Stacked Ensemble Machine Learning for Porosity and Absolute Permeability Prediction of Carbonate Rock Plugs

Kalule, Ramanzani; Abderrahmane, Hamid Ait; Sassi, Mohamed

doi:10.21203/rs.3.rs-2585859/v1

Cited by 3 publications

(4 citation statements)

References 42 publications

(38 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A common strategy employed in studies utilizing SE involves comparing the predictions of the SE with those of the base models (Kalule et al., 2023). Depending on the volume of the data used, an SE can be computationally expensive.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Automated signal‐based evaluation of dynamic cone resistance via machine learning for subsurface characterization

Aregbesola,

Byun

2024

Computer aided Civil Eng

View full text Add to dashboard Cite

Dynamic cone resistance (DCR) is a recently introduced soil resistance index that has the unit of stress. It is determined from the dynamic response at the tip of an instrumented dynamic cone penetrometer. However, DCR evaluation is generally a manual, time‐consuming, and error‐prone process. Thus, this study investigates the feasibility of determining DCR using a stacked ensemble (SE) machine learning (ML) model that utilizes signals obtained from dynamic cone penetration testing. Two ML experiments revealed that using only force signals provides more accurate predictions of DCR. In addition, the SE technique outperformed the base learning algorithms in both cases. Overall, the findings suggest that ML techniques can be used to automate the analysis of DCR with force and acceleration signals.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Stacking is an ensemble ML technique that combines predictions from various estimators in a meta‐learning algorithm (Kalule et al., 2023). This method is distinctive because of its ability to merge predictions from various simpler models, thereby enhancing the overall prediction accuracy through a meta‐learning model.…”

Section: Modeling Frameworkmentioning

confidence: 99%

Automated signal‐based evaluation of dynamic cone resistance via machine learning for subsurface characterization

Aregbesola,

Byun

2024

Computer aided Civil Eng

View full text Add to dashboard Cite

show abstract

“…It outperforms conventional inversion methods and traditional machine learning for porosity inference in handling these challenging scenarios. Neural networks that make DL models can be scaled up to adapt to diverse scenarios, including multi‐output regressions, resulting in enhanced performance (Feng et al., 2020; Kalule et al., 2023).…”

Section: Methodsmentioning

confidence: 99%

Ensemble of Neural Networks Utilizing Seismic Attributes for Rock‐Property Inversion With Uncertainty Estimation

Ntibahanana,

Jianguo,

Luemba

et al. 2024

Earth and Space Science

View full text Add to dashboard Cite

Seismic inversion holds significant importance across various domains of geoscience and engineering, including the characterization of energy resource reservoirs, the assessment of polluted sites, and CO2 storage. It is a process of estimating rock properties from seismic data that is inherently uncertain, nonlinear, non‐unique, and highly challenging. Using multiple seismic attributes increases the size of the data, requiring considerable processing resources and time. However, deep learning can accurately fit quantities of nonlinear variables, making it an excellent method for predicting spatially distributed subsurface properties. We trained some multi‐output regression neural networks to carry out porosity inversion from seismic data. We initially computed a series of seismic attributes and generated the corresponding porosity using interpreted horizons, well logs, and seismic data. Subsequently, we proposed a technique to identify the most relevant seismic attributes for porosity inversion. Because our networks work as stochastic modeling entities, we created a weight‐averaging ensemble approach to build a strong model with the highest level of accuracy. We combined realizations from baseline entities, considering their respective performance levels. Using the statistics between these realizations and the robust model, we determined the degree of uncertainty associated with the outcome. We found an R2 of 0.993 and an MAE of 0.00112 in the F3 block offshore the Netherlands, proving the method's effectiveness. The mean porosity was 0.175193, compared to 0.175626 from a reference model, and the mean uncertainty was ±0.0008998.

show abstract

“…To improve the problem of limited performance of a single model, ensemble learning has been developed; this method combines separate machine learning models through different combination strategies to improve the performance of the combined model (Nilsson, 1965;Friedman, 2001;Sammut and Webb, 2011;Zhang et al, 2022;Kalule et al, 2023). Chen and Lin used a committee machine with empirical formulas (CMEF) model to predict permeability using a collection of empirical formulas as experts.…”

Section: Introductionmentioning

confidence: 99%

Prediction of permeability in a tight sandstone reservoir using a gated network stacking model driven by data and physical models

Shi,

Bie

et al. 2024

Front. Earth Sci.

View full text Add to dashboard Cite

Introduction: Permeability is one of the most important parameters for reservoir evaluation. It is commonly measured in laboratories using underground core samples. However, it cannot describe the entire reservoir because of the limited number of cores. Therefore, petrophysicists use well logs to establish empirical equations to estimate permeability. This method has been widely used in conventional sandstone reservoirs, but it is not applicable to tight sandstone reservoirs with low porosity, extremely low permeability, and complex pore structures.Methods: Machine learning models can identify potential relationships between input features and sample labels, making them a good choice for establishing permeability prediction models. A stacking model is an ensemble learning method that aims to train a meta-learner to learn an optimal combination of expert models. However, the meta-learner does not evaluate or control the experts, making it difficult to interpret the contribution of each model. In this study, we design a gate network stacking (GNS) model, which is an algorithm that combines data and model-driven methods. First, an input log combination is selected for each expert model to ensure the best performance of the expert model and selfoptimization of the hyperparameters. Petrophysical constraints are then added to the inputs of the expert model and meta-learner, and weights are dynamically assigned to the output of the expert model. Finally, the overall performance of the model is evaluated iteratively to enhance its interpretability and robustness.Results and discussion: The GNS model is then used to predict the permeability of a tight sandstone reservoir in the Jurassic Ahe Formation in the Tarim Basin. The case study shows that the permeability predicted by the GNS model is more accurate than that of other ensemble models. This study provides a new approach for predicting the parameters of tight sandstone reservoirs.

show abstract

Stacked Ensemble Machine Learning for Porosity and Absolute Permeability Prediction of Carbonate Rock Plugs

Cited by 3 publications

References 42 publications

Automated signal‐based evaluation of dynamic cone resistance via machine learning for subsurface characterization

Automated signal‐based evaluation of dynamic cone resistance via machine learning for subsurface characterization

Ensemble of Neural Networks Utilizing Seismic Attributes for Rock‐Property Inversion With Uncertainty Estimation

Prediction of permeability in a tight sandstone reservoir using a gated network stacking model driven by data and physical models

Contact Info

Product

Resources

About