Reservoir characterization and porosity classification using probabilistic neural network (PNN) based on single and multi-smoothing parameters

Document Type : Research Paper


Mining Engineering Department, Arak University of Technology, Arak, Iran


Probabilistic neural network (PNN) is a feed-forward neural network using a smoothing parameter. We used PNN algorithm based on single and multi-smoothing parameters for multi-dimensional data classification. Using multi smoothing parameters, we implemented an improved probabilistic neural network (PNN) to estimate porosity distribution of a gas reservoir in North Sea. Comparing the results of implementing smoothing parameters which obtained from model-based optimization and particle swarm optimization (PSO) indicated the efficiency of PNN in characterizing the gas. Also results showed that while PSO algorithm was able to specify smoothing parameters with more precision, about 9%, but it was very time consuming. Finally, multi PNN based on PSO was applied to estimate porosity distribution of F3 reservoir. The results validated the main fracture or gas chimney of F3 reservoir with higher porosity. Also, gas bearing layers were highlighted by energy and similarity attributes.