- Home
- A-Z Publications
- First Break
- Previous Issues
- Volume 41, Issue 2, 2023
First Break - Volume 41, Issue 2, 2023
Volume 41, Issue 2, 2023
-
-
An Overview of Deep Geothermal Energy and Its Potential on the Island of Ireland
SummaryThis paper provides a short overview of geothermal energy, including a discussion on the key geological controls on heat distribution in the subsurface, and on the different types of geothermal resource and their potential uses. We then discuss the island of Ireland as an example of the role that geothermal energy can play in decarbonising the heat sector in a region characterised by relatively low-enthalpy (temperature) resources. Significant shallow geothermal potential exists across the island via the deployment of ground source heat pumps. The geology of onshore Ireland provides relatively limited potential for deep hydrothermal aquifers with primary porosity and permeability. Therefore, deep geothermal exploration on the island is likely to be focused on fractured carbonate reservoirs of Carboniferous age, with recorded groundwater temperatures reaching 38°C at 1 km depth, or on lower permeability petrothermal reservoirs developed as Enhanced or Advanced Geothermal Systems. The exception to this occurs within Mesozoic basins in Northern Ireland where porous and permeable Permo-Triassic sandstones are preserved beneath Paleogene basalts. Geothermal potential also exists in equivalent basins immediately offshore Ireland. For example, Triassic sandstones within the Kish Bank Basin, a few kilometres off the coast of Dublin, have estimated reservoir temperatures of 20–120°C across the basin.
-
-
-
Motion Sensor Noise Attenuation Using Deep Learning
Authors Bagher Farmani, Yash Pal, Morten W. Pedersen and Edwin HodgesAbstractA method is proposed to attenuate both instrumental and environmental noise from motion sensor records in multisensor streamer acquisition. The main elements are two convolutional neural network models. The first model attenuates vertical narrow band high amplitude noise mainly generated by the instruments attached to the streamers. The second model attenuates widespread background noise mainly associated with environmental conditions. To reduce the risk of possible signal loss an addback flow in the curvelet domain is used. The motivation for the work presented here was to develop a fully automated noise attenuation method that eliminates the need for time-consuming and subjective user parameter testing. The method has been validated using seismic data from different parts of the world and shown to consistently produce superior results to other state-of-the-art noise attenuation processes.
-
-
-
Derivation of rock's geomechanical parameters while drilling by combining surface drilling data, gamma ray data, and machine learning techniques in carbonate formations
Authors Ivo Colombo and Eliana R. RussoAbstractThis work presents a field application of an effective and reliable methodology for geomechanical parameters evaluation, using surface logging drilling data (rate of penetration, torque, weight on bit, stand pipe pressure, rotation per minute, flow rates) and well log data (sonic log, bulk density log, gamma ray log) to feed a model characterised by the combination of different machine learning algorithms (multiple linear regression, support vector regression, random forest, artificial neural network, and XGBoost). To expand the range of application to those cases where the downhole tools are not technically feasible or economically viable, a flexible workflow has been developed to derive a Synthetic Gamma Ray (SGR) from X-ray Fluorescence (XRF) analysis performed on cuttings.
The methodology, applied to a dataset of 11 wells drilled in the same geological units but in different fields in Kuwait, proves its successful use to derive several geomechanical parameters, among which the results associated with Young’s Modulus, density, and Poisson’s Ratios are here presented.
-
-
-
How Reusing Trained Machine Learning Models Accelerates and Improves the Work of Operational Geoscientists
Authors Paul de Groot and Hesham RefayeeAbstractWe show examples of trained machine learning models that are applied ‘AS IS’ to solve similar problems on unseen datasets. A huge benefit of this methodology is the speed of application. Operational geoscientists simply select a model from a library of trained models and apply this to their data. Within minutes they have a result that they can either use, or discard. In many cases, the alternative solution involves expensive and time-consuming reprocessing efforts. We show examples of detecting features, enhancing data, and predicting missing data.
