Production-Strategy Insights Using Machine Learning: Application for Bakken Shale

Luo, Guofan; Tian, Yao; Bychina, Mariia; Ehlig-Economides, Christine

doi:10.2118/195681-pa

Cited by 33 publications

(13 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Researchers have developed various prediction models based on ML methods to evaluate the impact of oil well properties, reservoir characteristics, and well production behaviors. With the help of ML simulation and modeling, the exploitation characteristics of shale oil/gas reservoirs are quickly analyzed, saving the exploration cost. − Due to the shale oil/gas production characteristics of rapid decay and gradual recovery, various parameters such as oil/gas well location, geological conditions, petrophysics, etc., must be considered comprehensively . Hence, oil/gas production is challenging to be predicted even with ML-based methods .…”

Section: Reconstruction Methods Of Kerogen Modelmentioning

confidence: 99%

Perspectives of Machine Learning Development on Kerogen Molecular Model Reconstruction and Shale Oil/Gas Exploitation

Kang

Zhao

2022

Energy Fuels

View full text Add to dashboard Cite

The shale revolution has provided abundant shale oil/gas resources for the world, but the efficient, sustainable, and environmentally friendly exploitation of shale oil/gas is still challenging. Kerogen is the primary hydrocarbon source of shale oil/gas. The research on the kerogen chemo-mechanical properties significantly influences the development of shale oil/gas extraction technology. Rapid reconstruction of the kerogen molecular models is the most effective way to study the generation mechanism of shale oil/gas from the bottom-up molecular level. However, due to the combinatorial explosion problem, the reconstruction complexity of kerogen increases sharply because of the kerogen’s characteristics of complex origin, large molecular weight, and diverse functional groups. The traditional kerogen molecular reconstruction methods require professionals to comprehensively analyze various experimental information to approximate the actual kerogen molecular models through trial-and-error. So, the traditional methods are time and material-consuming and extremely inefficient. These shortcomings make researchers spend too much strength on the reconstruction of kerogen molecular models and cannot focus on the study of kerogen chemo-mechanical properties. For the past few years, state-of-the-art machine learning (ML) methods have been applied to intelligently reconstruct the kerogen molecular models through high-throughput and predict shale oil/gas production mechanisms. Although the current work is still in the infancy stage, ML methods are believed to be the most promising way to solve the drawbacks of traditional methods and reconstruct kerogen in reliable and large molecular weight. Hence, mechano-energetics is proposed to study the efficient development and utilization of energy based on mechanics and ML. This paper briefly reviews the development history of kerogen molecular model reconstruction methods and the research of ML in the fields of kerogen reconstruction and shale oil/gas exploitation. Some recommendations for further ML-based work are also suggested. We are convinced that the ML methods will accelerate the research of kerogen and promote the significant development of unconventional oil/gas exploitation technologies.

show abstract

Section: Reconstruction Methods Of Kerogen Modelmentioning

confidence: 99%

Perspectives of Machine Learning Development on Kerogen Molecular Model Reconstruction and Shale Oil/Gas Exploitation

Kang

Zhao

2022

Energy Fuels

View full text Add to dashboard Cite

show abstract

“…Model interpretability refers to the degree to which the predictions of a ML model can be understood by a human [25]. In recent years, various interpretable ML techniques have been proposed.…”

Section: Model Interpretabilitymentioning

confidence: 99%

“…Ante-hoc interpretable techniques involve using algorithms with high transparency during the training process, resulting in a model that is inherently interpretable. For example, linear regression is an ante-hoc model since the coefficients of the linear model can be interpreted as the extent of influence of individual features on the prediction [25]. However, this approach may result in models that are overly simplistic and have inadequate prediction accuracy.…”

Section: Stagementioning

confidence: 99%

Interpretable Predictive Modeling of Tight Gas Well Productivity with SHAP and LIME Techniques

Hou

Zhan

et al. 2023

Energies

View full text Add to dashboard Cite

Accurately predicting well productivity is crucial for optimizing gas production and maximizing recovery from tight gas reservoirs. Machine learning (ML) techniques have been applied to build predictive models for the well productivity, but their high complexity and low interpretability can hinder their practical application. This study proposes using interpretable ML solutions, SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME), to provide explicit explanations of the ML prediction model. The study uses data from the Eastern Sulige tight gas field in the Ordos Basin, China, containing various geological and engineering factors. The results show that the gradient boosting decision tree model exhibits superior predictive performance compared to other ML models. The global interpretation using SHAP provides insights into the overall impact of these factors, while the local interpretation using SHAP and LIME offers individualized explanations of well productivity predictions. These results can facilitate improvements in well operations and field development planning, providing a better understanding of the underlying physical processes and supporting more informed and effective decision-making. Ultimately, this study demonstrates the potential of interpretable ML solutions to address the challenges of forecasting well productivity in tight gas reservoirs and enable more efficient and sustainable gas production.

show abstract

“…6 Importance of attributes to production estimation of Marcellus shale (Bhattacharya et al 2019) Similar concepts were applied to other shale formations such as Bakken shale. Luo et al (2019) investigated the possibility of predicting the productivity of horizontally drilled wells in Bakken shale based on completion and geological parameters. Geology and completion data of 2061 horizontal wells in the Bakken were used.…”

Section: Stimulationmentioning

confidence: 99%

A systematic review of data science and machine learning applications to the oil and gas industry

Tariq

Aljawad

Hasan

et al. 2021

J Petrol Explor Prod Technol

View full text Add to dashboard Cite

This study offered a detailed review of data sciences and machine learning (ML) roles in different petroleum engineering and geosciences segments such as petroleum exploration, reservoir characterization, oil well drilling, production, and well stimulation, emphasizing the newly emerging field of unconventional reservoirs. The future of data science and ML in the oil and gas industry, highlighting what is required from ML for better prediction, is also discussed. This study also provides a comprehensive comparison of different ML techniques used in the oil and gas industry. With the arrival of powerful computers, advanced ML algorithms, and extensive data generation from different industry tools, we see a bright future in developing solutions to the complex problems in the oil and gas industry that were previously beyond the grip of analytical solutions or numerical simulation. ML tools can incorporate every detail in the log data and every information connected to the target data. Despite their limitations, they are not constrained by limiting assumptions of analytical solutions or by particular data and/or power processing requirements of numerical simulators. This detailed and comprehensive study can serve as an exclusive reference for ML applications in the industry. Based on the review conducted, it was found that ML techniques offer a great potential in solving problems in almost all areas of the oil and gas industry involving prediction, classification, and clustering. With the generation of huge data in everyday oil and gas industry activates, machine learning and big data handling techniques are becoming a necessity toward a more efficient industry.

show abstract

Production-Strategy Insights Using Machine Learning: Application for Bakken Shale

Cited by 33 publications

References 22 publications

Perspectives of Machine Learning Development on Kerogen Molecular Model Reconstruction and Shale Oil/Gas Exploitation

Perspectives of Machine Learning Development on Kerogen Molecular Model Reconstruction and Shale Oil/Gas Exploitation

Interpretable Predictive Modeling of Tight Gas Well Productivity with SHAP and LIME Techniques

A systematic review of data science and machine learning applications to the oil and gas industry

Contact Info

Product

Resources

About