Prediction of gas hydrate saturation using machine learning and optimal set of well-logs

2020 ◽  
Author(s):  
Harpreet Singh ◽  
Yongkoo Seol ◽  
Evgeniy M. Myshakin
Keyword(s):  
Machine Learning ◽  
Gas Hydrate ◽  
Well Logs ◽  
Hydrate Saturation ◽  
Optimal Set

scholarly journals Research on the Estimate of Gas Hydrate Saturation Based on LSTM Recurrent Neural Network

Energies ◽  
2020 ◽  
Vol 13 (24) ◽  
pp. 6536
Author(s):  
Chuanhui Li ◽  
Xuewei Liu
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Recurrent Neural Network ◽  
Gas Hydrate ◽  
Short Term Memory ◽  
Chloride Concentration ◽  
Well Logs ◽  
Good Prediction ◽  
Learning Technology ◽  
Hydrate Saturation

Gas hydrate saturation is an important index for evaluating gas hydrate reservoirs, and well logs are an effective method for estimating gas hydrate saturation. To use well logs better to estimate gas hydrate saturation, and to establish the deep internal connections and laws of the data, we propose a method of using deep learning technology to estimate gas hydrate saturation from well logs. Considering that well logs have sequential characteristics, we used the long short-term memory (LSTM) recurrent neural network to predict the gas hydrate saturation from the well logs of two sites in the Shenhu area, South China Sea. By constructing an LSTM recurrent layer and two fully connected layers at one site, we used resistivity and acoustic velocity logs that were sensitive to gas hydrate as input. We used the gas hydrate saturation calculated by the chloride concentration of the pore water as output to train the LSTM network. We achieved a good training result. Applying the trained LSTM recurrent neural network to another site in the same area achieved good prediction of gas hydrate saturation, showing the unique advantages of deep learning technology in gas hydrate saturation estimation.

Estimation of gas hydrate saturation in Ulleung Basin using seismic attributes and well logs

2013 ◽  
Author(s):  
Taekju Jeong ◽  
Joongmoo Byun ◽  
Hyungwook Choi ◽  
Dong-Geun Yoo
Keyword(s):  
Gas Hydrate ◽  
Seismic Attributes ◽  
Well Logs ◽  
Ulleung Basin ◽  
Hydrate Saturation

GAS HYDRATE SATURATION ESTIMATED FROM ACOUSTIC IMPEDANCE IN THE ANDAMAN SEA, INDIA

2014 ◽  
Vol 33 (2) ◽  
pp. 163-168
Author(s):  
Xiujuan WANG ◽  
Jiliang WANG ◽  
Wei LI ◽  
Nittala Satyavani ◽  
Kalachand Sain
Keyword(s):  
Gas Hydrate ◽  
Acoustic Impedance ◽  
Andaman Sea ◽  
Hydrate Saturation

scholarly journals Wave Propagation Characteristics in Gas Hydrate-Bearing Sediments and Estimation of Hydrate Saturation

Energies ◽  
2021 ◽  
Vol 14 (4) ◽  
pp. 804
Author(s):  
Lin Liu ◽  
Xiumei Zhang ◽  
Xiuming Wang
Keyword(s):  
Gas Hydrate ◽  
Clay Content ◽  
Clean Energy ◽  
Compressional Wave ◽  
Physical Parameters ◽  
Well Log ◽  
Log Data ◽  
Phase Velocities ◽  
Hydrate Saturation ◽  
Hydrate Bearing Sediments

