Real-Time Prediction for Sonic Slowness Logs from Surface Drilling Data Using Machine Learning Techniques

2021 ◽  
Author(s):  
Vagif Suleymanov ◽  
Hany Gamal ◽  
Guenther Glatz ◽  
Salaheldin Elkatatny ◽  
Abdulazeez Abdulraheem
Keyword(s):  
Machine Learning ◽  
Real Time ◽  
Shear Wave ◽  
Correlation Coefficients ◽  
Acoustic Properties ◽  
Support Vector ◽  
Inference System ◽  
Svm Model ◽  
Drilling Data ◽  
Sonic Logs

Abstract Acoustic data obtained from sonic logging tools plays an important role in formation evaluation. Given the associated costs, however, the industry clearly stands to benefit from cheaper technologies to obtain compressional and shear wave slowness data. Therefore, this paper delineates an alternative solution for the prediction of sonic log data by means of Machine Learning (ML). This study takes advantage of an adaptive neuro-fuzzy inference system (ANFIS) and support vector machine (SVM) ML techniques to predict compressional and shear wave slowness from drilling data only. In particular, the network is trained utilizing 2000 data points such as weight on bit (WOB), rate of penetration (ROP), standpipe pressure (SPP), torque (T), drill pipe rotation (RPM), and mud flow rate (GPM). Consequently, acoustic properties of the rock can be estimated solely from readily available parameters thereby saving both costs and time associated with sonic logs. The obtained results are promising and supportive of both ANFIS and SVM model as viable alternatives to obtain sonic data without the need for running sonic logs. The developed ANFIS model was able to predict compressional and shear wave slowness with correlation coefficients of 0.94 and 0.98 and average absolute percentage errors (AAPE) of 1.87% and 2.61%, respectively. Similarly, the SVM model predicted sonic logs with high accuracy yielding to correlation coefficients of more than 0.98 and AAPE of 0.74% and 0.84% for both compressional and shear logs, respectively. Once a network is trained, the approach naturally lends itself to be integrated as a real time service. This study outlines a novel and cost-effective solution to estimate rock compressional and shear-wave slowness solely from readily available drilling parameters. Importantly, the model has been verified for wells drilled in different formations with complex lithology substantiating the effectiveness of the approach.

Improving Real-Time Drilling Data Quality Using Artificial Intelligence and Machine Learning Techniques

2021 ◽  
Author(s):  
S. H. Al Gharbi ◽  
A. A. Al-Majed ◽  
A. Abdulraheem ◽  
S. Patil ◽  
S. M. Elkatatny
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Data Quality ◽  
Real Time ◽  
Input Data ◽  
Support Vector ◽  
The Real ◽  
Drilling Data ◽  
Drilling Operations

Abstract Due to high demand for energy, oil and gas companies started to drill wells in remote areas and unconventional environments. This raised the complexity of drilling operations, which were already challenging and complex. To adapt, drilling companies expanded their use of the real-time operation center (RTOC) concept, in which real-time drilling data are transmitted from remote sites to companies’ headquarters. In RTOC, groups of subject matter experts monitor the drilling live and provide real-time advice to improve operations. With the increase of drilling operations, processing the volume of generated data is beyond a human's capability, limiting the RTOC impact on certain components of drilling operations. To overcome this limitation, artificial intelligence and machine learning (AI/ML) technologies were introduced to monitor and analyze the real-time drilling data, discover hidden patterns, and provide fast decision-support responses. AI/ML technologies are data-driven technologies, and their quality relies on the quality of the input data: if the quality of the input data is good, the generated output will be good; if not, the generated output will be bad. Unfortunately, due to the harsh environments of drilling sites and the transmission setups, not all of the drilling data is good, which negatively affects the AI/ML results. The objective of this paper is to utilize AI/ML technologies to improve the quality of real-time drilling data. The paper fed a large real-time drilling dataset, consisting of over 150,000 raw data points, into Artificial Neural Network (ANN), Support Vector Machine (SVM) and Decision Tree (DT) models. The models were trained on the valid and not-valid datapoints. The confusion matrix was used to evaluate the different AI/ML models including different internal architectures. Despite the slowness of ANN, it achieved the best result with an accuracy of 78%, compared to 73% and 41% for DT and SVM, respectively. The paper concludes by presenting a process for using AI technology to improve real-time drilling data quality. To the author's knowledge based on literature in the public domain, this paper is one of the first to compare the use of multiple AI/ML techniques for quality improvement of real-time drilling data. The paper provides a guide for improving the quality of real-time drilling data.

