stacks: Stacked Ensemble Modeling with Tidy Data
Principles

Couch, Simon; Kühn, Max

doi:10.21105/joss.04471

Cited by 7 publications

(7 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The accuracy of these models varies with respect to the applied pre-processing. The PCA is frequently used to decrease the redundancy of the seismic attributes before the modeling, which is a common issue in seismic characterization studies (Chopra et al 2018, Jesus et al 2019, Carvalho et al 2022. The results showed that PCA had a limited effect on improving the MLP model but significantly deteriorated the performance of SVM (Table 1).…”

Section: Resultsmentioning

confidence: 99%

An advanced ensemble modeling approach for predicting carbonate reservoir porosity from seismic attributes

Topór,

Sowiżdżał

2023

geol

View full text Add to dashboard Cite

This study uses a machine learning (ML) ensemble modeling approach to predict porosity from multiple seismic attributes in one of the most promising Main Dolomite hydrocarbon reservoirs in NW Poland. The presented workflow tests five different model types of varying complexity: K-nearest neighbors (KNN), random forests (RF), extreme gradient boosting (XGB), support vector machine (SVM), single layer neural network with multilayer perceptron (MLP). The selected models are additionally run with different configurations originating from the pre-processing stage, including Yeo–Johnson transformation (YJ) and principal component analysis (PCA). The race ANOVA method across resample data is used to tune the best hyperparameters for each model. The model candidates and the role of different pre-processors are evaluated based on standard ML metrics – coefficient of determination (R2), root mean squared error (RMSE), and mean absolute error (MAE). The model stacking is performed on five model candidates: two KNN, two XGB, and one SVM PCA with a marginal role. The results of the ensemble model showed superior accuracy over single learners, with all metrics (R2 0.890, RMSE 0.0252, MAE 0.168). It also turned out to be almost three times better than the neural net (NN) results obtained from commercial software on the same testing set (R2 0.318, RMSE 0.0628, MAE 0.0487). The spatial distribution of porosity from the ensemble model indicated areas of good reservoir properties that overlap with hydrocarbon production fields. This observation completes the evaluation of the ensemble technique results from model metrics. Overall, the proposed solution is a promising tool for better porosity prediction and understanding of heterogeneous carbonate reservoirs from multiple seismic attributes.

show abstract

Section: Resultsmentioning

confidence: 99%

An advanced ensemble modeling approach for predicting carbonate reservoir porosity from seismic attributes

Topór,

Sowiżdżał

2023

geol

View full text Add to dashboard Cite

show abstract

“…Pseudo-code for stacking algorithm implemented for regression challenge is given in Algorithm 1. For the classification challenge, the R based implementation of stacking in package stacks Couch and Kuhn (2022) was used. The default stacks implementation fits a selection of candidate models over predetermined grids of tuning parameters and blends the predictions of the candidate models from all the tuning parameter settings in the grids.…”

Section: Meta-learnersmentioning

confidence: 99%

What is to be gained by ensemble models in analysis of spectroscopic data?

Domijan

2023

Chemometrics and Intelligent Laboratory Systems

View full text Add to dashboard Cite

“…All statistical analysis was performed with R programming language v.4.0.3 19 . Packages used were 'tidymodels,' 20 'tidyverse,' 21 'stacks,' 22 'workflowsets,' 23 'pROC,' 24 'readxl,' 25 'RColorBrewer,' 26 'viridis,' 27 'GGally,' 28 and 'corrplot.' 29…”

Section: Softwarementioning

confidence: 99%

Multicenter analysis of COVID-19 hospitalizations and stacking machine learning algorithms for prediction of high-risk patients

Shaw,

Bassily,

Patel

et al. 2023

Preprint

View full text Add to dashboard Cite

ObjectiveTo create and validate an ensemble of machine learning algorithms to accurately predict ICU admission or mortality upon initial presentation to the emergency department.MethodsThis is a retrospective cohort study of a multicenter hospital system in the United States. The electronic health record was queried from March 2020 to December 2021 for patients who presented to the emergency department who were subsequently COVID-positive. Associated patient demographics, vitals, and laboratory vitals were obtained. High-risk individuals were defined as those who required ICU admission or died; low-risk individuals did not meet those criteria. The dataset was split into a 3:1 training to testing dataset. A machine learning ensemble stack was built to predict ICU admission and mortality.ResultsOf the 3,142 hospital admissions with a COVID positive test, there were 1,128 (36%) individuals labeled as high-risk, and 2,014 (64%) as low-risk. We obtained 147 unique variables. CRP, LDH, procalcitonin, glucose, anion gap, creatinine, age, oxygen saturation, oxygen device, and obtainment of an ABG were chosen. Six machine learning models were then trained over model-specific hyperparameters, and then assessed on the testing dataset, generating an area under the receiver operator curve of 0.751, with a specificity of 95% in predicting high-risk individuals based on an initial emergency department assessment.ConclusionA novel machine learning model was generated to predict ICU admission and patient mortality from a multicenter hospital system and validated on unseen data.

show abstract

stacks: Stacked Ensemble Modeling with Tidy Data Principles

Cited by 7 publications

References 4 publications

An advanced ensemble modeling approach for predicting carbonate reservoir porosity from seismic attributes

An advanced ensemble modeling approach for predicting carbonate reservoir porosity from seismic attributes

What is to be gained by ensemble models in analysis of spectroscopic data?

Multicenter analysis of COVID-19 hospitalizations and stacking machine learning algorithms for prediction of high-risk patients

Contact Info

Product

Resources

About