scholarly journals New Hybrid Approach for Developing Automated Machine Learning Workflows: A Real Case Application in Evaluation of Marcellus Shale Gas Production

Fuels ◽  
2021 ◽  
Vol 2 (3) ◽  
pp. 286-303
Author(s):  
Vuong Van Pham ◽  
Ebrahim Fathi ◽  
Fatemeh Belyadi
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Shale Gas ◽  
Field Data ◽  
Marcellus Shale ◽  
Hybrid Approach ◽  
Gas Production ◽  
Bayesian Optimization ◽  
Real Field ◽  
Engineering Problems

The success of machine learning (ML) techniques implemented in different industries heavily rely on operator expertise and domain knowledge, which is used in manually choosing an algorithm and setting up the specific algorithm parameters for a problem. Due to the manual nature of model selection and parameter tuning, it is impossible to quantify or evaluate the quality of this manual process, which in turn limits the ability to perform comparison studies between different algorithms. In this study, we propose a new hybrid approach for developing machine learning workflows to help automated algorithm selection and hyperparameter optimization. The proposed approach provides a robust, reproducible, and unbiased workflow that can be quantified and validated using different scoring metrics. We have used the most common workflows implemented in the application of artificial intelligence (AI) and ML in engineering problems including grid/random search, Bayesian search and optimization, genetic programming, and compared that with our new hybrid approach that includes the integration of Tree-based Pipeline Optimization Tool (TPOT) and Bayesian optimization. The performance of each workflow is quantified using different scoring metrics such as Pearson correlation (i.e., R2 correlation) and Mean Square Error (i.e., MSE). For this purpose, actual field data obtained from 1567 gas wells in Marcellus Shale, with 121 features from reservoir, drilling, completion, stimulation, and operation is tested using different proposed workflows. A proposed new hybrid workflow is then used to evaluate the type well used for evaluation of Marcellus shale gas production. In conclusion, our automated hybrid approach showed significant improvement in comparison to other proposed workflows using both scoring matrices. The new hybrid approach provides a practical tool that supports the automated model and hyperparameter selection, which is tested using real field data that can be implemented in solving different engineering problems using artificial intelligence and machine learning. The new hybrid model is tested in a real field and compared with conventional type wells developed by field engineers. It is found that the type well of the field is very close to P50 predictions of the field, which shows great success in the completion design of the field performed by field engineers. It also shows that the field average production could have been improved by 8% if shorter cluster spacing and higher proppant loading per cluster were used during the frac jobs.

Quantitative Prediction of Radon Concentration at Wellhead in Shale Gas Development

SPE Journal ◽  
2016 ◽  
Vol 22 (01) ◽  
pp. 235-243 ◽  
Author(s):  
Wei Tian ◽  
Xingru Wu ◽  
Tong Shen ◽  
Zhenyu Zhang ◽  
Sumeer Kalra
Keyword(s):  
Natural Gas ◽  
Numerical Simulations ◽  
Shale Gas ◽  
Radon Concentration ◽  
Marcellus Shale ◽  
Gas Production ◽  
Influential Factors ◽  
Natural Fracture ◽  
Quantitative Prediction ◽  
Radon Gas

Summary Hydraulic fracturing has been applied as an effective method to increase gas production from shale formations; however, this method has also raised concerns about its adverse impacts on environment. For example, in the Marcellus shale formation, some measured radon-gas concentrations exceeded the safe standard. Therefore, it is important to quantitatively evaluate radon concentration from fractured wells. However, existing researches have not successfully conducted a systematic and predictive study on the relationship between shale gas production and radon concentration at the wellhead of a hydraulically fractured well. To address this issue and quantitatively determine the radon concentration, we present the mechanisms of radon-gas generation and releasing, and conducted numerical simulations on its transport process in the subsurface formation system. The concentration of radon in produced gas is related with the original sources where the natural gas is extracted. Radon, generated from the radium alpha decay process, is trapped in pore spaces before the reservoir development. With the fluid flowing through the subsurface network, released radon will move to surface with the produced streams such as natural gas and flowback water. Our study shows that the radon concentration at wellhead could be significant. Influential factors such as natural-fracture-network properties, formation petrophysical parameters, and fracture dimension are investigated with sensitivity studies through numerical simulations. Analysis results suggest that radon wellhead concentration is strongly related with production rate. Thus, careful production design and protection are necessary to reduce radon hazard regarding the public and environmental impact.

