Pretraining Convolutional Neural Networks for Mudstone Petrographic Thin-Section Image Classification

Lima, Rafael Pires de; Duarte, D.

doi:10.3390/geosciences11080336

Cited by 18 publications

(9 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This has inspired research in the application of deep learning in this area. The positive effects of using these methods in hard coal petrography [ 17 , 18 , 19 ] and also in geology [ 20 , 21 ] are already known.…”

Section: Introductionmentioning

confidence: 99%

“…The mentioned methods were also used in plant phenotyping [ 29 ], crop estimation [ 30 ], and plant condition assessment [ 31 ]. There were also many attempts targeting the application of computer vision and artificial intelligence in petrography [ 20 , 35 ].…”

Section: Introductionmentioning

confidence: 99%

“…Microscopic vision, segmentation, and deep learning have been successfully applied to recognize petrographic components and mineral substances in coal [ 17 ], Other researchers have used computer vision methods to identify minerals in rocks [ 20 , 21 ] or determine the grain sizes of aggregates [ 26 ]. Since the same components (coal, minerals, rocks) are present in wood pellets and are treated as contaminants, attempts have been made to apply similar microscopic and deep learning methods to their recognition.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Deep Learning Approach to Intrusion Detection and Segmentation in Pellet Fuels Using Microscopic Images

Iwaszenko¹,

Szymańska²,

Róg³

2023

Sensors

View full text Add to dashboard Cite

Pellet fuels are nowadays commonly used as a heat source for food preparation. Unfortunately, they may contain intrusions which might be harmful for humans and the environment. The intrusions can be identified precisely using immersed microscopy analysis. The aim of this study is to investigate the possibility of autonomous identification of selected classes of intrusions using relatively simple deep learning models. The semantic segmentation was chosen as a method for impurity identification in the microscopic image. Three architectures of deep networks based on UNet architecture were examined. The networks contained the same depth as UNet but with a successively limited number of filters. The input image influence on the segmentation results was also examined. The efficiency of the network was assessed using the intersection over union index. The results showed an easily observable impact of the filter used on segmentation efficiency. The influence of the input image resolution is not so clear, and even the lowest (256 × 256 pixels) resolution used gave satisfactory results. The biggest (but still smaller than originally proposed UNet) network yielded segmentation quality good enough for practical applications. The simpler one was also applicable, although the quality of the segmentation decreased considerably. The simplest network gave poor results and is not suitable in applications. The two proposed networks can be used as a support for domain experts in practical applications.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Deep Learning Approach to Intrusion Detection and Segmentation in Pellet Fuels Using Microscopic Images

Iwaszenko¹,

Szymańska²,

Róg³

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Since then, most deep learning implementations in geosciences, particularly for image analysis tasks, have relied primarily on transfer learning methods (Li et al, 2017;de Lima et al, 2019;Baraboshkin et al, 2020;Wu et al, 2020). Although this method allows for some breakthroughs in geological image classification and recognition, the model was originally trained on a domain that inherently has different data features and distributions, but can still produce a high-performance result that could raise some concerns in the long run (Pires de Lima and Duarte, 2021;Koeshidayatullah, 2022). Furthermore, this is compounded by the relatively stagnant performance and low explainability of various CNN models, which created the urgency to develop a deeper and wider CNN model.…”