scholarly journals Real-Time Prediction of Rate of Penetration in S-Shape Well Profile Using Artificial Intelligence Models

Sensors ◽  
2020 ◽  
Vol 20 (12) ◽  
pp. 3506 ◽  
Author(s):  
Salaheldin Elkatatny
Keyword(s):  
Artificial Intelligence ◽  
Real Time ◽  
Support Vector ◽  
Empirical Correlations ◽  
Validation Data ◽  
Inference System ◽  
Rate Of Penetration ◽  
Drilling Parameters ◽  
Svm Model ◽  
Data Points

Rate of penetration (ROP) is defined as the amount of removed rock per unit area per unit time. It is affected by several factors which are inseparable. Current established models for determining the ROP include the basic mathematical and physics equations, as well as the use of empirical correlations. Given the complexity of the drilling process, the use of artificial intelligence (AI) has been a game changer because most of the unknown parameters can now be accounted for entirely at the modeling process. The objective of this paper is to evaluate the ability of the optimized adaptive neuro-fuzzy inference system (ANFIS), functional neural networks (FN), random forests (RF), and support vector machine (SVM) models to predict the ROP in real time from the drilling parameters in the S-shape well profile, for the first time, based on the drilling parameters of weight on bit (WOB), drillstring rotation (DSR), torque (T), pumping rate (GPM), and standpipe pressure (SPP). Data from two wells were used for training and testing (Well A and Well B with 4012 and 1717 data points, respectively), and one well for validation (Well C) with 2500 data points. Well A and Well B data were combined in the training-testing phase and were randomly divided into a 70:30 ratio for training/testing. The results showed that the ANFIS, FN, and RF models could effectively predict the ROP from the drilling parameters in the S-shape well profile, while the accuracy of the SVM model was very low. The ANFIS, FN, and RF models predicted the ROP for the training data with average absolute percentage errors (AAPEs) of 9.50%, 13.44%, and 3.25%, respectively. For the testing data, the ANFIS, FN, and RF models predicted the ROP with AAPEs of 9.57%, 11.20%, and 8.37%, respectively. The ANFIS, FN, and RF models overperformed the available empirical correlations for ROP prediction. The ANFIS model estimated the ROP for the validation data with an AAPE of 9.06%, whereas the FN model predicted the ROP with an AAPE of 10.48%, and the RF model predicted the ROP with an AAPE of 10.43%. The SVM model predicted the ROP for the validation data with a very high AAPE of 30.05% and all empirical correlations predicted the ROP with AAPEs greater than 25%.

Applying Different Artificial Intelligence Techniques in Dynamic Poisson's Ratio Prediction Using Drilling Parameters

2021 ◽  
pp. 1-15
Author(s):  
Osama Sidddig ◽  
Hany Gamal ◽  
Salaheldin Elkatatny ◽  
Abdulazeez Abdulraheem
Keyword(s):  
Machine Learning ◽  
Real Time ◽  
Poisson’S Ratio ◽  
Correlation Coefficients ◽  
Wellbore Stability ◽  
Performance Estimation ◽  
Poisson's Ratio ◽  
Support Vector ◽  
Drilling Parameters ◽  
Data Points

Abstract Rock geomechanical properties impact wellbore stability, drilling performance, estimation of in-situ stresses, and design of hydraulic fracturing. One of these properties is Poisson's ratio which is measured from lab testing or derived from well logs, the former is costly, time-consuming and doesn't provide continuous information, and the latter may not be always available. An alternative prediction technique from drilling parameters in real-time is proposed in this paper. The novel contribution of this approach is that the drilling data is always available and obtained from the first encounter with the well. These parameters are easily obtainable from drilling rig sensors such as rate of penetration, weight on bit and torque. Three machine-learning methods were utilized, support vector machine (SVM), functional network (FN) and random forest (RF). Dataset (2905 data points) from one well were used to build the models, while a dataset from another well with 2912 data points was used to validate the constructed models. Both wells have diverse lithology consists of carbonate, shale and sandstone. To ensure optimal accuracy, sensitivity and optimization tests on various parameters in each algorithm were performed.The three machine learning tools provided good estimations, however, SVM and RF yielded close results, with correlation coefficients of 0.99 and the average absolute percentage error (AAPE) values were mostly less than 1%. While in FN the outcomes were less efficient with correlation coefficients of 0.92 and AAPE around 3.8%. Accordingly, the presented approach provides an effective tool for Poisson's ratio prediction on a real-time basis at no additional expense. In addition, the same approach could be used in other rock mechanical properties.

