Using machine learning for model benchmarking and forecasting of depletion-induced seismicity in the Groningen gas field (original) (raw)
Related papers
Frontiers in Earth Science
Shear sonic log (DTS) availability is vital for litho-fluid discrimination within reservoirs, which is critical for field development and production. For certain reasons, most of the wells in the Lower Indus Basin (LIB) lack DTS logs, which are modeled using conventional techniques based on empirical relations and rock physics modeling. However, in their extensive computation, these approaches need assumptions and multiple prerequisites, which can compromise the true reservoir characteristics. Machine learning (ML) has recently emerged as a robust and optimized technique for predicting precise DTS with fewer input data sets. To predict the best DTS log that adheres to the geology, a comparison was made between three supervised machine learning (SML) algorithms: random forest (RF), decision tree regression (DTR), and support vector regression (SVR). Based on qualitative statistical measures, the RF stands out as the best algorithm, with maximum determination of correlation (R2) value...
In unconventional reservoir sweet-spot identification, brittleness is an important parameter that is used as an easiness measure of production from low permeability reservoirs. In shaly reservoirs, production is realized from hydraulic fracturing, which depends on how brittle the rock is-as it opens natural fractures and also creates new fractures. A measure of brittleness, brittleness index, is obtained through elastic properties of the rock. In practice, problems arise using this method to predict brittleness because of the limited availability of elastic logs. To address this issue, machine learning techniques are adopted to predict brittleness at well locations from readily available geophysical logs and spatially using 3D seismic data. The geophysical logs available as input are gamma ray, neutron, sonic, photoelectric factor, and density logs while the seismic is a post-stack time migrated data of high quality. Support Vector Regression, Gradient Boosting, and Artificial Neural Network are used to predict the brittleness from the geophysical logs and Texture Model Regression to invert the brittleness from the seismic data. The Gradient Boosting outperformed the other algorithms in predicting brittleness. The result of this research further demonstrates the application of machine learning, and how these tools can be leveraged to create data-driven solutions to geophysical problems. Also, the seismic inversion of brittleness shows promising results that will be further investigated in the future.
First International Meeting for Applied Geoscience & Energy Expanded Abstracts
In unconventional reservoir sweet-spot identification, brittleness is an important proxy used as a measure of easiness for oil and gas production. Production from this low permeability reservoir is realized by hydraulic fracturing, which depends on how brittle the rock is-as it opens natural fractures and also creates new fractures. An estimate of brittleness, brittleness index, is obtained at well locations through a mathematical combination of elastic logs. In practice, problems arise to predict brittleness because of the limited availability of elastic logs and sparsity of wells to understand the lateral variation of brittleness. To address this problem, machine learning techniques are adopted to predict brittleness at well locations from readily available geophysical logs and spatially using continuous 3D seismic data. This study tests machine learning algorithms to forecast reservoir brittleness throughout the entire reservoir interval using well logs and 3D seismic in a shale gas field of central Appalachian Basin. Our results show the effectiveness of using gradient boosting to predict brittleness from gamma ray, density, and neutron logs with a training and testing R 2 score of 0.95 and 0.85, respectively. We demonstrate a novel application of seismic texture as an indicator for brittleness through the qualitative agreement of the inversion output with the blind well and also the fracture attribute.
MACHINE LEARNING ALGORITHMS APPLIED TO SEISMIC ACTIVITY
2019
*The paper was submitted as an Extended Essay to the International Baccalaureate Organization in 2019 and earned the highest grade, A. This work explores classic regression and classification algorithms, linear and logistic, as well as the relatively new model Support Vector Machines to determine how the differences in the mathematical formalism of machine learning algorithms affect the accuracy of regression and classification. A dataset containing records of seismic activity in Pakistan was then chosen and the software Weka was used to compare the accuracy of regression and classification of both machine learning algorithms. It was found that they produced similar results.
First International Meeting for Applied Geoscience & Energy Expanded Abstracts, 2021
We carried out a unique workflow for rock property prediction based on supervised artificial neural networks to characterize carbonate reservoirs in the Santos Basin, Brazil. Seismic amplitude, horizon, and depth-based features were used and credibly related to conventional reservoir properties like porosity. We demonstrate the usage of modern data science and model architecture optimization techniques. As a result, we fine-tune the predictive models to reduce over-fitting and achieve better model generalization. We can provide confidence estimates for the rock property predictions. As a part of this study, we also conducted a controlled experiment to measure prediction accuracy's sensitivity to having 4, 8, and 13 wells in model training. The resulting workflow eliminates the subjective background model building and wavelet estimation processes. The machine learning methods produce highresolution rock property volumes to facilitate a faster mapping of reservoir heterogeneity than traditional methods. In this structurally complex pre-salt carbonate play, all results generated using this state-of-the-art technology have excellent matches to blind well control.
