- Home
- Conferences
- Conference Proceedings
- Conferences
Second EAGE Subsurface Intelligence Workshop
- Conference date: October 28-31, 2022
- Location: Manama, Bahrain
- Published: 28 October 2022
-
-
Predicting Porosity Through Machine Learning
Authors R. Alkheliwi and M. AlhussainSummaryPorosity is a critical reservoir property that is indicative of existence of hydrocarbons during exploration phase. However, neutron porosity which is a measure of this property is usually obtained through wireline logs after a drilling run. In this work, porosity is predicted from conventional logs such as drilling logs, mud gases, and depth. This work shows optimal results that can at a later stage be generalized to other wireline logs and be implemented in a production system.
-
-
-
Well Connectivity Evaluation Based on Additive Explanations
Authors A. Voskresenskiy, N. Bukhanov, K. Katterbauer and A. AlshehriSummaryWell connectivity is an essential outcome of dynamic data analysis during reservoir development. It allows to understand interconnections between injection and producer wells and optimize decision making process. Conventionally this analysis requires physics-driven models like fluid flow through porous media simulation or Capacity Resistance Models (CRM). We propose data-driven approach which is based on deep learning models applied to vast amount of time series data which represents production profiles for benchmark reservoir. Deep learning models, namely Gradient Boosting (CatBoost) and Long Short-Term Memory neural networks (LSTM) are used as a basis for additive explanation algorithm. In order to validate our approach, we compare results with similarity measures and causal inference methods for time series.
-
-
-
Deep-Learning Approach to Auto-Label Processing Domains for Seismic Data
Authors A. Bin Mahfoodh and S. AlsubaieSummaryMany data formats for processed seismic data lack the availability of having a standard placeholder for indicating the processing domain for the given seismic file, and this can lead to having seismic files with missing or incorrect processing domains. A geoscientist may experience difficulties in locating required seismic stacks, in an area of interest, with unavailable indexed labels for processing domains.
To overcome this problem, we propose a data-driven approach to automate labeling and classifying stacked seismic data based on their processing domains (depth or time) by applying image processing techniques and train a deep learning model using convolutional neural networks (CNN). The proposed approach shows promising results on automatically labeling thousands of legacy and newly uploaded stacked seismic files in a corporate database with up to 90% accuracy level. This auto-labeling mechanism is based on a confidence level as a percentage and flagged as an auto-generated meta-data to differentiate between human and machine annotated data.
-
-
-
A Wasserstein GAN with Gradient Penalty for 3D Porous Media Generation.
Authors M. Corrales, M. Izzatullah, H. Hoteit and M. RavasiSummaryLinking the pore-scale and reservoir-scale subsurface fluid flow remains an open challenge in areas such as oil recovery and Carbon Capture and Storage (CCS). One of the main factors hindering our knowledge of such a process is the scarcity of physical samples from geological areas of interest. One way to tackle this issue is by creating accurate, digital representations of the available rock samples to perform numerical fluid flow simulations. Recent advancements in Machine Learning and Deep Generative Modeling open up a new promising avenue for generating realistic digital rock samples at low cost. This is particularly the case for Generative Adversarial Networks (GANs) due to their ability to learn complex high-dimensional distributions and produce high-quality samples. The present study introduces a novel Wasserstein GAN with gradient penalty (WGAN-GP) to generate 3D high-quality porous media samples. Moreover, a comprehensive set of evaluation metrics inspired by the geometry and topology of the structure and the fluid flow properties is established to assess the quality of the generative process.
-
-
-
The Clock is Ticking: AI as a Hydrocarbon Exploitation Accelerator
Authors D. Stoddart, A. Kvalheim, B. Alaei, D. Oikonomou and E. LarsenSummaryEarth Science Analytics presents an AI/ML driven workflow for the finding and exploitation of hydrocarbons that not only facilitates the disappearance of data silos (digitalization journey) but acts as a much needed exploration accelerator (data analytics and decision making journey). The proposed methodology empowers all geoscientists alike to easily leverage the potential of ML to find and exploit hydrocarbons, and when combined with established explorations methods and domain specialists forms a formidable tool. We will give relevant examples that lend credence to the application of ML to finding hydrocarbons close to infrastructure.
-
-
-
Production Acceleration for a Mature Waterflood in Kuwait through Predictive Model Combining ML with Reservoir Physics
Authors C. Calad, M. Samir, S. Plotno, G. Castano, P. Sarma, K.A. Ziyab, A. Al-Sagheer and N. Faisal Al-KhedhairSummaryThe paper describes the application of Data Physics (physics embedded machine learning) to model and optimize a large mature field in the province of KOC West Kuwait Asset. The field has been in production since 1959 and water-flooding started in 2003. The field has currently close to 100 active producers and 15 injectors. After creating the Data Physics model, an optimization workflow using evolutionary algorithms was run to generate injection optimum prescription, resulting in a potential production increase of 5% maintaining the current injection levels and hence with no significant increase of cost.
