DSDE: In Theory

This paper investigates the use of machine learning to rapidly predict the solutions of a high-fidelity, complex physics model using a simpler physics model.

This study proposes a hybrid model that combines the capacitance/resistance model, a machine-learning model, and an oil model to assess and optimize water-alternating-gas (WAG) injectors in a carbonate field.

Computational fluid dynamics modeling is used to gain better understanding of filter-cake formation in inclined and vertical well drilling operations under elevated temperature and pressure, highlighting the importance of controlling fluid invasion to optimize drilling performance.

This paper presents the design and development of a prototype intelligent water-injection and smart allocation tool aimed at achieving autonomous waterflood operations.

This paper addresses the challenges of integrating huge amounts of data and developing model frameworks and systematic workflows to identify opportunities for production enhancement by choosing the best candidate wells.

Supervised learning was used to develop an ensemble of models that account for historical production data, geolocation parameters, and completion parameters to forecast production behavior of oil and gas wells.

The authors of this paper propose a hybrid approach that combines physics with data-driven approaches for efficient and accurate forecasting of the performance of unconventional wells under codevelopment.

This paper develops a deep-learning work flow that can predict the changes in carbon dioxide mineralization over time and space in saline aquifers, offering a more-efficient approach compared with traditional physics-based simulations.

This work provides a new modeling tool, validated against a static-wellbore solver and field data, to estimate and manage downhole temperature in higher-temperature oil, gas, and geothermal wells.

This paper presents an approach using artificial neural networks to predict the discharge pressure of electrical submersible pumps.