteration information. It will provide a rapid and effective method for geological mapping and metallogenic prediction in this region.