Trending Content

Big Step Towards Digitalization: AI Driven History Matching for Complex Completions

Add to Cart
Course Credit: 0.15 CEU, 1.5 PDH

In the current environment, artificial intelligence (AI) is used in any part of the oil and gas industry. The main problem in oil and gas is the limited number of data and the accuracy in measurements. Currently, many think that AI is not smart enough. The reason is the lack of temporal and spatial prediction in AI techniques; as we move away from the training point, the field predictions are deviating. Prior to the current wave of AI, numerical modeling was the mainstream for predicting many problems in the oil and gas industry.

Currently, many engineers follow the fashion by looking for a quick substitute to dynamic numerical models through ML /AI black box tools. Without knowing that a dynamic numerical model has a big advantage, understanding the effect of time and space in defined problems. The problem is even larger once we deal with new completions such as ICD, Limited Entry, etc. In this presentation, Dr. Irani will explain the modification to Neural Network Backpropagation that trains both derivative and actual values of the rate. Such a solver will be combined with a numerical solver to provide better predictions.

SPE Webinars are FREE to members courtesy of the

Post Tags

 1 chapter
  1 downloadable resource

Course Chapters

  • 1Big Step Towards Digitalization: AI Driven History Matching for Complex Completions - Chapter 1
    Media Type: Video

Credits

Earn credits by completing this course0.15 CEU credit1.5 PDH credits

Speakers

Dr. Mazda Irani
Dr. Wael Ziadat