-
-
-
Machine Learning and Seismic Structural Attributes Hybrid Approach to Map Complex Fault System
Authors M.K. Khan, Y. Bashir, S. Dossary, S.S. Ali and G. Janampa AnanosSummaryThis paper present a hybrid Machine Learning and seismic structural attributes approach to extract detailed major and minor discontinuities from seismic data from a complex fault system that present a challenge using conventional interpretation techniques. Fault interpretation is image segmentation problem and we thus adopted U-net encoder-decoder architecture as a first step in this hybrid workflow, it is well suited for seismic discontinuities. Image segmentation can not only figure out whether a particular feature such as faults exist but can also create a mask showing where in the volume those features exist.
-
-
-
Challenges in AI-Based Geological Cutting Description Text Documents Structuring
Authors M. Mezghani, E. Tirikov, N. AlAnsari and M. AlDomainiSummaryApplying Artificial Intelligence technology to analyze data requires the availability of a clean dataset that can be used for the training step (predictive model training). Geological cutting samples description is one of the disciplines where artificial intelligence can be applied to automate the cutting samples description. In this presentation, we will share our implemented workflow for cutiing description documents structuring.
-
-
-
Integrated ML Approach Combining Image and Sonic Data for Geomechanical Property Analysis of Thin-Bedded Wolfcamp formation
Authors S. Das, A. Wray, E. Haddad, S. Bhadra and H. ManchandaSummaryAdvances in an integrated, physics-driven approach to reservoir characterization can be applied to enhance efficiencies in the development of unconventional reservoirs. The optimized production of unconventional reservoirs is dependent on lateral wellbore placement and completion practices. A high-resolution image-derived geomechanical model and Hayman factor-driven thin-bed analysis can provide enhanced characterization of unconventional reservoirs. Dipole sonic-derived mechanical property outputs do not adequately resolve thin beds and therefore do not provide a representative characterization of the reservoir for stimulation modelling and subsequent completion optimization. A novel workflow utilizing inversion modelling and regression analysis has been proposed to address this challenge of under-characterization of unconventional reservoirs. The workflow, applied to the Wolfcamp Formation in this example, integrates high-resolution borehole image data, and geo-mechanical logs. Ultimately, the workflow aims to support optimized lateral target selection through an enhanced understanding of the impact of the high-resolution rock properties on reservoir quality and drilling & completion performance. By integrating the results of this new workflow with other available downhole data and calibration to core, it is considered that the existing data resolution blind spot encountered with characterizing many unconventional reservoirs can be significantly reduced in a cost-effective manner.
-
-
-
Application of Machine Learning for Analytical Insight from Multiple Geoscience Support Databases to Enhance Service Delivery
Authors S. Ali Syed, M.H. Badar, R.M. Alkheliwi, L. Deng, M. Ashraf and M. KhanSummarySyed Sadaqat Ali is a Geophysical Consultant at Saudi Aramco’s Exploration and Petroleum Engineering Computer Center Organization (EXPEC). His group is responsible for providing leading edge geoscience computing solutions to the entire Exploration organization. Prior to joining Saudi Aramco in 2008, Sadaqat was managing consultant for Halliburton MENA. Sadaqat’s experience working closely with the major commercial technologies has led him to witness the advancement in geoscience technologies over the past 3 decade. Sadaqat holds M.Sc in Exploration Geophysics(Quaid-e-Azam University, Pakistan). His current field of interest is in applications of Deep learning to Geosciences. Sadaqat is a member of SEG, EAGE and AAPG.
-
-
-
Physics Informed Seismic Deblending Using a Self-Supervised Denoiser
More LessSummarySimultaneous sources aims at reducing the acquisition time of seismic surveys by either firing multiple sources at the same time, or closely after one another. This leads to entangled seismic data that has to be untangled in order to be meaningful for processing and imaging purposes. Untangling the seismic data amounts to solving an underdetermined linear inverse problem. The blending operator introduces coherent overlapping seismic events in the source gathers, but in the receiver gathers the entangled data will appear as noise. To obtain meaningful seismic data, we have to add regularization to filter this noise. In this work we propose the use of a self-supervised denoiser that filters the blending noise, that is cleverly coupled with the blending operator. Our algorithm thereby combines the physics of the blending process through the blending operator with a highly effective self-supervised denoiser. The denoiser requires no ground-truth labels or pre-training on synthetic data, which is a huge benefit over other machine learning algorithms.
