Using artificial neural networks to identity the well test interpretation model

The objective of this paper is to present a new approach to identify a preliminary well test interpretation model from derivative plot data. In this paper we show that using artificial neural networks technolgy is a significant improvement over pattern recognition techniques currently used (e.g., syntactic pattern recognition) in well test interpretation. Moreover, artificial neural networks eliminate the need for elaborate data preparation (e.g., smoothing, segmenting, and symbolic transformation) and they do not require writing complex rules to identify a pattern. The paper illustrates the application of this new approach with two field examples.

Using artificial neural networks to identity the well test interpretation model Conference Paper