Evaluating the Effectiveness of Machine Learning Technologies in Improving Real-Time Drilling Data-Quality

2022 ◽  
pp. 1-14
Author(s):  
Salem Al-Gharbi ◽  
Abdulaziz Al-Majed ◽  
Salaheldin Elkatatny ◽  
Abdulazeez Abdulraheem
Keyword(s):  
Machine Learning ◽  
Data Quality ◽  
Real Time ◽  
Oil And Gas ◽  
Expert Knowledge ◽  
Cost Effective ◽  
Learning Technologies ◽  
Support Vector ◽  
Drilling Data ◽  
Artificial Neural Network Ann

Abstract Due to high demand for energy, oil and gas companies started to drill wells in remote environments conducting unconventional operations. In order to maintain safe, fast and more cost-effective operations, utilizing machine learning (ML) technologies has become a must. The harsh environments of drilling sites and the transmission setups, are negatively affecting the drilling data, leading to less than acceptable ML results. For that reason, big portion of ML development projects were actually spent on improving the data by data-quality experts. The objective of this paper is to evaluate the effectiveness of ML on improving the real-time drilling-data-quality and compare it to a human expert knowledge. To achieve that, two large real-time drilling datasets were used; one dataset was used to train three different ML techniques: artificial neural network (ANN), support vector machine (SVM) and decision tree (DT), the second dataset was used to evaluate it. The ML results were compared with the results of a real- time drilling data quality expert. Despite the complexity of ANN and good results in general, it achieved a relative root mean square error (RRMSE) of 2.83%, which was lower than DT and SVM technologies that achieved RRMSE of 0.35% and 0.48% respectively. The uniqueness of this work is in developing ML that simulates the improvement of drilling-data- quality by an expert. This research provides a guide for improving the quality of real-time drilling data.

Application of Machine Learning for Lithology-on-Bit Prediction using Drilling Data in Real-Time

2021 ◽  
Author(s):  
Temirlan Zhekenov ◽  
Artem Nechaev ◽  
Kamilla Chettykbayeva ◽  
Alexey Zinovyev ◽  
German Sardarov ◽  
...  
Keyword(s):  
Machine Learning ◽  
Data Quality ◽  
Real Time ◽  
Hybrid Modeling ◽  
Data Set ◽  
Drilling Parameters ◽  
Drilling Data ◽  
Stable Solutions ◽  
Mud Logging

SUMMARY Researchers base their analysis on basic drilling parameters obtained during mud logging and demonstrate impressive results. However, due to limitations imposed by data quality often present during drilling, those solutions often tend to lose their stability and high levels of predictivity. In this work, the concept of hybrid modeling was introduced which allows to integrate the analytical correlations with algorithms of machine learning for obtaining stable solutions consistent from one data set to another.

scholarly journals Development of detection method for automatic hemostasis using machine learning with abdominal cavity irrigation

2020 ◽  
Vol 7 (7) ◽  
pp. 2103
Author(s):  
Yoshihisa Matsunaga ◽  
Ryoichi Nakamura
Keyword(s):  
Machine Learning ◽  
Minimally Invasive Surgery ◽  
Minimally Invasive ◽  
Real Time ◽  
Invasive Surgery ◽  
Abdominal Cavity ◽  
Training Dataset ◽  
Support Vector ◽  
Processing Cost ◽  
Surgical Field

Background: Abdominal cavity irrigation is a more minimally invasive surgery than that using a gas. Minimally invasive surgery improves the quality of life of patients; however, it demands higher skills from the doctors. Therefore, the study aimed to reduce the burden by assisting and automating the hemostatic procedure a highly frequent procedure by taking advantage of the clearness of the endoscopic images and continuous bleeding point observations in the liquid. We aimed to construct a method for detecting organs, bleeding sites, and hemostasis regions.Methods: We developed a method to perform real-time detection based on machine learning using laparoscopic videos. Our training dataset was prepared from three experiments in pigs. Linear support vector machine was applied using new color feature descriptors. In the verification of the accuracy of the classifier, we performed five-part cross-validation. Classification processing time was measured to verify the real-time property. Furthermore, we visualized the time series class change of the surgical field during the hemostatic procedure.Results: The accuracy of our classifier was 98.3% and the processing cost to perform real-time was enough. Furthermore, it was conceivable to quantitatively indicate the completion of the hemostatic procedure based on the changes in the bleeding region by ablation and the hemostasis regions by tissue coagulation.Conclusions: The organs, bleeding sites, and hemostasis regions classification was useful for assisting and automating the hemostatic procedure in the liquid. Our method can be adapted to more hemostatic procedures. 