Natural gas hydrate is a new clean energy source in the 21st century, which has become a research point of the exploration and development technology. Acoustic well logs are one of the most important assets in gas hydrate studies. In this paper, an improved Carcione–Leclaire model is proposed by introducing the expressions of frame bulk modulus, shear modulus and friction coefficient between solid phases. On this basis, the sensitivities of the velocities and attenuations of the first kind of compressional (P1) and shear (S1) waves to relevant physical parameters are explored. In particular, we perform numerical modeling to investigate the effects of frequency, gas hydrate saturation and clay on the phase velocities and attenuations of the above five waves. The analyses demonstrate that, the velocities and attenuations of P1 and S1 are more sensitive to gas hydrate saturation than other parameters. The larger the gas hydrate saturation, the more reliable P1 velocity. Besides, the attenuations of P1 and S1 are more sensitive than velocity to gas hydrate saturation. Further, P1 and S1 are almost nondispersive while their phase velocities increase with the increase of gas hydrate saturation. The second compressional (P2) and shear (S2) waves and the third kind of compressional wave (P3) are dispersive in the seismic band, and the attenuations of them are significant. Moreover, in the case of clay in the solid grain frame, gas hydrate-bearing sediments exhibit lower P1 and S1 velocities. Clay decreases the attenuation of P1, and the attenuations of S1, P2, S2 and P3 exhibit little effect on clay content. We compared the velocity of P1 predicted by the model with the well log data from the Ocean Drilling Program (ODP) Leg 164 Site 995B to verify the applicability of the model. The results of the model agree well with the well log data. Finally, we estimate the hydrate layer at ODP Leg 204 Site 1247B is about 100–130 m below the seafloor, the saturation is between 0–27%, and the average saturation is 7.2%.

scholarly journals Elevated gas hydrate saturation within silt and silty clay sediments in the Shenhu area, South China Sea

2011 ◽  
Vol 116 (B5) ◽  
Author(s):  
Xiujuan Wang ◽  
Deborah R. Hutchinson ◽  
Shiguo Wu ◽  
Shengxiong Yang ◽  
Yiqun Guo
Keyword(s):  
South China Sea ◽  
South China ◽  
Gas Hydrate ◽  
Silty Clay ◽  
Shenhu Area ◽  
China Sea ◽  
Hydrate Saturation

Application of Machine Learning in Gas-Hydrate Formation and Trendline Prediction

2021 ◽  
Author(s):  
Celestine Udim Monday ◽  
Toyin Olabisi Odutola
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Natural Gas ◽  
Gas Hydrate ◽  
Gas Flow ◽  
Flow Line ◽  
Learning Algorithms ◽  
Hydrate Formation ◽  
Machine Learning Algorithms ◽  
Gas Hydrate Formation

Abstract Natural Gas production and transportation are at risk of Gas hydrate plugging especially when in offshore environments where temperature is low and pressure is high. These plugs can eventually block the pipeline, increase back pressure, stop production and ultimately rupture gas pipelines. This study seeks to develops machine learning models after a kinetic inhibitor to predict the gas hydrate formation and pressure changes within the natural gas flow line. Green hydrate inhibitor A, B and C were obtained as plant extracts and applied in low dosages (0.01 wt.% to 0.1 wt.%) on a 12meter skid-mounted hydrate closed flow loop. From the data generated, the optimal dosages of inhibitor A, B and C were observed to be 0.02 wt.%, 0.06 wt.% and 0.1 wt.% respectively. The data associated with these optimal dosages were fed to a set of supervised machine learning algorithms (Extreme gradient boost, Gradient boost regressor and Linear regressor) and a deep learning algorithm (Artificial Neural Network). The output results from the set of supervised learning algorithms and Deep Learning algorithms were compared in terms of their accuracies in predicting the hydrate formation and the pressure within the natural gas flow line. All models had accuracies greater than 90%. This result show that the application Machine learning to solving flow assurance problems is viable. The results show that it is viable to apply machine learning algorithms to solve flow assurance problems, analyzing data and getting reports which can improve accuracy and speed of on-site decision making process.

Machine Learning for Multiple Petrophysical Properties Regression Based on Core Images and Well Logs in a Heterogenous Reservoir

2021 ◽  
Author(s):  
Tao Lin ◽  
Mokhles Mezghani ◽  
Chicheng Xu ◽  
Weichang Li
Keyword(s):  
Machine Learning ◽  
Model Building ◽  
Image Features ◽  
Well Logs ◽  
Model Complexity ◽  
Rock Properties ◽  
Core Analysis ◽  
Petrophysical Properties ◽  
Blind Test ◽  
Porosity And Permeability

