The pore pressure in most sedimentary formations such as it is in the Niger Delta, Nigeria are rarely normal. They predominantly occur as over-pressured zones, when these abnormal pressures are not predicted accurately prior to drilling, disastrous occurrences, such as kicks, and blowouts may occur. The existing models used for pore pressure predictions were developed using data outside Niger Delta environment as such a number of them yield inaccurate results. This paper provides a new approach for predicting pore pressures particularly for Niger Delta using offset well logs acquired in the Niger Delta. A number of industries utilized pore pressure prediction models were appraised using offset well data from the Niger Delta. Density and sonic velocity logs were used in generating the overburden pressure and Normal Compaction Trend. Shale trend and overburden pressure were used as inputs in the models for predicting pore pressure using RokDoc.In the development of an appropriate model for pore pressure prediction, Eaton model was modified for Niger Delta environment. Results of the model's sensitivity analysis revealed sonic velocity as the most sensitive parameter while findings from the Goal Seek analysis showed that increasing the exponent in the original Eaton's model from 3 to 3.9 yielded the most concordant result with the measured pressure data. The statistical error analysis conducted revealed that the modified Eaton's model had the least absolute mean percentage error value of 2%. Given the above results, the modified Eaton's model showed more accurate predictions when compared with existing models and will be effective in predicting pore pressure in the study area.
Machine Learning techniques and applications have lately gained a lot of interest in many areas, including spheres of arithmetic, finances, engineering, dialectology, and a lot more. This is owing to the upwelling of ground-breaking and sophisticated machine learning procedures to exceedingly multifaceted complications along with the prevailing advances in high speed computing. Numerous usages of Machine learning in daily life include pattern recognition, automation, data processing and analysis, and so on. The Petroleum industry is not lagging behind also. On the contrary, machine learning approaches have lately been applied to enhance production, forecast recoverable hydrocarbons, augment well placement by means of pattern recognition, optimize hydraulic fracture design, and to help in reservoir characterization. In this paper, three different machine learning models were trained and utilized to explore the feasibility of forecasting pore pressure of a well. The machine learning algorithms include, Simple Linear Regression, Decision Stump and Multilayer Perceptron (ANN). The predictive accuracies of the algorithm was analyzed using statistical measures. Five (5) parameters were utilized as input variables in the models: hydrostatic pressure, overburden pressure, observed and normal sonic velocities and pore pressure. 80% of the data was used in training while the remaining 20% was used for testing of the models. A sensitivity analysis of the five variable was conducted so as to identify correlations of the variables. Results of the sensitivity analysis revealed that both hydrostatic and overburden pressures appear to have the strongest correlation with pore pressure (0.766) and closely followed by normal compacted sonic velocity (0.753). Meanwhile, observed sonic velocity has the least correlation (0.046). The models were appraised by determining their Relative Absolute Errors. Results indicate that Multilayer Perceptron has the best prediction and least Relative Absolute Error of 5.77%. While the Decision Stump model had a Relative absolute error of 54.41%. The Simple Linear Regression had a relative absolute error of 67.93%. By and large, all three models appear to be suitable for modeling pore pressure but the Multilayer Perceptron is the most accurate.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.