A New Method for Pore Pressure Prediction on Malfunctioning Cells Using Artificial Neural Networks

Markovic, Milica; Branković, Jelena; Stošović, Miona Andrejević; Živković, Sanja; Brankovic, Bojan

doi:10.1007/s11269-021-02763-0

Cited by 5 publications

(2 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, compared to the traditional trial-and-error method, the proposed delay process calculation method in this study provides better effectiveness, which has significant value for monitoring and controlling infiltration flow in concrete dams. Markovic et al (2021) developed a new method for predicting permeation pressure in incompatible cells using multiple sequential ANNs to address the issue of an incompatible cell with a small available dataset. The results showed that this approach achieved high accuracy in predicting values, which were more precise than those obtained using only one ANN for prediction.…”

Section: Introductionmentioning

confidence: 99%

Wavelet–ANN hybrid model evaluation in seepage prediction in nonhomogeneous earthen dams

Fatehi-Nobarian,

Fard Moradinia

2024

Water Practice &Amp; Technology

View full text Add to dashboard Cite

In this study, novel methods such as wavelet–artificial neural network hybrid models and artificial neural network models were used to predict seepage from the Zonouz earthen dam. The dataset consisted of 972 piezometric data points. Statistical fitting methods such as root mean squared error, determination coefficient, scatter plots, and data distribution diagrams were used to evaluate the results. The findings indicated that the wavelet–artificial neural network hybrid model was more accurate than the artificial neural network model. Specifically, during training, the wavelet–artificial neural network hybrid model had determination coefficients and root mean squared errors of 0.820, 0.680, 743.39, and 792.52, while the artificial neural network model had 0.700, 0.600, 426.39, and 131.45. Similarly, during validation, the wavelet–artificial neural network hybrid model had determination coefficients and root mean squared errors of 0.700, 0.600, 426.39, and 131.45, while the artificial neural network model had 0.823, 0.680, 743.39, and 792.52. Therefore, the wavelet–artificial neural network hybrid model can be proposed as a precise method for predicting seepage in earthen dams and is more accurate than the artificial neural network model. This study highlights the importance of preventing dam failures and using advanced modeling techniques for better predictions and preventive measures.

show abstract

Section: Introductionmentioning

confidence: 99%

Wavelet–ANN hybrid model evaluation in seepage prediction in nonhomogeneous earthen dams

Fatehi-Nobarian,

Fard Moradinia

2024

Water Practice &Amp; Technology

View full text Add to dashboard Cite

show abstract

“…Simulation approaches that depend on the seismic log data were carried out to obtain a reliable model for pore pressure determination where an encouraging results were obtained (Asedegbega et al 2021). A recent study was performed for the goal of pore pressure determination using Artificial Neural Network (ANN) where this technique was successfully applied previously for the estimation of rate of penetration where reasonable results were produced (Markovic et al 2021). Simulation approaches encourage further investigation for geopressure estimation as a successful alternative of actual pore pressure measurement.…”

Section: Introductionmentioning

confidence: 99%

Developing a new approach for the anticipation of subsurface pressure in three oil wells from various fields in Iraq

Abbas

2021

J Petrol Explor Prod Technol

View full text Add to dashboard Cite

Subsurface pressure quantification is the main goal for all drilling engineers due to its vital importance to minimizing drilling costs and preventing various excavating dilemmas such as stuck pipe, pipe collapsing, lost circulation, and well kick. Formation pressure is measured directly in producing hydrocarbon zones using special equipment; however, it is difficult to obtain pore pressure measurements in other intervals; therefore, many approaches were suggested and developed to anticipate the geopressure due to its importance on the drilling operation. Traditionally, Eaton's method is the most widely used for geopressure anticipation from well logs. In the current study, a new proposed formula for geopressure determination was derived from the modified Eaton's equation which is based on the inception of the mechanical specific energy. The study was applied on three oil-producing wells from different fields in Iraq (Missan C, West Qurna 15, and Zubair 171). The estimated subsurface pressure from the new suggested approach was validated by comparison with the actual in situ subsurface pressure obtained from Drill Stem Test (DST) and Repeated Formation Test (RFT). Statistical analysis is used for the validation by applying Mean squared error (MSE) and Mean Absolute percentage Error (MAE). Encouraging results were obtained from the present research for all wells being studied. The main finding of the current work is involving a new parameter (mechanical specific energy) for subsurface pressure determination, where it was not included in the previous techniques of geopressure equations. It was found that the value of exponent (m) in the new proposed equation has a significant influence on the predicted geopressure, where (m) varies from 0.1626 to 0.6896 depending on the type of the excavated rock plus the materials that the drill bit is manufactured of, where the interaction between these components is vital. The present work could be a useful method when planning to excavate a new well adjacent to the area of the investigated wells, where special well logs are unavailable for pore pressure measurement and suitable usage of mud weight is highly needed for the overall drilling process.

show abstract

Formation Pressure Estimation Method for High Temperature and High Pressure Wells in Ledong Area of South China Sea

Zhang

Yang

et al. 2021

Nat Resour Res

View full text Add to dashboard Cite

A New Method for Pore Pressure Prediction on Malfunctioning Cells Using Artificial Neural Networks

Cited by 5 publications

References 28 publications

Wavelet–ANN hybrid model evaluation in seepage prediction in nonhomogeneous earthen dams

Wavelet–ANN hybrid model evaluation in seepage prediction in nonhomogeneous earthen dams

Developing a new approach for the anticipation of subsurface pressure in three oil wells from various fields in Iraq

Formation Pressure Estimation Method for High Temperature and High Pressure Wells in Ledong Area of South China Sea

Contact Info

Product

Resources

About