Abstract Seismic interpretation is an essential factor in the success of field development projects because it allows geologists and engineers to better understand subsurface formations and identify potential resources; however, noisy seismic data, especially in regions with complex geological structures, frequently hinder this process. Such noise emerging from equipment limitations, environmental interference, and inherent geological complexities can obscure essential geological features, making accurate subsurface imaging challenging and reducing the effectiveness of traditional interpretation methods. This paper presents a machine learning (ML) method to enhance the conditioning of 2D and 3D post-stack seismic data by targeting noise and migration artifacts. These issues are often responsible for compromising the quality of seismic data sets. The method this paper presents leverages convolutional neural networks (CNNs) to identify and correct spatial inconsistencies within the data. With minimal preprocessing, requiring only the conversion of data into a 3D NumPy array format, this approach simplifies the workflow while improving data clarity and accuracy. Early statistical analysis of outliers and data normalization provides the ML model with stable inputs, allowing it to iteratively train on raw data and infer the original signal patterns in an unsupervised manner without the need for labeled data sets. The model outputs a conditioned version of the seismic data, significantly reducing noise while preserving critical geological features. The results demonstrate that ML seismic conditioning improves fault imaging, horizon continuity in areas with low signal-to-noise ratios (SNR), and localized smoothing without compromising resolution. Furthermore, the method presented in this paper retains signal fidelity and relative amplitude strengths, ensuring that geological interpretations remain accurate and reliable. By automating the traditional manual task of data conditioning, the proposed solution optimizes interpreter workflows, allowing them to focus on higher-level geological analysis and decision-making. This approach ultimately increases the accuracy of subsurface interpretations and resource exploration, improving the overall quality and efficiency of seismic interpretation projects. In addition, for 2D seismic, traditional methods of denoising rely on expert judgement using tools such as f-x deconvolution. 2D CNNs offer an efficient alternative, especially when training data can be synthesized and leveraged in supervised learning. This method can help the CNN identify and remove noise while preserving pertinent subsurface structures. This paper presents a 2D CNN architecture containing a model trained with synthetic seismic data to improve SNR of field seismic data; hence, interpretation.

Abstract This paper presents a custom Machine Learning approach for reducing seismic noise while improving resolution and features identification. The seismic data enhancement created via this approach has positive impact on every stage of the oil-field life cycle, however, it is particularly advantageous during the exploration phase, where high quality seismic data is often unavailable from traditional solutions due to several factors. The high-quality seismic data output from the custom Machine Learning approach enables more accurate identification of hydrocarbon reservoir potentials, reduces prospect risk, provides basis for optimized well placements, and would ultimately contribute to higher exploration and exploitation success rates. Overall, this solution approach involves autogenerating Deep Neural Network models that are individually tailored to remove noise from input seismic data, while improving resolution and preserving edges. The process consists of five stages: pre-processing, features extraction, neural network model training, post-processing, and results evaluation. Training data is generated by perturbing the input seismic data to create a super-noisy version of the data. The deep neural network then creates a model that removes noise from the perturbed data to recover the original input data. Thereafter, the same noise removal model is applied to the original unperturbed seismic data to generate a noise-free version of the original seismic data. Since the training data is generated from the original seismic itself, the noise removing model is tailored for each seismic data volume. The process does not require well data input. Output seismic volumes from the Machine Learning Conditioning process in this project had better signal to noise ratio compared to the input. Seismic events were realistically smoothened and sharpened without smearing edges, thus improving horizon and fault interpretation. Some hitherto hidden reflector relations were revealed in the output seismic data, thus improving stratigraphic interpretation. Seismic attributes also had better quality from the output seismic data. The process is automated, so it saves time and makes it possible to efficiently work with multiple datasets to reduce interpretation uncertainty. As the industry moves towards exploring and developing more challenging green reservoirs and redeveloping brown reservoirs, having the cost-effective means provided by this solution helps in generating more detailed insight from existing seismic data volumes, thereby creating multiplied value. The new fully automated method developed for conditioning seismic data in this project is unlike other solutions in that it learns noise patterns from the input data and removes them in the same run, making it more versatile than pretrained models that only work in specific settings. As the process does not require well data input, it is useful right from the earliest phases of exploration. Results are more accurate than traditional data conditioning methods, and the process is extremely quick compared to the alternative of having to reprocess the seismic data.

