Lithological facies classification using deep convolutional neural network

İmamverdiyev, Yadigar; Sukhostat, Lyudmila

doi:10.1016/j.petrol.2018.11.023

Cited by 140 publications

(40 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The method was tested on a public data set also employed in [1,7,8] where each feature vector consists of seven measurements, namely gamma ray (GR), resistivity log (RL), photoelectric effect (PE), neutron-density porosity difference (DPHI), average neutron density porosity (PHIA), approximated as the root of the average fit (magenta), and the uncertainty of the result, corresponding to the typical accuracy prediction error, is estimated from the individual green least-squares approximations evaluated at N * draw (d). In this example the expected model accuracy is 73% and the estimate uncertainty is ±3% with 95% confidence (NOLAN, SHANKLE, SHRIMPLIN, NEWBY, CHURCH-MAN BIBLE, CROSS H CATTLE, KIMZEY A, LUKE G U and Recruit F9) were used for model training and evaluation.…”

Section: Resultsmentioning

confidence: 99%

“…Boosted trees approach dominated the top part of the leaderboard, with top eight scores all employing the method. A recent 1D-CNN model by Imamverdiyev and Sukhostat [8] deserves particular attention due to its relatively good performance.…”

Section: Introductionmentioning

confidence: 99%

“…The microaveraged F 1 score (average prediction success) increased to 87.35% if the second-best guess of the model is included and if its likelihood is at least 50% of the likelihood of the best prediction. An accuracy comparison of our method, the approach by Imamverdiyev and Sukhostat [8] (1D-CNN) Fig. 7 A part of the model prediction vs the manually classified data.…”

mentioning

confidence: 99%

See 2 more Smart Citations

A practical method for well log data classification

Kostorz

2020

Comput Geosci

View full text Add to dashboard Cite

In this work, a method for well log data classification is presented. The method relies on a coordinate transformation to restructure the data in an optimal way and a quasi-probabilistic interpolation technique capable of smoothing noisy data. The approach does not require case-specific design, is computationally efficient and provides a statistical characterization of the classification problem. Consequently, transition zones between facies can be modelled in a realistic fashion and intermediate rock types can be identified with ease. Apart from being capable of classifying unseen data with high accuracy, the technique can also be used as an informative quality and consistency assessment tool for manually classified data. The properties of the method are demonstrated on a realistic test case study.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

A practical method for well log data classification

Kostorz

2020

Comput Geosci

View full text Add to dashboard Cite

show abstract

“…Mitra et al [28] trained a CNN-based system to identify six species from microscope digital images and concluded that CNN architecture can provide the 'brain' for a viable robotic picking system. Imamverdiyev and Sukhostat [29] published an interesting geological application of CNN for lithofacies classification by employing different variables. Palafox et al [30] automatically detected geological landforms on Mars and they applied CNN successfully.…”

Section: Previous Studies On the Use Of Cnn In Geosciencesmentioning

confidence: 99%

A Convolutional Neural Network Architecture for Auto-Detection of Landslide Photographs to Assess Citizen Science and Volunteered Geographic Information Data Quality

Can

Kocaman

Gökçeoğlu

2019

IJGI

View full text Add to dashboard Cite

Several scientific processes benefit from Citizen Science (CitSci) and VGI (Volunteered Geographical Information) with the help of mobile and geospatial technologies. Studies on landslides can also take advantage of these approaches to a great extent. However, the quality of the collected data by both approaches is often questionable, and automated procedures to check the quality are needed for this purpose. In the present study, a convolutional neural network (CNN) architecture is proposed to validate landslide photos collected by citizens or nonexperts and integrated into a mobile- and web-based GIS environment designed specifically for a landslide CitSci project. The VGG16 has been used as the base model since it allows finetuning, and high performance could be achieved by selecting the best hyper-parameters. Although the training dataset was small, the proposed CNN architecture was found to be effective as it could identify the landslide photos with 94% precision. The accuracy of the results is sufficient for purpose and could even be improved further using a larger amount of training data, which is expected to be obtained with the help of volunteers.

show abstract

“…Neste trabalho foram obtidas taxas de precisão de 60 a 100 % dependendo da litologia analisada. Imamverdiyev et al (2019) [3] foi utilizada uma rede neural artificial profunda convolucional unidimensional (1D-CNN) para predizer a litologia. As variáveis de entrada foram o efeito fotoelétrico (PE), GR, registro de resistividade (RL), diferença de porosidade de densidade de nêutrons (DPHI), porosidade de densidade média de nêutrons (PHIA).…”

Section: Introductionunclassified

Predição da Litologia por Machine Learning Utilizando Perfis de Perfuração

Luz¹,

Figueiredo²

2020

Anais Do 14. Congresso Brasileiro De Inteligência Computacional

View full text Add to dashboard Cite

A indústria do petróleo está entre uma das atividades mais importantes e caras no mundo, atraindo muita atenção e esforço. Os custos envolvidos na exploração estimulam estudos que visam o aumento do conhecimento que promova a redução das despesas com as atividades do processo de prospecção, exploração e refino. Neste contexto, a utilização de algoritmos capazes de predizer com maior acurácia a litologia, que está estreitamente relacionada à caracterização de reservatórios, tornam-se conhecimentos valiosos. Este trabalho se insere nesse contexto e tem por objetivo a inferência da litologia na área da bacia de petróleo a partir de modelos de Machine Learning, tais como: k-Nearest Neighbors, Random Forest e Redes Neurais, utilizando um número menor de perfis de perfuração. Os resultados mostraram se promissores, podendo ser utilizados no processamento de log de poços para discriminação litológica.

show abstract

Lithological facies classification using deep convolutional neural network

Cited by 140 publications

References 16 publications

A practical method for well log data classification

A practical method for well log data classification

A Convolutional Neural Network Architecture for Auto-Detection of Landslide Photographs to Assess Citizen Science and Volunteered Geographic Information Data Quality

Predição da Litologia por Machine Learning Utilizando Perfis de Perfuração

Contact Info

Product

Resources

About