Enterprise-scale artificial intelligence (AI) has the potential to transform upstream oil and gas operations.. Successful implementation requires attention to data integration, the development, deployment, and maintenance of a large number of machine learning (ML) models, and a combined expertise in data science and the oil and gas domain.

Managing complex production data

The first prerequisite for an effective implementation of a production optimization solution is access to high fidelity data from a variety of different sources such as well data, production data, reservoir modeling data, field infrastructure data, and financial and economic planning data for the production business. In the case of AI-based virtual metering, for example, data should include all frequent measurements that can be used as input features and well test results that will be used as target values for training the models. For a typical oil and gas field, this data needs to be available for many pads, with each pad including multiple production wells.

The number of wells for a production optimization application can easily be in the order of hundreds to thousands. Organizing and unifying all the data sources necessary for a production optimization application requires an efficient data lake and a data model that enables quick and reliable access to all data sources.

Creating and Maintaining Machine learning models for upstream AI

Developing a good machine learning model is a highly iterative process and typically requires domain expertise, careful exploration of the data sources and experimentation with different feature sets, learning techniques and machine learning models. Managing hundreds or thousands of machine learning models is a challenging task. First, every model needs to be trained and hyperparameter-tuned. Once these models are trained, they need to be productionized to continuously generate predictions and scores, and these outputs need to be persisted and made available in the application interface. Finally, the quality of the predictions needs to be continuously monitored and the models must be retrained or replaced in case of performance degradation. Performing these tasks at the scale required for a field-level virtual metering application poses many technical challenges.

Transforming upstream production with enterprise AI

The BHC3™ Production Optimization application answers the needs of upstream AI deployments at enterprise scale. The application draws on the power of the BHC3 AI Suite, offering an extendible data model that can be configured and tailored for new deployments. The relationships between all key assets and measurements in an oil and gas fields are predefined in this data model, and once the data model is configured, all static and time series data related to a field can be readily accessed efficiently through the application data model.

The complexity of AI model deployment and management is also simplified. By leveraging the architecture of the BHC3 AI Suite, thousands of models can be trained, processed, or tuned simultaneously, and the user can configure the logic that defines the data used for training the virtual meters. As an example, an operator can specify whether for one type of virtual meter (e.g., gas production rate), the training data should be shared between all wells in a pad or collected individually for each well. The application is also preconfigured with specific machine learning models. Upstream businesses can also configure the application to select any other ML model from a library of machine learning pipelines available through the BHC3 AI Suite.

Incorporating domain expertise

Although enterprise AI applications can simplify the complexity of production optimization, subject matter expertise plays an important role in successful deployments. Identifying data sets that are most reliable and trusted by the field engineers and technicians will greatly expedite the application’s feature engineering and feature selection. This process requires the help of a subject matter expert that is familiar with the specific field.

There are also specific operation and procedures that are specific to each field and may be difficult to detect without familiarity and deep domain understanding. Finally, experts can validate the predictions and the explainability of the models used in BHC3 Production Optimization. This final step is critical to ensure that the application is configured properly and integrated as a part of the production system.

BakerHughesC3.ai is deploying enterprise AI in upstream oil and gas by leveraging the data science expertise of C3 AI and the deep energy technology understanding of Baker Hughes to deliver optimized production for oil and gas enterprises. Learn how at BakerHughesC3.ai.

About the authors

Amir H. Delgoshaie is a Data Science Manager at C3 AI, where he has worked on the development and deployment of multiple large-scale AI applications for the utility, energy, and manufacturing sectors. He holds a Ph.D. in Energy Resources Engineering from Stanford University and Master’s and Bachelor’s degrees in Mechanical Engineering from ETH Zurich and Sharif UT. Prior to C3 AI, he developed algorithms and software at various research and industrial institutions.

Z. Larry Jin is a Senior Data Scientist at C3 AI. He has been working on multiple projects within a variety of industries, including manufacturing and oil & gas. Before C3 AI, he received his Ph.D. and master’s degree in Energy Resource Engineering from Stanford University where he focused on applying AI and deep learning to the energy sector.

Riyad Muradov is a Senior Data Scientist at C3 AI, with experience in developing and scaling data-driven applications in energy and financial sectors. He holds a Master’s degree in Energy Resources Engineering from Stanford University with a focus on geostatistics and reservoir characterization.

This article was originally published in a World Oil Newsletter in December 2021