On Utilizing Functional Network to Develop Mathematical Model for Poisson's Ratio Determination

Elastic parameter such as Poisson's ratio is used to construct the geo-mechanical earth models (GEM's). GEM's are used in many rock and petroleum engineering applications. This paper aims to formulate a generalized empirical model to predict static Poisson's ratio of the carbonate rock based on well logs as inputs and triaxial test determined static Poisson's ratio's as an output, using artificial intelligence (AI) tools. The set of data on which AI models are developed comprised of 120 data points from different wells in a giant carbonate reservoir of the Middle East that covered a wide range of values. To transform black box nature of AI model into white box, AI based empirical correlation is developed to predict static Poisson's ratio using the weights associated with trained model. The use of new equation is very cost effective in terms saving the laboratory experiments. The new equation can be used without retraining of AI models again.