The new-generation oil-base mud (OBM) microresistivity imagers provide photorealistic high-resolution quantified formation imaging. One of the existing interpretation methods is based on composite processing providing an apparent resistivity image largely free of the standoff effect. Another one is the inversion-based workflow, which is an alternative quantitative interpretation, providing a higher quality resistivity image, button standoff, and formation permittivities at two frequencies. In this work, a workflow based on artificial neural networks (NNs) is developed for quantitative interpretation of OBM imager data as an alternative to inversion-based workflow.
The machine learning approach aims to achieve at least the inversion-level quality in formation resistivity, permittivity, and standoff images an order of magnitude faster, making it suitable for implementation on automated interpretation services as well as integration with other machine learning based algorithms. The major challenge is the underdetermined problem since OBM imager provides only four measurements per button, and eight model parameters related to formation, mud properties, and standoff need to be predicted. The corresponding nonlinear regression problem was extensively studied to determine tool sensitivities and the combination of inputs required to predict each unknown parameter most accurately and robustly. This study led to the design of cascaded feed-forward neural networks, where one or more model parameters are predicted at each stage and then passed on to following steps in the workflow as inputs until all unknowns are accurately obtained.
Both inverted field data sets and synthetic data from finite-element electromagnetic modeling were used in multiple training scenarios. In the first strategy, field data from few buttons and existing inversion results were used to train a single NN to reproduce standoff and resistivity images for all other buttons. Although the generated images are comparable to images coming from inversion, the method is dependent on the availability of field data for variable mud properties, which at the moment limits the generalization of the NNs to diverse mud and formation properties.
In the second strategy, we utilized the synthetic responses from a finite element model (FEM) simulator for a wide range of standoffs, formation, and mud properties to develop a cascaded workflow, where each stage predicts one or more model parameters. Early stages of the workflow predict the mud properties from low formation resistivity data sections. NNs then feed the estimated mud angle and permittivities at two frequencies into next stages of the workflow to finally predict standoff, formation resistivity, and formation permittivities. Knowledge of measurement sensitivities was critical to design the efficient parameterization and robust cascaded neural networks not only due mathematically underdetermined nature of the problem but also the wide dynamic range of mud and formation properties variation and the measurements. Results for processed resistivity, standoff, and permittivity images are presented, demonstrating very good agreement and consistency with inversion-generated images. The combination of two strategies, training on both synthetic and field data, can lead to further improvement of robustness allowing customization of interpretation applications for specific formations, muds, or applications.
The field-scale design of chemical enhanced oil recovery (cEOR) processes requires running complex numerical models that are computationally demanding. This paper provides an efficient screening platform for the cEOR feasibility study by presenting five artificial neural network (ANN) based models. We constructed 1,100 ANN training cases using CMG-STARS to capture the variation in reservoir petrophysical properties and the range of injected chemicals properties for a five-spot pattern. The design parameters were coupled with the reservoir properties using several functional links to optimize the ANN models and improve their performances. The training cases were employed using back-propagation methods to construct one forward model (Model #1) and four inverse models. Model #1 predicts reservoir response (i.e., oil rate, water cut, injector bottomhole pressure, cumulative oil) for known reservoir characteristics (i.e., permeability, thickness, residual oil saturation, chemical adsorption) and project design parameters (i.e., pattern size, chemical slug size and concentration), Model #2 predicts reservoir characteristics by history matching the reservoir response, and Model #3 predicts project design parameters for known reservoir response and characteristics. Models #4 and #5 predict project design parameters for a targeted cumulative oil volume and project duration time, which is useful for economical evaluation before the implementation of cEOR projects.
The validation results show that the developed ANN-based models closely predict the numerical results. In addition, the models are able to reduce the computational time by four orders of magnitude, which is significant considering the complexity of cEOR modeling and the need for reliable and efficient tools in building cEOR feasibility studies. In terms of accuracy, Model #1 has a prediction error of 5% whereas the error for other four inverse ANN models is about 20–40%. To enhance the performance of the inverse ANN models, we changed the ANN structure, increased training cases, and used functional links, which slightly reduced the error. Further, we introduced a back-check loop that uses the predicted parameters from the inverse ANN models as inputs in the forward ANN model. A comparison of back-check results for the reservoir response with the numerical results delivers a relatively small error of 10%, revealing the non-uniqueness of solutions obtained from the inverse ANN models.