scholarly journals Machine Learning Models for Predicting Hearing Prognosis in Unilateral Idiopathic Sudden Sensorineural Hearing Loss

2020 ◽  
Vol 13 (2) ◽  
pp. 148-156
Author(s):  
Keon Vin Park ◽  
Kyoung Ho Oh ◽  
Yong Jun Jeong ◽  
Jihye Rhee ◽  
Mun Soo Han ◽  
...  
Keyword(s):  
Machine Learning ◽  
Hearing Loss ◽  
Sensorineural Hearing Loss ◽  
Sudden Sensorineural Hearing Loss ◽  
Sensorineural Hearing ◽  
Statistical Hypothesis ◽  
Support Vector ◽  
Learning Models ◽  
Svm Model ◽  
Machine Learning Models

Objectives. Prognosticating idiopathic sudden sensorineural hearing loss (ISSNHL) is an important challenge. In our study, a dataset was split into training and test sets and cross-validation was implemented on the training set, thereby determining the hyperparameters for machine learning models with high test accuracy and low bias. The effectiveness of the following five machine learning models for predicting the hearing prognosis in patients with ISSNHL after 1 month of treatment was assessed: adaptive boosting, K-nearest neighbor, multilayer perceptron, random forest (RF), and support vector machine (SVM).Methods. The medical records of 523 patients with ISSNHL admitted to Korea University Ansan Hospital between January 2010 and October 2017 were retrospectively reviewed. In this study, we analyzed data from 227 patients (recovery, 106; no recovery, 121) after excluding those with missing data. To determine risk factors, statistical hypothesis tests (e.g., the two-sample <i>t</i>-test for continuous variables and the chi-square test for categorical variables) were conducted to compare patients who did or did not recover. Variables were selected using an RF model depending on two criteria (mean decreases in the Gini index and accuracy).Results. The SVM model using selected predictors achieved both the highest accuracy (75.36%) and the highest F-score (0.74) on the test set. The RF model with selected variables demonstrated the second-highest accuracy (73.91%) and F-score (0.74). The RF model with the original variables showed the same accuracy (73.91%) as that of the RF model with selected variables, but a lower F-score (0.73). All the tested models, except RF, demonstrated better performance after variable selection based on RF.Conclusion. The SVM model with selected predictors was the best-performing of the tested prediction models. The RF model with selected predictors was the second-best model. Therefore, machine learning models can be used to predict hearing recovery in patients with ISSNHL.

scholarly journals Estimating Forest Carbon Fluxes Using Machine Learning Techniques Based on Eddy Covariance Measurements

2018 ◽  
Vol 10 (1) ◽  
pp. 203 ◽  
Author(s):  
Xianming Dou ◽  
Yongguo Yang ◽  
Jinhui Luo
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Eddy Covariance ◽  
Carbon Flux ◽  
Carbon Fluxes ◽  
Forest Carbon ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Inference System ◽  
Learning Techniques

Approximating the complex nonlinear relationships that dominate the exchange of carbon dioxide fluxes between the biosphere and atmosphere is fundamentally important for addressing the issue of climate change. The progress of machine learning techniques has offered a number of useful tools for the scientific community aiming to gain new insights into the temporal and spatial variation of different carbon fluxes in terrestrial ecosystems. In this study, adaptive neuro-fuzzy inference system (ANFIS) and generalized regression neural network (GRNN) models were developed to predict the daily carbon fluxes in three boreal forest ecosystems based on eddy covariance (EC) measurements. Moreover, a comparison was made between the modeled values derived from these models and those of traditional artificial neural network (ANN) and support vector machine (SVM) models. These models were also compared with multiple linear regression (MLR). Several statistical indicators, including coefficient of determination (R2), Nash-Sutcliffe efficiency (NSE), bias error (Bias) and root mean square error (RMSE) were utilized to evaluate the performance of the applied models. The results showed that the developed machine learning models were able to account for the most variance in the carbon fluxes at both daily and hourly time scales in the three stands and they consistently and substantially outperformed the MLR model for both daily and hourly carbon flux estimates. It was demonstrated that the ANFIS and ANN models provided similar estimates in the testing period with an approximate value of R2 = 0.93, NSE = 0.91, Bias = 0.11 g C m−2 day−1 and RMSE = 1.04 g C m−2 day−1 for daily gross primary productivity, 0.94, 0.82, 0.24 g C m−2 day−1 and 0.72 g C m−2 day−1 for daily ecosystem respiration, and 0.79, 0.75, 0.14 g C m−2 day−1 and 0.89 g C m−2 day−1 for daily net ecosystem exchange, and slightly outperformed the GRNN and SVM models. In practical terms, however, the newly developed models (ANFIS and GRNN) are more robust and flexible, and have less parameters needed for selection and optimization in comparison with traditional ANN and SVM models. Consequently, they can be used as valuable tools to estimate forest carbon fluxes and fill the missing carbon flux data during the long-term EC measurements.