Abstract Reservoir characterization requires accurate prediction of multiple petrophysical properties such as bulk density (or acoustic impedance), porosity, and permeability. However, it remains a big challenge in heterogeneous reservoirs due to significant diagenetic impacts including dissolution, dolomitization, cementation, and fracturing. Most well logs lack the resolution to obtain rock properties in detail in a heterogenous formation. Therefore, it is pertinent to integrate core images into the prediction workflow. This study presents a new approach to solve the problem of obtaining the high-resolution multiple petrophysical properties, by combining machine learning (ML) algorithms and computer vision (CV) techniques. The methodology can be used to automate the process of core data analysis with a minimum number of plugs, thus reducing human effort and cost and improving accuracy. The workflow consists of conditioning and extracting features from core images, correlating well logs and core analysis with those features to build ML models, and applying the models on new cores for petrophysical properties predictions. The core images are preprocessed and analyzed using color models and texture recognition, to extract image characteristics and core textures. The image features are then aggregated into a profile in depth, resampled and aligned with well logs and core analysis. The ML regression models, including classification and regression trees (CART) and deep neural network (DNN), are trained and validated from the filtered training samples of relevant features and target petrophysical properties. The models are then tested on a blind test dataset to evaluate the prediction performance, to predict target petrophysical properties of grain density, porosity and permeability. The profile of histograms of each target property are computed to analyze the data distribution. The feature vectors are extracted from CV analysis of core images and gamma ray logs. The importance of each feature is generated by CART model to individual target, which may be used to reduce model complexity of future model building. The model performances are evaluated and compared on each target. We achieved reasonably good correlation and accuracy on the models, for example, porosity R2=49.7% and RMSE=2.4 p.u., and logarithmic permeability R2=57.8% and RMSE=0.53. The field case demonstrates that inclusion of core image attributes can improve petrophysical regression in heterogenous reservoirs. It can be extended to a multi-well setting to generate vertical distribution of petrophysical properties which can be integrated into reservoir modeling and characterization. Machine leaning algorithms can help automate the workflow and be flexible to be adjusted to take various inputs for prediction.

scholarly journals Application of Various Machine Learning Techniques in Predicting Total Organic Carbon from Well Logs

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Osama Siddig ◽  
Ahmed Farid Ibrahim ◽  
Salaheldin Elkatatny
Keyword(s):  
Machine Learning ◽  
Organic Carbon ◽  
Total Organic Carbon ◽  
The Other ◽  
Well Logs ◽  
Machine Learning Techniques ◽  
Percentage Error ◽  
Average Error ◽  
Support Vector ◽  
Empirical Correlations

Unconventional resources have recently gained a lot of attention, and as a consequence, there has been an increase in research interest in predicting total organic carbon (TOC) as a crucial quality indicator. TOC is commonly measured experimentally; however, due to sampling restrictions, obtaining continuous data on TOC is difficult. Therefore, different empirical correlations for TOC have been presented. However, there are concerns about the generalization and accuracy of these correlations. In this paper, different machine learning (ML) techniques were utilized to develop models that predict TOC from well logs, including formation resistivity (FR), spontaneous potential (SP), sonic transit time (Δt), bulk density (RHOB), neutron porosity (CNP), gamma ray (GR), and spectrum logs of thorium (Th), uranium (Ur), and potassium (K). Over 1250 data points from the Devonian Duvernay shale were utilized to create and validate the model. These datasets were obtained from three wells; the first was used to train the models, while the data sets from the other two wells were utilized to test and validate them. Support vector machine (SVM), random forest (RF), and decision tree (DT) were the ML approaches tested, and their predictions were contrasted with three empirical correlations. Various AI methods’ parameters were tested to assure the best possible accuracy in terms of correlation coefficient (R) and average absolute percentage error (AAPE) between the actual and predicted TOC. The three ML methods yielded good matches; however, the RF-based model has the best performance. The RF model was able to predict the TOC for the different datasets with R values range between 0.93 and 0.99 and AAPE values less than 14%. In terms of average error, the ML-based models outperformed the other three empirical correlations. This study shows the capability and robustness of ML models to predict the total organic carbon from readily available logging data without the need for core analysis or additional well interventions.

Sign in / Sign up

Export Citation Format

Share Document