Hadi, Farqad (Petroleum Engineering Department, Baghdad University) | Albehadili, Ali (Iraqi Drilling Company) | Jassim, Abduihussein (Najaf Oil Fields) | Almahdawi, Faleh (Petroleum Engineering Department, Baghdad University)
Formulating a prediction tool that can estimate the formation permeability in uncored wells is of particular importance for many applications related to reservoir simulation and production management. Although formation permeability can be obtained from a laboratory or from a reservoir, core analysis and well-test data are limited due to cost and time-saving purposes. A major challenge of previous methods is that they are required other parameters to be previously computed such as porosity and water saturation. In addition, they are affected by the uncertainty that introduced by the cementation factor and saturation exponent. This study presents two prediction methods, multiple regression analysis (MRA) and artificial neural networks (ANNs), to estimate formation permeability using conventional well log data.
The prediction methods were demonstrated by means of a field case in SE Iraq. The study uses core/well log data from Mishrif reservoir which is mainly composed of carbonate (limestone) formations. Two traditional methods were reviewed and presented for permeability determination. These methods are the classical method and the flow zone indicator (FZI) method.
At the same porosity, the results showed a wide range of formation permeability prediction. This result gives a special attention to the assumption that the relationship between permeability and porosity is generally unique in carbonate environments. The deep lateral log resistivity appears to be more conservative in the permeability function rather than other parameters, followed in decreasing order by bulk density, sonic travel time, micro and shallow resistivities, and shale volume. Although the presented models based on RA and ANNs resemble to be closely in determining the formation permeability, the correlation coefficient of ANNs was found to be higher than that obtained from RA, which indicated that the ANNs is more precise than RA. The comparison among previous methods shows the superiority of the FZI method rather than the classical method. However, core porosity and permeability should be previously determined to apply FZI method. This study presents efficient and cost-effective models for a prediction of permeability in uncored wells by incorporating conventional well logs.
In this study, the authors investigated a fully data-driven approach using artificial neural networks (ANNs) for real-time virtual flowmetering and back-allocation in production wells. The authors present a new data-driven approach to estimate the injection rate in all noninstrumented wells in a large waterflooding operation accurately.
In this study, the authors investigated a fully data-driven approach using artificial neural networks (ANNs) for real-time virtual flowmetering and back-allocation in production wells. Australian technology developer MezurX is touting its newly introduced flow, density, and mud monitoring system as a significantly better alternative to the widely used Coriolis meter. Technology developers are working on a new ultrasonic flowmeter for drilling fluids aimed at obtaining better measurements than current systems with far fewer disruptions to rig systems.
Total plans to start a digital factory to tap artificial intelligence in a bid to save hundreds of millions of dollars on exploration and production projects, according to an executive. Behavior-based safety is not a new concept nor is it new at Murphy Oil. But when Murphy launched its Safety Observation Program as a digital tool, it revitalized the way the culture of safety spread throughout the company. New funding for a chatbot technology, or smart assistant, represents the latest development in the Norwegian operator’s drive toward digitalization. Rapid advances in deep learning continue to demonstrate the significance of end-to-end training with no a priori knowledge.
Ashtead Technology has acquired Louisiana-based subsea equipment rental and cutting services specialist, Aqua-Tech Solutions, as part of the company’s international growth plans in the US. High-fidelity 3D engineering simulations are valuable in making decisions, but they can be cost-prohibitive and require significant amounts of time to execute. The integration of deep-learning neural networks with computational fluid dynamics may help accelerate the simulation process. The chemical reactions creating buildups of scale that can clog a well can be replicated in a chemical lab, but researchers are finding many more variables on the surfaces of pipes that need to be considered. The web-based interactive tool provides users specialized “ocean neighborhood analyses,” including maps and graphics by analyzing more than 100 ocean datasets instantaneously. BP and partners have sanctioned the Azeri Central East project, the next stage of development of the giant Azeri-Chirag-Deepwater Gunashli oilfield complex in the Azerbaijan sector of the Caspian Sea. The pipeline system will have the initial capacity to deliver 150,000 B/D of crude oil to multiple delivery points, accessing local refineries and connecting to several downstream pipelines.
