An optimized XGBoost-based machine learning method for predicting wave run-up on a sloping beach
Accurate and computationally efficient prediction of wave run-up is required to mitigate the impacts of inundation and erosion caused by tides, storm surges, and even tsunami waves. The conventional methods for calculating wave run-up involve physical experiments or numerical modeling. Machine learn...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-01-01
|
| Series: | MethodsX |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2215016123001206 |
| _version_ | 1797796463847145472 |
|---|---|
| author | Dede Tarwidi Sri Redjeki Pudjaprasetya Didit Adytia Mochamad Apri |
| author_facet | Dede Tarwidi Sri Redjeki Pudjaprasetya Didit Adytia Mochamad Apri |
| author_sort | Dede Tarwidi |
| collection | DOAJ |
| description | Accurate and computationally efficient prediction of wave run-up is required to mitigate the impacts of inundation and erosion caused by tides, storm surges, and even tsunami waves. The conventional methods for calculating wave run-up involve physical experiments or numerical modeling. Machine learning methods have recently become a part of wave run-up model development due to their robustness in dealing with large and complex data. In this paper, an extreme gradient boosting (XGBoost)-based machine learning method is introduced for predicting wave run-up on a sloping beach. More than 400 laboratory observations of wave run-up were utilized as training datasets to construct the XGBoost model. The hyperparameter tuning through the grid search approach was performed to obtain an optimized XGBoost model. The performance of the XGBoost method is compared to that of three different machine learning approaches: multiple linear regression (MLR), support vector regression (SVR), and random forest (RF). The validation evaluation results demonstrate that the proposed algorithm outperforms other machine learning approaches in predicting the wave run-up with a correlation coefficient (R2) of 0.98675, a mean absolute percentage error (MAPE) of 6.635%, and a root mean squared error (RMSE) of 0.03902. Compared to empirical formulas, which are often limited to a fixed range of slopes, the XGBoost model is applicable over a broader range of beach slopes and incident wave amplitudes. • The optimized XGBoost method is a feasible alternative to existing empirical formulas and classical numerical models for predicting wave run-up. • Hyperparameter tuning is performed using the grid search method, resulting in a highly accurate machine-learning model. • Our findings indicate that the XGBoost method is more applicable than empirical formulas and more efficient than numerical models. |
| first_indexed | 2024-03-13T03:33:29Z |
| format | Article |
| id | doaj.art-7fb928c20d3e43aca3f93fa71141e085 |
| institution | Directory Open Access Journal |
| issn | 2215-0161 |
| language | English |
| last_indexed | 2024-03-13T03:33:29Z |
| publishDate | 2023-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | MethodsX |
| spelling | doaj.art-7fb928c20d3e43aca3f93fa71141e0852023-06-24T05:17:24ZengElsevierMethodsX2215-01612023-01-0110102119An optimized XGBoost-based machine learning method for predicting wave run-up on a sloping beachDede Tarwidi0Sri Redjeki Pudjaprasetya1Didit Adytia2Mochamad Apri3Industrial and Financial Mathematics Research Group, Faculty of Mathematics and Natural Sciences, Institut Teknologi Bandung, Bandung, Indonesia; School of Computing, Telkom University, Bandung, IndonesiaIndustrial and Financial Mathematics Research Group, Faculty of Mathematics and Natural Sciences, Institut Teknologi Bandung, Bandung, Indonesia; Corresponding author.School of Computing, Telkom University, Bandung, IndonesiaIndustrial and Financial Mathematics Research Group, Faculty of Mathematics and Natural Sciences, Institut Teknologi Bandung, Bandung, IndonesiaAccurate and computationally efficient prediction of wave run-up is required to mitigate the impacts of inundation and erosion caused by tides, storm surges, and even tsunami waves. The conventional methods for calculating wave run-up involve physical experiments or numerical modeling. Machine learning methods have recently become a part of wave run-up model development due to their robustness in dealing with large and complex data. In this paper, an extreme gradient boosting (XGBoost)-based machine learning method is introduced for predicting wave run-up on a sloping beach. More than 400 laboratory observations of wave run-up were utilized as training datasets to construct the XGBoost model. The hyperparameter tuning through the grid search approach was performed to obtain an optimized XGBoost model. The performance of the XGBoost method is compared to that of three different machine learning approaches: multiple linear regression (MLR), support vector regression (SVR), and random forest (RF). The validation evaluation results demonstrate that the proposed algorithm outperforms other machine learning approaches in predicting the wave run-up with a correlation coefficient (R2) of 0.98675, a mean absolute percentage error (MAPE) of 6.635%, and a root mean squared error (RMSE) of 0.03902. Compared to empirical formulas, which are often limited to a fixed range of slopes, the XGBoost model is applicable over a broader range of beach slopes and incident wave amplitudes. • The optimized XGBoost method is a feasible alternative to existing empirical formulas and classical numerical models for predicting wave run-up. • Hyperparameter tuning is performed using the grid search method, resulting in a highly accurate machine-learning model. • Our findings indicate that the XGBoost method is more applicable than empirical formulas and more efficient than numerical models.http://www.sciencedirect.com/science/article/pii/S2215016123001206XGBoost |
| spellingShingle | Dede Tarwidi Sri Redjeki Pudjaprasetya Didit Adytia Mochamad Apri An optimized XGBoost-based machine learning method for predicting wave run-up on a sloping beach MethodsX XGBoost |
| title | An optimized XGBoost-based machine learning method for predicting wave run-up on a sloping beach |
| title_full | An optimized XGBoost-based machine learning method for predicting wave run-up on a sloping beach |
| title_fullStr | An optimized XGBoost-based machine learning method for predicting wave run-up on a sloping beach |
| title_full_unstemmed | An optimized XGBoost-based machine learning method for predicting wave run-up on a sloping beach |
| title_short | An optimized XGBoost-based machine learning method for predicting wave run-up on a sloping beach |
| title_sort | optimized xgboost based machine learning method for predicting wave run up on a sloping beach |
| topic | XGBoost |
| url | http://www.sciencedirect.com/science/article/pii/S2215016123001206 |
| work_keys_str_mv | AT dedetarwidi anoptimizedxgboostbasedmachinelearningmethodforpredictingwaverunuponaslopingbeach AT sriredjekipudjaprasetya anoptimizedxgboostbasedmachinelearningmethodforpredictingwaverunuponaslopingbeach AT diditadytia anoptimizedxgboostbasedmachinelearningmethodforpredictingwaverunuponaslopingbeach AT mochamadapri anoptimizedxgboostbasedmachinelearningmethodforpredictingwaverunuponaslopingbeach AT dedetarwidi optimizedxgboostbasedmachinelearningmethodforpredictingwaverunuponaslopingbeach AT sriredjekipudjaprasetya optimizedxgboostbasedmachinelearningmethodforpredictingwaverunuponaslopingbeach AT diditadytia optimizedxgboostbasedmachinelearningmethodforpredictingwaverunuponaslopingbeach AT mochamadapri optimizedxgboostbasedmachinelearningmethodforpredictingwaverunuponaslopingbeach |