A hybrid multi-step sensitivity-driven evolutionary polynomial regression enables robust model structure selection

Gomes, Ruan G. S.; Gomes, Guilherme José Cunha; Vrugt, Jasper A.

doi:10.1016/j.engappai.2022.105421

Cited by 4 publications

(3 citation statements)

References 59 publications

(118 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, as discussed in the introductory section, the single-objective methodology is susceptible to overfitting, leading to equations with poor generalization ability. In response, researchers have proposed multiobjective methodologies to overcome this limitation and obtain equations with enhanced generalization ability [27][28][29]32].…”

Section: Traditional Epr Methodsmentioning

confidence: 99%

“…In fact, due to this limitation, some researchers (i) run EPR codes multiple times until they find a good predictive capacity [31], (ii) choose models with a better physical response based on trial and error, (iii) or simply neglect sensitivity analysis as part of machine learning postprocessing [28]. This research gap has motivated the introduction of the multi-step sensitivity-driven framework of the MODEGA-SD method [32]. The core concept of this approach involves conducting Monte Carlo simulations, which EPR means running a specified number of independent EPR simulations.…”

Section: Evolutionary Polynomial Regression (Epr) Is a Hybrid Regress...mentioning

confidence: 99%

“…The logarithm of the permeability of tight carbonate rocks, log 10 (K) was the output. The MODEGA-SD method [32] was improved to investigate the influence of split-sampling cross-validation on statistical model performance metrics and sensitivity analysis of MODEGA-SD-derived models. Finally, our proposed model was compared to other machine learning models found in the existing literature.…”

Section: Evolutionary Polynomial Regression (Epr) Is a Hybrid Regress...mentioning

confidence: 99%

See 2 more Smart Citations

Permeability of tight carbonate rocks from sensitivity-driven Evolutionary Polynomial Regression

Gomes,

Vrugt

et al. 2024

Preprint

View full text Add to dashboard Cite

The permeability (K) of tight carbonate rocks is important to maximize the efficiency of hydrocarbon production and overall reservoir management. While such property is crucial for engineering design, conducting experimental tests to determine K can be both time-consuming and expensive. As such, reliable and high-fidelity models derived with soft computing techniques become useful for estimating K. Using a data set containing samples from 130 data points published in the literature, this work developed a sensitivity-driven evolutionary polynomial regression (EPR) model to predict K. The model computes the permeability, log10K (mD), as a function of three explanatory variables: porosity, ϕ (-), formation factor, F (-), and the characteristic pore throat diameter, dPT (m). One unique feature of our approachis that it considers the physical meaning of the variables that influence the investigated phenomenon during the construction of the model. Verification of the methodology was carried out using split-sampling cross-validation. The developed model showed attributes such as parsimony (lower number of parameters and input variables), good predictive capability (accurate tracking observed log10K), generalization ability (preserving physical meaning), and robustness (consistent performance under cross-validation). Sensitivity analysis revealed that the model can adequately simulate the increase in K with increasing ϕ and dPT, as well as its capacity to capture the non-linear relationship between log10K and F. Comparison of simulated K-values with results of models published in the literature, further validated the ability of our optimum EPR model structure. The proposed model shows potential as a promising method to estimate the permeability of tight carbonate rocks.

show abstract

Section: Traditional Epr Methodsmentioning

confidence: 99%

Section: Evolutionary Polynomial Regression (Epr) Is a Hybrid Regress...mentioning

confidence: 99%

Section: Evolutionary Polynomial Regression (Epr) Is a Hybrid Regress...mentioning

confidence: 99%

See 1 more Smart Citation

Permeability of tight carbonate rocks from sensitivity-driven Evolutionary Polynomial Regression

Gomes,

Vrugt

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

Finite element and evolutionary polynomial regression analyses of the effect of a cavity on the bearing capacity factor $${{\varvec{N}}}_{{\varvec{c}}}$$ of strip footing

Alzabeebee,

Ismael,

Keawsawasvong

et al. 2024

Model. Earth Syst. Environ.

View full text Add to dashboard Cite

Predicting Tunnel-Induced Settlement in Cohesionless soils in Greenfield Condition

El Naggar,

Youssef,

El Naggar

2023

Transportation Geotechnics

View full text Add to dashboard Cite

A hybrid multi-step sensitivity-driven evolutionary polynomial regression enables robust model structure selection

Cited by 4 publications

References 59 publications

Permeability of tight carbonate rocks from sensitivity-driven Evolutionary Polynomial Regression

Permeability of tight carbonate rocks from sensitivity-driven Evolutionary Polynomial Regression

Finite element and evolutionary polynomial regression analyses of the effect of a cavity on the bearing capacity factor $${{\varvec{N}}}_{{\varvec{c}}}$$ of strip footing

Predicting Tunnel-Induced Settlement in Cohesionless soils in Greenfield Condition

Contact Info

Product

Resources

About