A Stacked Generalization Model to Enhance Prediction of Earthquake-Induced Soil Liquefaction
Earthquakes cause liquefaction, which disturbs the design phase during the building construction process. The potential of earthquake-induced liquefaction was estimated initially based on analytical and numerical methods. The conventional methods face problems in providing empirical formulations in...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/19/7292 |
| _version_ | 1797476940021497856 |
|---|---|
| author | Sri Preethaa Yuvaraj Natarajan Arun Pandian Rathinakumar Dong-Eun Lee Young Choi Young-Jun Park Chang-Yong Yi |
| author_facet | Sri Preethaa Yuvaraj Natarajan Arun Pandian Rathinakumar Dong-Eun Lee Young Choi Young-Jun Park Chang-Yong Yi |
| author_sort | Sri Preethaa |
| collection | DOAJ |
| description | Earthquakes cause liquefaction, which disturbs the design phase during the building construction process. The potential of earthquake-induced liquefaction was estimated initially based on analytical and numerical methods. The conventional methods face problems in providing empirical formulations in the presence of uncertainties. Accordingly, machine learning (ML) algorithms were implemented to predict the liquefaction potential. Although the ML models perform well with the specific liquefaction dataset, they fail to produce accurate results when used on other datasets. This study proposes a stacked generalization model (SGM), constructed by aggregating algorithms with the best performances, such as the multilayer perceptron regressor (MLPR), support vector regression (SVR), and linear regressor, to build an efficient prediction model to estimate the potential of earthquake-induced liquefaction on settlements. The dataset from the Korean Geotechnical Information database system and the standard penetration test conducted on the 2016 Pohang earthquake in South Korea were used. The model performance was evaluated by using the R<sup>2</sup> score, mean-square error (MSE), standard deviation, covariance, and root-MSE. Model validation was performed to compare the performance of the proposed SGM with SVR and MLPR models. The proposed SGM yielded the best performance compared with those of the other base models. |
| first_indexed | 2024-03-09T21:10:53Z |
| format | Article |
| id | doaj.art-304f21ffcced418c8b01ae993d2e76ce |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T21:10:53Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-304f21ffcced418c8b01ae993d2e76ce2023-11-23T21:46:46ZengMDPI AGSensors1424-82202022-09-012219729210.3390/s22197292A Stacked Generalization Model to Enhance Prediction of Earthquake-Induced Soil LiquefactionSri Preethaa0Yuvaraj Natarajan1Arun Pandian Rathinakumar2Dong-Eun Lee3Young Choi4Young-Jun Park5Chang-Yong Yi6Department of Artificial Intelligence and Data Science, KPR Institute of Engineering and Technology, Coimbatore 641665, IndiaDepartment of Artificial Intelligence and Data Science, KPR Institute of Engineering and Technology, Coimbatore 641665, IndiaResearch Engineer, QpiCloud Technologies, Bangalore 560045, IndiaSchool of Architecture, Civil, Environment and Energy Engineering, Kyungpook National University, 80 Daehak-ro, Buk-gu, Daegu 41566, KoreaEarth Turbine, 36, Dongdeok-ro 40-gil, Jung-gu, Daegu 41905, KoreaIntelligent Construction Automation Center, Kyungpook National University, 80, Daehak-ro, Buk-gu, Daegu 41566, KoreaIntelligent Construction Automation Center, Kyungpook National University, 80, Daehak-ro, Buk-gu, Daegu 41566, KoreaEarthquakes cause liquefaction, which disturbs the design phase during the building construction process. The potential of earthquake-induced liquefaction was estimated initially based on analytical and numerical methods. The conventional methods face problems in providing empirical formulations in the presence of uncertainties. Accordingly, machine learning (ML) algorithms were implemented to predict the liquefaction potential. Although the ML models perform well with the specific liquefaction dataset, they fail to produce accurate results when used on other datasets. This study proposes a stacked generalization model (SGM), constructed by aggregating algorithms with the best performances, such as the multilayer perceptron regressor (MLPR), support vector regression (SVR), and linear regressor, to build an efficient prediction model to estimate the potential of earthquake-induced liquefaction on settlements. The dataset from the Korean Geotechnical Information database system and the standard penetration test conducted on the 2016 Pohang earthquake in South Korea were used. The model performance was evaluated by using the R<sup>2</sup> score, mean-square error (MSE), standard deviation, covariance, and root-MSE. Model validation was performed to compare the performance of the proposed SGM with SVR and MLPR models. The proposed SGM yielded the best performance compared with those of the other base models.https://www.mdpi.com/1424-8220/22/19/7292liquefactionpredictionmachine learningensemble modelssettlementdata augmentation |
| spellingShingle | Sri Preethaa Yuvaraj Natarajan Arun Pandian Rathinakumar Dong-Eun Lee Young Choi Young-Jun Park Chang-Yong Yi A Stacked Generalization Model to Enhance Prediction of Earthquake-Induced Soil Liquefaction Sensors liquefaction prediction machine learning ensemble models settlement data augmentation |
| title | A Stacked Generalization Model to Enhance Prediction of Earthquake-Induced Soil Liquefaction |
| title_full | A Stacked Generalization Model to Enhance Prediction of Earthquake-Induced Soil Liquefaction |
| title_fullStr | A Stacked Generalization Model to Enhance Prediction of Earthquake-Induced Soil Liquefaction |
| title_full_unstemmed | A Stacked Generalization Model to Enhance Prediction of Earthquake-Induced Soil Liquefaction |
| title_short | A Stacked Generalization Model to Enhance Prediction of Earthquake-Induced Soil Liquefaction |
| title_sort | stacked generalization model to enhance prediction of earthquake induced soil liquefaction |
| topic | liquefaction prediction machine learning ensemble models settlement data augmentation |
| url | https://www.mdpi.com/1424-8220/22/19/7292 |
| work_keys_str_mv | AT sripreethaa astackedgeneralizationmodeltoenhancepredictionofearthquakeinducedsoilliquefaction AT yuvarajnatarajan astackedgeneralizationmodeltoenhancepredictionofearthquakeinducedsoilliquefaction AT arunpandianrathinakumar astackedgeneralizationmodeltoenhancepredictionofearthquakeinducedsoilliquefaction AT dongeunlee astackedgeneralizationmodeltoenhancepredictionofearthquakeinducedsoilliquefaction AT youngchoi astackedgeneralizationmodeltoenhancepredictionofearthquakeinducedsoilliquefaction AT youngjunpark astackedgeneralizationmodeltoenhancepredictionofearthquakeinducedsoilliquefaction AT changyongyi astackedgeneralizationmodeltoenhancepredictionofearthquakeinducedsoilliquefaction AT sripreethaa stackedgeneralizationmodeltoenhancepredictionofearthquakeinducedsoilliquefaction AT yuvarajnatarajan stackedgeneralizationmodeltoenhancepredictionofearthquakeinducedsoilliquefaction AT arunpandianrathinakumar stackedgeneralizationmodeltoenhancepredictionofearthquakeinducedsoilliquefaction AT dongeunlee stackedgeneralizationmodeltoenhancepredictionofearthquakeinducedsoilliquefaction AT youngchoi stackedgeneralizationmodeltoenhancepredictionofearthquakeinducedsoilliquefaction AT youngjunpark stackedgeneralizationmodeltoenhancepredictionofearthquakeinducedsoilliquefaction AT changyongyi stackedgeneralizationmodeltoenhancepredictionofearthquakeinducedsoilliquefaction |