Figure 2: Areal pressure depletion at different time steps of the first well.

Figure 1: 2D and 3D visualization of the best AHM solution for both wells considering Natural Fractures.

EDFM-AI Case study

          --- AHM for cluster efficiency and optimal cluster spacing

Challenges: A main drive to conduct this project was to understand why the first well did not perform as well as the second. After implementing our EDFM-AI, the AHM framework gave us quick possible answers to that problem. We concluded that the efficiency of the completions and the fracture job had tremendous impact on the performance so that the second well with larger cluster efficiency and less water saturation in the fractures exhibit better performance. 

‚ÄčSimTech Solution:For this project, two oil wells AHM were evaluated with EDFM-AI considering natural fractures. The objective of these assessment was to confirm standard reservoir properties from all the available data from the field (microseismic, petrophysics, completions, and production data) and to include slanted hydraulic fractures and cluster efficiency as uncertain parameters. Additionally, NN-MCMC method employed around 20,000 samples in each iteration for searching better solutions and optimal cluster spacing.