AbstractIn dynamic landscape of oil and gas drilling, Generative Artificial Intelligence (Generative AI) emerges as the indispensable ally, leveraging historical drilling data to revolutionize operational efficiency, mitigate risks, and empower informed decision-making. Existing Generative AI methods and tools, such as Large Language Models (LLMs) and agents, require tuning and customization to the oil and gas drilling sector. Applying Generative AI in drilling confronts hurdles such as ensuring data quality and navigating the complexity of operations. A methodology integrating Generative AI into drilling demands is comprehensive and interdisciplinary. Agile strategy revolves around constructing a network of specialized agents of LLMs, meticulously crafted to understand industry-specific terminology and intricate operational relationships rooted in drilling domain expertise. Every agent is linked to manuals, standards, specific operational drilling data source and it has unique instructions optimizing computational efficiency and driving cost savings. Moreover, to ensure cost-effectiveness, LLMs are selectively employed, while repetitive user inquiries are addressed through data retrieval from an aggregated storage. Consistent responses to user queries are provided through text and graphs revealing insights from drilling operations, standards, manuals, practices, and lessons learned. Applied methodology efficiently navigates inside the pre-processed user database relying on custom agents developed. Communication with the user is set in the form of chat framed within a web application, and queries on the database about hundreds of wells are answered in less than a minute. Methodology can analyze data and graphs by comparing Key Performance Indicators (KPIs). A wide range of graph output is represented by bar charts, scatter plots, and maps, including self-explaining charts like Time versus Depth Curve (TVD) with Non-Productive Time (TVD) events marked with details underneath.Understanding the data content, data preparation steps, and user needs is fundamental to a successful methodology application. The proposed Generative AI methodology is not just a tool for data interpretation, but a catalyst for real-time decision-making in complex drilling environments. Its integration into oil and gas drilling operations signifies a pivotal advancement, showcasing its transformative potential in revolutionizing the industry's landscape. This approach leads to notable cost reductions, improved resource utilization, and increased productivity, paving the way for a new era in drilling operations. A method driven by selective, cost-effective, and domain specific LLM agents stands poised to revolutionize drilling operations, seamlessly integrating generative AI to amplify efficiency and propel informed decision-making within the oil and gas drilling sector.

A challenging step in reservoir modeling is capturing fluid composition variation. This is a complex task as fluid samples taken from wells in different areas of the reservoir usually have large areal and vertical compositional variation. Modeling representative composition variation with depth in the presence of multiple samples is critical for reservoir simulation and hydrocarbon initially in place assessment, and, on the other hand, a technically challenging task. In this paper, we present an automated workflow integrated in a commercial exploration and production (E&P) software that addresses compositional variation for reservoir simulation model initialization for multiple fluid samples. Composition variation with depth requires a depth window, number of depth points, composition, temperature, pressure and reference depth for all fluid samples. Using a specific equation of state (EoS), the workflow is executed for every fluid sample by performing compositional variation with depth based on Gibbs conditions for thermodynamic equilibrium. The output of this step is a composition variation with depth distribution for every fluid sample. Finally, the best-matching model is chosen by comparing each model results with the data for all existing fluid samples. The proposed workflow was tested using a specific EoS in a reservoir with several fluid samples. One composition variation with depth model was generated for every fluid sample. In the next step, all models were evaluated by calculating the average errors between the model and each fluid sample. Finally, the best-matching models were selected, and the results were evaluated. It was observed that the best-matching models were able to accurately predict the pressure and saturation pressure for large number of fluid samples. The proposed workflow was also integrated into an industry-leading E&P modeling software platform to serve as an automated functionality that outputs the required files to perform initialization with equilibration of the dynamic reservoir model. Capturing fluid composition variation in the reservoir is an important step in reservoir modeling. The proposed work presents an automated workflow that generates the best-matching composition variation with depth model for multiple samples. Using traditional approaches, this is a challenging and time-consuming step as fluid samples taken from wells in different areas of a reservoir can have significant areal compositional variation.

Capturing fluid composition variation and distribution in the reservoir is an essential first step for reservoir modeling. Vertical fluid composition variation is commonly considered. However, fluid samples taken from wells in different areas of a reservoir can highlight significant areal variation in the composition to be modeled. Fluid contacts may be tilted, and despite many studies on the subject, the setup is not straightforward. The combination of all three makes the initialization challenging and time consuming. In this paper we describe an automated workflow that integrates fluid sample data and petrophysical data to generate an initial fluid composition distribution that captures vertical and areal composition variations and accurately computes the initial fluid distribution to represent tilted contact configurations and their associated transition zones. Fluid sample data such as composition, pressure, temperature, and sampling depth are provided to an engine that computes composition variation with depth for each sample based on the equation of state (EOS) that characterizes the fluid behavior of the reservoir. The generated composition variation with depth for each sample is spatially distributed at their associated wells and is used to compute the areal composition distribution between the wells in the reservoir. This results in a tridimensional distribution of each fluid component representing the fluid model that captures both vertical and areal composition variations. In parallel, saturation height functions and hysteresis models are used to automatically generate drainage capillary pressure data and associated imbibition and scanning curves used to capture the drainage and imbibition processes responsible for the paleo and current water saturation distribution in the reservoir. The fully automated reservoir initialization process accounts for all available pressure-volume-temperature (PVT) samples. The solution is portable, significantly faster, and accurately captures complex reservoir geology and reservoir history. We present field examples of the proposed approach and illustrate its flexibility and associated comprehensiveness and efficiency. The complete automation of complex initialization methods considering areal and vertical composition variation, combined with tilted contacts modeling, is helping to resolve significant challenges faced across the industry.