Field development planning using reservoir models is a key step in the field development process. Numerical optimization of specific field development strategies is often used to aid planning, and Bayesian Optimization is a popular optimization method that has been applied in the past.

The ability to define an accurate interval velocity model resulting in a reliable image of the subsurface is a key challenge in prestack depth imaging. The delineation of an accurate interval velocity model is at the heart of every depth imaging process, so it is of vital importance to have all the input needed to ensure the velocity model is accurate, high resolution and geologically realistic.

Elastic inversion from common reflection angle migration (CRAM) gathers can accurately capture lithology-driven lateral variations in reservoir properties, particularly in a strongly deformed and faulted geologic environment.

Predicting the permeability of fractured reservoirs is valuable for both reservoir assessment and drilling planning. Characterization of such systems requires advanced amplitude analysis, mainly based on seismic imaging results of the recorded wavefield.

A seismic survey was conducted in a production oil field in Serbia. It was assumed that significant reserves still exist in the field, as well as additional undiscovered reservoirs. An advanced seismic imaging technology was required to further characterize the existing reservoirs and identify and characterize new ones.

Seismic processing, imaging, characterization and interpretation are preferably executed as a continuous workflow to maintain seismic data integrity and consistencies. Geophysicists must construct a workflow from hundreds of applications and algorithms, and thousands of parameters, to achieve desired project outcomes. Almost all these applications and algorithms are based on assumptions about the underlying geological model complexity and subsurface conditions.

The past few years have seen increased interest in the application of machine learning in the industry, specifically to seismic interpretation.

There has been growing interest in the use of machine learning technologies for processing and interpreting seismic data. Many procedures that traditionally have been performed using deterministic methods and algorithms can be effectively replaced by neural networks and other artificial intelligence methodologies, improving simplicity, efficiency and automation.

The AspenTech DEI Team promotes an inclusive work environment that enables the success of all employees. Learn about the year ahead for DEI at AspenTech.

This case study details the work done at the Universiti Malaysia Pahang to research oleochemical fractionation to how to make the process more sustainable, reducing process carbon footprint. The case study explores the AspenTech solutions implemented as well as the value created.