scholarly journals Emerging unconventional shale plays in Western Australia

2013 ◽  
Vol 53 (1) ◽  
pp. 313 ◽  
Author(s):  
K. Ameed R. Ghori
Keyword(s):  
Shale Gas ◽  
Early Stage ◽  
Marcellus Shale ◽  
Gas Production ◽  
Source Rocks ◽  
Lower Permian ◽  
Upper Ordovician ◽  
Canning Basin ◽  
The Us ◽  
Gas Potential

Production of shale gas in the US has changed its position from a gas importer to a potential gas exporter. This has stimulated exploration for shale-gas resources in WA. The search started with Woodada Deep–1 (2010) and Arrowsmith–2 (2011) in the Perth Basin to evaluate the shale-gas potential of the Permian Carynginia Formation and the Triassic Kockatea Shale, and Nicolay–1 (2011) in the Canning Basin to evaluate the shale-gas potential of the Ordovician Goldwyer Formation. Estimated total shale-gas potential for these formations is about 288 trillion cubic feet (Tcf). Other petroleum source rocks include the Devonian Gogo and Lower Carboniferous Laurel formations of the Canning Basin, the Lower Permian Wooramel and Byro groups of the onshore Carnarvon Basin, and the Neoproterozoic shales of the Officer Basin. The Canning and Perth basins are producing petroleum, whereas the onshore Carnarvon and Officer basins are not producing, but they have indications for petroleum source rocks, generation, and migration from geochemistry data. Exploration is at a very early stage, and more work is needed to estimate the shale-gas potential of all source rocks and to verify estimated resources. Exploration for shale gas in WA will benefit from new drilling and production techniques and technologies developed during the past 15 years in the US, where more than 102,000 successful gas production wells have been drilled. WA shale-gas plays are stratigraphically and geochemically comparable to producing plays in the Upper Ordovician Utica Shale, Middle Devonian Marcellus Shale and Upper Devonian Bakken Formation, Upper Mississippian Barnett Shale, Upper Jurassic Haynesville-Bossier formations, and Upper Cretaceous Eagle Ford Shale of the US. WA is vastly under-explored and emerging self-sourcing shale plays have revived onshore exploration in the Canning, Carnarvon, and Perth basins.

Artificial Intelligence AI Assisted Thermography to Detect Corrosion Under Insulation CUI

2021 ◽  
Author(s):  
Ayman Amer ◽  
Ali Alshehri ◽  
Hamad Saiari ◽  
Ali Meshaikhis ◽  
Abdulaziz Alshamrany
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Oil And Gas ◽  
Assessment Tool ◽  
Oil And Gas Industry ◽  
Real Field ◽  
Learning Approach ◽  
Real Time System ◽  
Gas Industry ◽  
Corrosion Under Insulation

Abstract Corrosion under insulation (CUI) is a critical challenge that affects the integrity of assets where the oil and gas industry is not immune. Its severity arises due to its hidden nature as it can often times go unnoticed. CUI is stimulated, in principle, by moisture ingress through the insulation layers to the surface of the pipeline. This Artificial Intelligence (AI)-powered detection technology stemmed from an urgent need to detect the presence of these corrosion types. The new approach is based on a Cyber Physical (CP) system that maximizes the potential of thermographic imaging by using a Machine Learning application of Artificial Intelligence. In this work, we describe how common image processing techniques from infra-red images of assets can be enhanced using a machine learning approach allowing the detection of locations highly vulnerable to corrosion through pinpointing locations of CUI anomalies and areas of concern. The machine learning is examining the progression of thermal images, captured over time, corrosion and factors that cause this degradation are predicted by extracting thermal anomaly features and correlating them with corrosion and irregularities in the structural integrity of assets verified visually during the initial learning phase of the ML algorithm. The ML classifier has shown outstanding results in predicting CUI anomalies with a predictive accuracy in the range of 85 – 90% projected from 185 real field assets. Also, IR imaging by itself is subjective and operator dependent, however with this cyber physical transfer learning approach, such dependency has been eliminated. The results and conclusions of this work on real field assets in operation demonstrate the feasibility of this technique to predict and detect thermal anomalies directly correlated to CUI. This innovative work has led to the development of a cyber-physical that meets the demands of inspection units across the oil and gas industry, providing a real-time system and online assessment tool to monitor the presence of CUI enhancing the output from thermography technologies, using Artificial Intelligence (AI) and machine learning technology. Additional benefits of this approach include safety enhancement through non-contact online inspection and cost savings by reducing the associated scaffolding and downtime.