Nafta-Gaz, 2022
The application of machine learning (ML) tools and data-driven modeling became a standard approach for solving many problems in exploration geology and contributed to the discovery of new reservoirs. This study explores an application of machine learning ensemble methods – random forest (RF) and extreme gradient boosting (XGBoost) to derive porosity and saturation type (gas/water) in multi-horizon sandstone formations from Miocene deposits of the Carpathian Foredeep. The training of ML algorithms was divided into two stages. First, the RF algorithm was used to compute porosity based on seismic attributes and well location coordinates. The obtained results were used as an extra feature to saturation type modeling using the XGBoost algorithm. The XGBoost was run with and without well location coordinates to evaluate the influence of the spatial information for the modeling performance. The hyperparameters for each model were tuned using the Bayesian optimization algorithm. To check th...
Leak-Off Pressure Using Weakly Correlated Geospatial Information and Machine Learning Algorithms
Geosciences
Leak-off pressure (LOP) is a key parameter to determine the allowable weight of drilling mud in a well and the in situ horizontal stress. The LOP test is run in situ and is frequently used by the petroleum industry. If the well pressure exceeds the LOP, wellbore instability may occur, with hydraulic fracturing and large mud losses in the formation. A reliable prediction of LOP is required to ensure safe and economical drilling operations. The prediction of LOP is challenging because it is affected by the usually complex earlier geological loading history, and the values of LOP and their measurements can vary significantly geospatially. This paper investigates the ability of machine learning algorithms to predict leak-off pressure on the basis of geospatial information of LOP measurements. About 3000 LOP test data were collected from 1800 exploration wells offshore Norway. Three machine learning algorithms (the deep neural network (DNN), random forest (RF), and support vector machine...
Netherlands Journal of Geosciences, 2017
This paper reviews the evolution of a sequence of seismological models developed and implemented as part of a workflow for Probabilistic Seismic Hazard and Risk Assessment of the seismicity induced by gas production from the Groningen gas field. These are semi-empirical statistical geomechanical models derived from observations of production-induced seismicity, reservoir compaction and structure of the field itself. Initial versions of the seismological model were based on a characterisation of the seismicity in terms of its moment budget. Subsequent versions of the model were formulated in terms of seismic event rates, this change being driven in part by the reduction in variability of the model forecasts in this domain. Our approach makes use of the Epidemic Type After Shock model (ETAS) to characterise spatial and temporal clustering of earthquakes and has been extended to also incorporate the concentration of moment release on pre-existing faults and other reservoir topographic ...
Application of Machine Learning in Geotechnical Engineering for Risk Assessment
IntechOpen, 2023
Within the domain of geotechnical engineering, risk assessment is pivotal, acting as the linchpin for the safety, durability, and resilience of infrastructure projects. While traditional methodologies are robust, they frequently require extensive manual efforts and can prove laborious. With the onset of the digital era, machine learning (ML) introduces a paradigm shift in geotechnical risk assessment. This chapter delves into the confluence of ML and geotechnical engineering, spotlighting its enhanced predictive capabilities regarding soil behaviors, landslides, and structural resilience. Harnessing modern datasets and rich case studies, we offer an exhaustive examination that highlights the transformative role of ML in reshaping geotechnical risk assessment practices. Throughout our exploration of evolution, challenges, and future horizons, this chapter emphasizes the significance of ML in advancing and transforming geotechnical practices.
Applicability of Statistical Learning Algorithms for Seismic Attenuation Prediction
civil.iitb.ac.in
Four algorithms are outlined, each of which has interesting features for predicting contaminant levels in groundwater. Artificial neural networks (ANN), support vector machines (SVM), locally weighted projection regression (LWPR), and relevance vector machines (RVM) are utilized as surrogates for a relatively complex and time-consuming mathematical model to simulate nitrate concentration in groundwater at specified receptors. Nitrates in the application reported in this paper are due to on-ground nitrogen loadings from fertilizers and manures. The practicability of the four learning machines in this work is demonstrated for an agriculture-dominated watershed where nitrate contamination of groundwater resources exceeds the maximum allowable contaminant level at many locations. Cross-validation and bootstrapping techniques are used for both training and performance evaluation. Prediction results of the four learning machines are rigorously assessed using different efficiency measures to ensure their generalization ability. Prediction results show the ability of learning machines to build accurate models with strong predictive capabilities and hence constitute a valuable means for saving effort in groundwater contamination modeling and improving model performance.