Modeling of Pore Pressure using Artificial Neural Networks
Received Date: Mar 26, 2020 / Accepted Date: Apr 11, 2020 / Published Date: Apr 20, 2020
Abstract
Most formation pressure prediction techniques employed in the industry today are based on formulations that are exclusively compatible with petro-physical input data obtained either from well logs or seismic surveys. This trend has consequently restricted the prognosis of pore pressure to these models that are sometimes unsuitable for certain environments. This paper presents an approach for modeling the pore pressure of the formation using Artificial Neural Network. The Artificial Neural Network was employed in forecasting the pore pressure from a wire line formation test data in the form of Modular Dynamic Tester dataset consisting of the measured pore pressure, true vertical depths, mobility, and temperature and pretest volume. . The dataset was portioned into two groups, the learning dataset as well as the prediction dataset. The former was used in training the Artificial Neuron Network model while the latter was employed in the validation of the model’s accuracy. The True vertical depths, mobility, and temperature and pretest volume were employed as inputs into the artificial neural network .The Artificial Neural network produced high-prediction accuracy as seen from the correlation coefficient of 0.9927 and Root Mean Square Error of 0.6628. Considering the results obtained, the Artificial Neural network will be effective in forecasting pore pressures and would provide an alternative means of doing that.
Keywords: Model; Neural network; Pore pressures
Citation: Tanko A, Bello A (2020) Modeling of Pore Pressure using Artificial Neural Networks. Oil Gas Res 6: 168. Doi: 10.4172/2472-0518.1000168
Copyright: © 2020 Tanko A, et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Share This Article
Recommended Journals
Open Access Journals
Article Tools
Article Usage
- Total views: 1747
- [From(publication date): 0-2020 - Aug 16, 2024]
- Breakdown by view type
- HTML page views: 1167
- PDF downloads: 580