Section: Introductionmentioning

confidence: 99%

FaciesViT: Vision transformer for an improved core lithofacies prediction

et al. 2022

View full text Add to dashboard Cite

Lithofacies classification is a fundamental step to perform depositional and reservoir characterizations in the subsurface. However, such a classification is often hindered by limited data availability and biased and time-consuming analysis. Recent work has demonstrated the potential of image-based supervised deep learning analysis, specifically convolutional neural networks (CNN), to optimize lithofacies classification and interpretation using core images. While most works have used transfer learning to overcome limited datasets and simultaneously yield a high-accuracy prediction. This method raises some serious concerns regarding how the CNN model learns and makes a prediction as the model was originally trained with entirely different datasets. Here, we proposed an alternative approach by adopting a vision transformer model, known as FaciesViT, to mitigate this issue and provide improved lithofacies prediction. We also experimented with various CNN architectures as the baseline models and two different datasets to compare and evaluate the performance of our proposed model. The experimental results show that the proposed models significantly outperform the established CNN architecture models for both datasets and in all cases, achieving an f1 score and weighted average in all tested metrics of 95%. For the first time, this study highlights the application of the Vision Transformer model to a geological dataset. Our findings show that the FaciesViT model has several advantages over conventional CNN models, including (i) no hyperparameter fine-tuning and exhaustive data augmentation required to match the accuracy of CNN models; (ii) it can work with limited datasets; and (iii) it can better generalize the classification to a new, unseen dataset. Our study shows that the application of the Vision transformer could further optimize image recognition and classification in the geosciences and mitigate some of the issues related to the generalizability and the explainability of deep learning models. Furthermore, the implementation of our proposed FaciesViT model has been shown to improve the overall performance and reproducibility of image-based core lithofacies classification which is significant for subsurface reservoir characterization in different basins worldwide.

show abstract

“…Geosciences in general have been adopting deep learning-based analytics in its workflows, such as image processing tasks. However, the lack of labeled, varied, and sufficiently large datasets 12 have resulted in images being overtrained and overfit to certain geological contexts 13 or with deep learning algorithms such as Convolutional Neural Networks (CNNs) with not enough data to yield satisfactory result 14 .The use of transfer learning has been suggested as an alternative 4,15,16 , with the risk of overtraining on a single geological context using this kind of approach. Furthermore, the high accuracy obtained from the transfer learning methods creates another dimension of uncertainty whereby a model trained to recognize animals or other daily objects can be applied to classify geological images, such as seismic and petrographic images that have entirely different high-and low-level features.…”

Section: Introductionmentioning

confidence: 99%

PetroGAN: A novel GAN-based approach to generate realistic, label-free petrographic datasets

Ferreira¹,

Ochoa²,

A.³

2022

Preprint

View full text Add to dashboard Cite

Deep learning architectures have enriched data analytics in the geosciences, complementing traditional approaches to geological problems. Although deep learning applications in geosciences show encouraging signs, the actual potential remains untapped. This is primarily because geological datasets, particularly petrography, are limited, time-consuming, and expensive to obtain, requiring in-depth knowledge to provide a high-quality labeled dataset. We approached these issues by developing a novel deep learning framework based on generative adversarial networks (GANs) to create the first realistic synthetic petrographic dataset. The StyleGAN2 architecture is selected to allow robust replication of statistical and esthetical characteristics, and improving the internal variance of petrographic data. The training dataset consists of 10070 images of rock thin sections both in plane-and cross-polarized light. The algorithm trained for 264 GPU hours and reached a state-of-the-art Fréchet Inception Distance (FID) score of 12.49 for petrographic images. We further observed the FID values vary with lithology type and image resolution. Our survey established that subject matter experts found the generated images were indistinguishable from real images. This study highlights that GANs are a powerful method for generating realistic synthetic data, experimenting with the latent space, and as a future tool for self-labelling, reducing the effort of creating geological datasets.

show abstract

Pretraining Convolutional Neural Networks for Mudstone Petrographic Thin-Section Image Classification

Cited by 18 publications

References 32 publications

A Deep Learning Approach to Intrusion Detection and Segmentation in Pellet Fuels Using Microscopic Images

A Deep Learning Approach to Intrusion Detection and Segmentation in Pellet Fuels Using Microscopic Images

FaciesViT: Vision transformer for an improved core lithofacies prediction

PetroGAN: A novel GAN-based approach to generate realistic, label-free petrographic datasets

Contact Info

Product

Resources

About