-
-
-
Seismic Avo Attributes and Machine Learning Techniques Characterise a Distributed Carbonate Build-Up Deposit System in the Salawati Basin, Eastern Indonesia
Authors Yudistira Effendi and Lilik T. HardantoAbstractThere are several undeveloped discoveries and drill-ready prospects in the Salawati Basin, Eastern Indonesia, especially offshore. These offer significant growth potential, particularly the challenging Miocene hydrocarbon-producing reservoirs. The seismic data suggests that this play extends to the north of the producing area, but this has not been confirmed by a successful well. The combination of standard seismic attributes with seismic Amplitude Variation with Offset (AVO) attributes is key to revealing the reservoir in the exploration phase.
In this project, poststack attributes from an AV O inversion were used as input for an unsupervised clustering technique based on a Growing Neural Gas algorithm, to generate the most probable facies distribution as well as the probability per facies, in order to better characterise a complex regional channel deposition system.
The classification of AVO-related seismic attributes as direct hydrocarbon indicators is used to extrapolate reservoir information from the seismic data that correlates with well data from surrounding fields.
The study demonstrates that seismic volume-based unsuper-vised facies classification associated with advanced visualisation and detection helps delineate the prospect’s potential. In this example, the workflow identified a reservoir within the Kais interval of the Miocene Carbonate. The model also shows lateral variations in other reservoir intervals and contributes to the exploration hydrocarbon strategy.
-
-
-
Harnessing Machine Learning in the Subsurface to Promote Operational Efficiency
By Chris HantonAbstractMachine learning, despite having more than 50 years of history in subsurface disciplines, has largely remained a niche workflow, frequently performed in isolation with lack of repeatability. While advances in computing and programming language have opened up access to machine learning as a tool, we have yet to see the same growth in operational efficiency experienced by other segments and verticals within the energy industry. Application of ML toward data conditioning and workflow set-up could save geoscientists hundreds of hours each year, allowing for faster delivery of results and improving standardisation and consistency across departments.
-
-
-
A Machine Learning Workflow for Log Data Prediction at the Basin Scale
Authors Keyla Gonzalez, Olga Brusova and Alejandro ValencianoSummaryLog data recorded by wireline tools are incomplete in most well locations. Vital information often needs to be predicted to precisely characterise the Earth’s subsurface. Here we describe a machine learning (ML) workflow to predict missing data in well logs at the basin scale. The ML models produce outstanding results when adequate quality data is provided for the model training and inference. Using examples from the Permian Basin in the US, we illustrate the use of the automated data clean-up pipeline and the clean-up impact on ML algorithm training and prediction. The ML models achieve a prediction quality of 90% to 95% in a blind test containing 679 wells if trained on clean data from the Permian Basin.
-
Volumes & issues
-
Volume 42 (2024)
-
Volume 41 (2023)
-
Volume 40 (2022)
-
Volume 39 (2021)
-
Volume 38 (2020)
-
Volume 37 (2019)
-
Volume 36 (2018)
-
Volume 35 (2017)
-
Volume 34 (2016)
-
Volume 33 (2015)
-
Volume 32 (2014)
-
Volume 31 (2013)
-
Volume 30 (2012)
-
Volume 29 (2011)
-
Volume 28 (2010)
-
Volume 27 (2009)
-
Volume 26 (2008)
-
Volume 25 (2007)
-
Volume 24 (2006)
-
Volume 23 (2005)
-
Volume 22 (2004)
-
Volume 21 (2003)
-
Volume 20 (2002)
-
Volume 19 (2001)
-
Volume 18 (2000)
-
Volume 17 (1999)
-
Volume 16 (1998)
-
Volume 15 (1997)
-
Volume 14 (1996)
-
Volume 13 (1995)
-
Volume 12 (1994)
-
Volume 11 (1993)
-
Volume 10 (1992)
-
Volume 9 (1991)
-
Volume 8 (1990)
-
Volume 7 (1989)
-
Volume 6 (1988)
-
Volume 5 (1987)
-
Volume 4 (1986)
-
Volume 3 (1985)
-
Volume 2 (1984)
-
Volume 1 (1983)