Attempt of Lithology Prediction from Surface Drilling Data and Machine Learning for Scientific Drilling Programs

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.

Download Full-text

Well-Logging based lithology prediction using Machine Learning

10.3997/2214-4609.202054010 ◽

2020 ◽

Author(s):

Y. Meshalkin ◽

A. Shakirov ◽

D. Orlov ◽

D. Koroteev

Keyword(s):

Machine Learning ◽

Well Logging ◽

Lithology Prediction

Download Full-text

Supervised Machine Learning Techniques Applied to Wireline log Data for Automated Lithology Prediction

10.3997/2214-4609.202149bgs33 ◽

2021 ◽

Author(s):

M. Popescu ◽

R. Head ◽

T. Ferriday ◽

K. Evans ◽

J. Montero ◽

...

Keyword(s):

Machine Learning ◽

Supervised Machine Learning ◽

Machine Learning Techniques ◽

Log Data ◽

Learning Techniques ◽

Lithology Prediction

Download Full-text

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

10.2118/204658-ms ◽

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.

Download Full-text

Using Supervised Machine Learning Algorithms for Automated Lithology Prediction from Wireline Log Data

10.2118/208559-ms ◽

2021 ◽

Author(s):

Marian Popescu ◽

Rebecca Head ◽

Tim Ferriday ◽

Kate Evans ◽

Jose Montero ◽

...

Keyword(s):

Machine Learning ◽

Learning Algorithm ◽

Machine Learning Algorithms ◽

Supervised Machine Learning ◽

Training Dataset ◽

Depth Interval ◽

Log Data ◽

Machine Learning Approach ◽

Lithology Prediction ◽

Logging While Drilling

Abstract This paper presents advancements in machine learning and cloud deployment that enable rapid and accurate automated lithology interpretation. A supervised machine learning technique is described that enables rapid, consistent, and accurate lithology prediction alongside quantitative uncertainty from large wireline or logging-while-drilling (LWD) datasets. To leverage supervised machine learning, a team of geoscientists and petrophysicists made detailed lithology interpretations of wells to generate a comprehensive training dataset. Lithology interpretations were based on applying determinist cross-plotting by utilizing and combining various raw logs. This training dataset was used to develop a model and test a machine learning pipeline. The pipeline was applied to a dataset previously unseen by the algorithm, to predict lithology. A quality checking process was performed by a petrophysicist to validate new predictions delivered by the pipeline against human interpretations. Confidence in the interpretations was assessed in two ways. The prior probability was calculated, a measure of confidence in the input data being recognized by the model. Posterior probability was calculated, which quantifies the likelihood that a specified depth interval comprises a given lithology. The supervised machine learning algorithm ensured that the wells were interpreted consistently by removing interpreter biases and inconsistencies. The scalability of cloud computing enabled a large log dataset to be interpreted rapidly; >100 wells were interpreted consistently in five minutes, yielding >70% lithological match to the human petrophysical interpretation. Supervised machine learning methods have strong potential for classifying lithology from log data because: 1) they can automatically define complex, non-parametric, multi-variate relationships across several input logs; and 2) they allow classifications to be quantified confidently. Furthermore, this approach captured the knowledge and nuances of an interpreter's decisions by training the algorithm using human-interpreted labels. In the hydrocarbon industry, the quantity of generated data is predicted to increase by >300% between 2018 and 2023 (IDC, Worldwide Global DataSphere Forecast, 2019–2023). Additionally, the industry holds vast legacy data. This supervised machine learning approach can unlock the potential of some of these datasets by providing consistent lithology interpretations rapidly, allowing resources to be used more effectively.

Download Full-text

Multi Well Analysis Data Processing for Event Analysis and Mitigation

10.2118/201002-ms ◽

2021 ◽

Author(s):

Vallet Laurent ◽

Gutarov Pavel ◽

Chevallier Bertrand ◽

Converset Julien ◽

Paterson Graeme ◽

...

Keyword(s):

Machine Learning ◽

Data Analysis ◽

New Technologies ◽

Early Stage ◽

Mitigation Measures ◽

Construction Process ◽

Field Development ◽

Drilling Data ◽

Lost Time ◽

Productive Time

Abstract In the current economic environment, delivering wells on time and on budget is paramount. Well construction is a significant cost of any field development and it is more important than ever to minimize these costs and to avoid unnecessary lost time and non-productive time. Invisible lost time and non-productive time can represent as much as 40% of the cost of well construction and can lead to more severe issues such as delaying first oil, losing the well or environmental impact. There has been much work developing systems to optimize well construction, but the industry still fails to routinely detect and avoid problematic events such as stuck pipe, kicks, losses and washouts. Standardizing drilling practice can help also to improve the efficiency, this practice has shown a 30% cost reduction through repetitive and systematic practices, automation becomes the key process to realize it and Machine Learning introduced by new technologies is the key to achieve it. Drilling data analysis is key to understanding reasons for bad performances and detecting at an early stage potential downhole events. It can be done efficiently to provide to the user tools to look at the well construction process in its whole instead of looking at the last few hours as it is done at the rig site. In order to analyze the drilling data, it is necessary to have access to reliable data in Real-Time to compare with a data model considering the context (BHA, fluids, well geometry). Well planning, including multi-well offset analysis of risks, drilling processes and geology enables a user to look at the full well construction process and define levels of automation. This paper applies machine learning to a post multi-well analysis of a deepwater field development known for its drilling challenges. Minimizing the human input through automation allowed us to compare offset wells and to define the root cause for non-productive time. In our case study an increase of the pressure while drilling should have led to immediate mitigation measures to avoid a wiper trip. This paper presents techniques used to systematize surface data analysis and a workflow to identify at an early stage a near pack off which was spotted in an automatic way. The application of this process during operations could have achieved a 10%-time reduction of the section 12 ¼’’.

Download Full-text