Machine learning approaches for improving near-real-time IMERG rainfall estimates by integrating Cloud Properties from NOAA CDR PATMOSX

2021 ◽  
Author(s):  
Zhi Zhang ◽  
Dagang Wang ◽  
Jianxiu Qiu ◽  
Jinxin Zhu ◽  
Tingli Wang
Keyword(s):  
Machine Learning ◽  
Real Time ◽  
River Basin ◽  
Central China ◽  
Support Vector ◽  
Learning Approaches ◽  
Satellite Precipitation ◽  
Cloud Properties ◽  
Spatial Coverage ◽  
Extreme Gradient Boosting

AbstractThe Global Precipitation Measurement (GPM) mission provides satellite precipitation products with an unprecedented spatio-temporal resolution and spatial coverage. However, its near-real-time (NRT) product still suffers from low accuracy. This study aims to improve the early run of the Integrated Multi-satellitE Retrievals for GPM (IMERG) by using four machine learning approaches, i.e., support vector machine (SVM), random forest (RF), artificial neural network (ANN), and Extreme Gradient Boosting (XGB). The cloud properties are selected as the predictors in addition to the original IMERG in these approaches. All the four approaches show similar improvement, with 53%-60% reduction of root-mean-square error (RMSE) compared with the original IMERG in a humid area, i.e., the Dongjiang River Basin (DJR) in southeastern China. The improvements are even greater in a semi-arid area, i.e., the Fenhe River Basin (FHR) in central China, the RMSE reduction ranges from 63%-66%. The products generated by the machine learning methods performs similarly to or even outperform than the final run of IMERG. Feature importance analysis, a technique to evaluate input features based on how useful they are in predicting a target variable, indicates that the cloud height and the brightness temperature are the most useful information in improving satellite precipitation products, followed by the atmospheric reflectivity and the surface temperature. This study shows that a more accurate NRT precipitation product can be produced by combining machine learning approaches and cloud information, which is of importance for hydrological applications that requires NRT precipitation information including flood monitoring.

scholarly journals Using Machine Learning-Based Algorithms to Analyze Erosion Rates of a Watershed in Northern Taiwan

2020 ◽  
Vol 12 (5) ◽  
pp. 2022 ◽  
Author(s):  
Kieu Anh Nguyen ◽  
Walter Chen ◽  
Bor-Shiun Lin ◽  
Uma Seeboonruang
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Fuzzy Inference ◽  
Absolute Error ◽  
Organic Content ◽  
Rank Test ◽  
Support Vector ◽  
Inference System ◽  
Erosion Rates ◽  
Northern Taiwan

This study continues a previous study with further analysis of watershed-scale erosion pin measurements. Three machine learning (ML) algorithms—Support Vector Machine (SVM), Adaptive Neuro-Fuzzy Inference System (ANFIS), and Artificial Neural Network (ANN)—were used to analyze depth of erosion of a watershed (Shihmen reservoir) in northern Taiwan. In addition to three previously used statistical indexes (Mean Absolute Error, Root Mean Square of Error, and R-squared), Nash–Sutcliffe Efficiency (NSE) was calculated to compare the predictive performances of the three models. To see if there was a statistical difference between the three models, the Wilcoxon signed-rank test was used. The research utilized 14 environmental attributes as the input predictors of the ML algorithms. They are distance to river, distance to road, type of slope, sub-watershed, slope direction, elevation, slope class, rainfall, epoch, lithology, and the amount of organic content, clay, sand, and silt in the soil. Additionally, measurements of a total of 550 erosion pins installed on 55 slopes were used as the target variable of the model prediction. The dataset was divided into a training set (70%) and a testing set (30%) using the stratified random sampling with sub-watershed as the stratification variable. The results showed that the ANFIS model outperforms the other two algorithms in predicting the erosion rates of the study area. The average RMSE of the test data is 2.05 mm/yr for ANFIS, compared to 2.36 mm/yr and 2.61 mm/yr for ANN and SVM, respectively. Finally, the results of this study (ANN, ANFIS, and SVM) were compared with the previous study (Random Forest, Decision Tree, and multiple regression). It was found that Random Forest remains the best predictive model, and ANFIS is the second-best among the six ML algorithms.

Sign in / Sign up

Export Citation Format

Share Document