-
-
-
Plug and Play Post-Stack Seismic Inversion with CNN-Based Denoisers
Authors J. Romero, M. Corrales, N. Luiken and M. RavasiSummarySeismic inversion is the prime method to estimate subsurface properties from seismic data. However, such inversion is a notoriously ill-posed inverse problem due to the band-limited and noisy nature of the data. Consequently, the data misfit term must be augmented with appropriate regularization that incorporates prior information about the sought-after solution. Conventionally, model-based regularization terms are problem-dependent and hand-crafted; this can limit the modeling capability of the inverse problem. Recently, a new framework has emerged under the name of Plug-and-Play (PnP) regularization, which suggests reinterpreting the effect of the regularizer as a denoising problem. Convolutional neural networks-based denoisers are state-of-the-art methods for image denoising: their adoption in the PnP framework has led to algorithms with improved capabilities over classical regularization in computer vision and medical imaging applications. In this work, we present a comparison between standard model-based and data-driven regularization techniques in post-stack seismic inversion and give some insights into the optimization and denoiser-related parameters tuning. The results on synthetic seismic data indicate that PnP regularization using a bias-free CNN-based denoiser with an additional noise map as input can outperform standard model-based methods.
-
-
-
Extracting Surface Wave Dispersion Curves with Deep Learning
Authors D. Chamorro, J. Zhao, C. Birnie, M. Staring, M. Fliedner and M. RavasiSummaryMulti-channel Analysis of Surface Waves (MASW) is a seismic method employed to obtain useful information about the shear-wave velocities of the subsurface. A fundamental step in the methodology is the extraction of dispersion curves from dispersion spectra obtained after applying specific processing algorithms; to some extent, this extraction can be automated. However, it still requires extensive quality control, which can be time-demanding in large dataset scenarios. We present a novel approach that leverages deep learning to automatically identify a direct mapping between seismic shot gathers at the associated dispersion curves. Given a site of interest, a set of 1D velocity models is created using prior knowledge of the local geology; pairs of seismic shot gathers and Rayleigh-wave phase dispersion curves are then numerically modeled and used to train a simplified residual network. The proposed approach is shown to achieve satisfactory predictions of dispersion curves on a synthetic test dataset and is ultimately deployed on a field dataset. The predicted dispersion curves are finally inverted, and the resulting shear-wave velocity model is plausible and consistent with prior geological knowledge of the area.
-
-
-
Machine Learning to Map Complex Salt Dome Structures
Authors O. Alsalmi, S. Dossary and G. AnanosSummaryWe developed a robust method based on convolutional neural network (CNN) for salt-body delineation from 2D seismic data. CNN builds an optimal mapping relationship between the seismic signals and the salt-bodies directly from the reflection amplitude, which avoids the process of manual selection where interpretation labor is intensive and interpreter bias might be introduced. Experimental results from our method show high accuracy predictions with fast inference time. This method of detecting Salt-bodies automatically and efficiently will have significant implications for hydrocarbon accumulation and sealing discovery in petroleum reservoirs.
-
-
-
A Machine Learning Workflow for Depositional Environment Prediction from Microfossil Observations
Authors M. Al Ibrahim and M. MezghaniSummaryBiostratigraphic analysis is one of the important tasks in determining the paleodepositional environment of subsurface rocks. This task is traditionally done by a biostratigrapher and involves recording microfossil observations from thin sections and interpreting these observations. Because the collected data can contain tens of microfossil species, an expert is needed to perform the correct interpretation. This work applies machine learning, specifically, ensemble decision trees, in predicting the paleodepositional environment from microfossil observations. The methodology is applied on data collected from forty-four wells. Results showed that data cleaning and data conditioning are essential steps for constructing a reliable model that can be used in understanding the depositional environment. Ensemble decision trees strike a good balance between obtaining good accuracy and allowing explainability. Finally, data imbalance is a problem in real-world datasets that must be addressed to produce better accuracy. Overall, machine learning allows for the integration of biostratigraphic data with other geologic observations, e.g., rock texture, to produce a consistent interpretation. A larger scale automated pipeline can be applied on the database to produce predictions as new data is inputted.
-
-
-
Toward Autonomous Wellsite Geology: Artificial Intelligence for Cutting Lithology Prediction
Authors M. Mezghani and E. TolstayaSummaryDrill cutting samples are valuable data that cover the major part of drilled well compared to the core samples that cover only a limited depth interval. Therefore, accurate and objective cutting description plays major role in decision making while drilling, in the reservoir characterization studies, and in modeling workflows. We developed an Artificial Intelligence workflow to automatically predict cutting lithology percentages using cutting photos. The workflow can be applied near-real-time as soon as photos are acquired.
-
-
-
ML-Aware Synthetic Data Generation
By S. TsimferSummarySeismic interpretation automation has been on the rise for the last few years: new emerging technologies, especially deep neural networks, have been successfully applied for detection numerous types of structural and geological patterns.
Unfortunately, the quality of such models directly depends on the quality and amount of training data. While historic and archive fields may provide enough material for prototypes and hypothesis testing, it is nowhere near the needed amount of data for truly production-ready algorithms.
To alleviate this problem, we’ve developed a synthetic generator, targeted specifically at model training. Despite being based on trivial assumptions and physical models, it uses a number of techniques to improve variation of created images, while keeping them look alike to real seismic surveys. With its help, we’ve been able to enhance the performance of our fault and horizon tracking models, as well as to tackle the seismic acoustic inversion task.
-