scholarly journals The concept of well integrity in gas production activities

2016 ◽  
Vol 23 (2) ◽  
pp. 205-213 ◽  
Author(s):  
Peter Reichetseder
Keyword(s):  
Drinking Water ◽  
Shale Gas ◽  
Environmental Protection Agency ◽  
Marcellus Shale ◽  
The United States ◽  
Gas Production ◽  
Well Integrity ◽  
Drinking Water Resources ◽  
The Us ◽  
Geological Situation

Abstract Shale gas production in the US, predominantly from the Marcellus shale, has been accused of methane emissions and contaminating drinking water under the suspicion that this is caused by hydraulic fracturing in combination with leaking wells. Misunderstandings of the risks of shale gas production are widespread and are causing communication problems. This paper discusses recent preliminary results from the US Environmental Protection Agency (EPA) draft study, which is revealing fact-based issues: EPA did not find evidence that these mechanisms have led to widespread, systemic impacts on drinking water resources in the United States, which contrasts many broad-brushed statements in media and public. The complex geological situation and extraction history of oil, gas and water in the Marcellus area in Pennsylvania is a good case for learnings and demonstrating the need for proper analysis and taking the right actions to avoid problems. State-of-the-art technology and regulations of proper well integrity are available, and their application will provide a sound basis for shale gas extraction.

scholarly journals The Collaboration between Hearing Aid Users and Artificial Intelligence to Optimize Sound

2021 ◽  
Vol 42 (03) ◽  
pp. 282-294
Author(s):  
Laura Winther Balling ◽  
Lasse Lohilahti Mølgaard ◽  
Oliver Townend ◽  
Jens Brehm Bagger Nielsen
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Signal Processing ◽  
Hearing Aids ◽  
Hearing Aid ◽  
Bayesian Optimization ◽  
Listening Environments ◽  
User Data ◽  
The Individual ◽  
Average User

AbstractHearing aid gain and signal processing are based on assumptions about the average user in the average listening environment, but problems may arise when the individual hearing aid user differs from these assumptions in general or specific ways. This article describes how an artificial intelligence (AI) mechanism that operates continuously on input from the user may alleviate such problems by using a type of machine learning known as Bayesian optimization. The basic AI mechanism is described, and studies showing its effects both in the laboratory and in the field are summarized. A crucial fact about the use of this AI is that it generates large amounts of user data that serve as input for scientific understanding as well as for the development of hearing aids and hearing care. Analyses of users' listening environments based on these data show the distribution of activities and intentions in situations where hearing is challenging. Finally, this article demonstrates how further AI-based analyses of the data can drive development.

Acadian hinterland-vergent detachment structures in the southwestern Appalachian Plateau: Implications for the Marcellus Shale gas exploration and production

2018 ◽  
Vol 6 (4) ◽  
pp. SN85-SN99 ◽  
Author(s):  
Dengliang Gao ◽  
Thomas Donahoe ◽  
Taizhong Duan ◽  
Peter Sullivan
Keyword(s):  
Shale Gas ◽  
Middle Devonian ◽  
Marcellus Shale ◽  
Three Dimensional ◽  
Gas Production ◽  
Seismic Facies ◽  
Seismic Structure ◽  
Appalachian Plateau ◽  
Structural Style ◽  
Exploration And Production

Three-dimensional seismic data in southwestern Pennsylvania in the Appalachian Plateau demonstrate that the structural style in the Devonian section is dominated by east-vergent folds and reverse faults, which contrasts with that in the Valley and Ridge Province where west-vergent folds and thrusts dominate. Vertical (cross-stratal) variations in fold curvature and fault throw indicate that the intensity of shortening increases from the Salina (Upper Silurian) to the Onondaga (Middle Devonian) and then decreases from the Onondaga to the Elk (Upper Devonian). Lateral (along-stratal) variations in fold curvature and fault throw indicate that the folds and faults tend to propagate in the cross-strike and along-strike directions. Isochron thickness below the Onondaga increases on the anticlinal, up-thrown side of the faults, whereas isochron thickness above the Onondaga increases to the synclinal, down-thrown side of the faults. In concert with seismic structure and isochron thickness, seismic facies see vertical and lateral variations that are spatially and temporally related to folds and faults. Four years of gas production data from the Middle Devonian Marcellus Shale show that the gas productivity drops near the regional reverse faults, whereas regional drilling patterns from a broader perspective of the Plateau reveal operational gaps near major cross-regional wrench faults. These observations are indicative of the dynamic interplay among hinterland-vergent detachment deformation, syntectonic sedimentation, and shale gas preservation during the Acadian (Middle Devonian–Early Mississippian).

Sign in / Sign up

Export Citation Format

Share Document