AGI stands for artificial general intelligence, a hypothetical computer program that can perform intellectual tasks as well as, or better than, a human. AGI will make today’s most advanced AIs look like pocket calculators. In collaboration with Stanford University and Brown University, Google explores how existing knowledge in an organization can be used as noisier, higher-level supervision—or, as it is often termed, weak supervision—to quickly label large training data sets. Robots have been a part of industrial production for decades, but the interface between humans and robots has changed as automation technologies increased in complexity, scope, and scale. Once a novelty, collaborative robots are projected to become a significant element of the automation landscape.
Alkinani, Husam H. (Missouri University of Science and Technology) | Al-Hameedi, Abo Taleb T. (Missouri University of Science and Technology) | Dunn-Norman, Shari (Missouri University of Science and Technology) | Alkhamis, Mohammed M. (Missouri University of Science and Technology) | Mutar, Rusul A. (Ministry of Communications and Technology)
Lost circulation is a complicated problem to be predicted with conventional statistical tools. As the drilling environment is getting more complicated nowadays, more advanced techniques such as artificial neural networks (ANNs) are required to help to estimate mud losses prior to drilling. The aim of this work is to estimate mud losses for induced fractures formations prior to drilling to assist the drilling personnel in preparing remedies for this problem prior to entering the losses zone. Once the severity of losses is known, the key drilling parameters can be adjusted to avoid or at least mitigate losses as a proactive approach.
Lost circulation data were extracted from over 1500 wells drilled worldwide. The data were divided into three sets; training, validation, and testing datasets. 60% of the data are used for training, 20% for validation, and 20% for testing. Any ANN consists of the following layers, the input layer, hidden layer(s), and the output layer. A determination of the optimum number of hidden layers and the number of neurons in each hidden layer is required to have the best estimation, this is done using the mean square of error (MSE). A supervised ANNs was created for induced fractures formations. A decision was made to have one hidden layer in the network with ten neurons in the hidden layer. Since there are many training algorithms to choose from, it was necessary to choose the best algorithm for this specific data set. Ten different training algorithms were tested, the Levenberg-Marquardt (LM) algorithm was chosen since it gave the lowest MSE and it had the highest R-squared. The final results showed that the supervised ANN has the ability to predict lost circulation with an overall R-squared of 0.925 for induced fractures formations. This is a very good estimation that will help the drilling personnel prepare remedies before entering the losses zone as well as adjusting the key drilling parameters to avoid or at least mitigate losses as a proactive approach. This ANN can be used globally for any induced fractures formations that are suffering from the lost circulation problem to estimate mud losses.
As the demand for energy increases, the drilling process is becoming more challenging. Thus, more advanced tools such as ANNs are required to better tackle these problems. The ANN built in this paper can be adapted to commercial software that predicts lost circulation for any induced fractures formations globally.
Computer vision (CV) techniques were applied to X-ray computed tomographic (CT) images of reservoir cores to evaluate their potential for rapidly identifying fractures and other lithologic/geologic characteristics. The analyses utilized feature-labeled CT cross sectional images, themselves distributed submillimeter voxels of density- and atomic number-sensitive CT Numbers, as inputs to a Fully Convolutional Neural Network (FCN) for semantic segmentation of reservoir core features. In FCN, an image is interrogated using a series of sliding windows at various scales to create weighted filters to reduce error between classes in training images. These networks of filter layers were used to assign probabilities of classes, which were upscaled back to the original image dimensions resulting in probabilistic class assignments onto each pixel. FCN model accuracy, defined by its ability to replicate manually-assigned labels in the raw (unannotated) training image stack, was at least 80% and generally improved with the size of the training set. Once the labels were assigned, the underlying feature frequency, orientation, and size were measured in 3D volume reconstructions using algorithms modified from standard image analysis software. This method allowed users to endow a classification model with subject matter knowledge for further, autonomous label prediction. Thus, while initial image annotation was labor intensive, subsequent images were rapidly classified once the model was built. The classified labels were analyzed for abundance, orientation, and size of fractures were calculated to characterize spatial information of these features. FCN combined with fracture labeling improved knowledge capture and automation of fracture identification. Models trained by high quality 3D datasets can greatly reduce the time needed to describe subsequent core. The method demonstrated is not limited to fractures, other lithologic/geologic features could be trained using the same method, which may result in additional efficiencies.