Tree Boosting Methods Comparison for Landslide Susceptibility Maps, Case Study: Kejajar, Wonosobo
Landslides in Indonesia occur almost every year and cause large material losses. Early prevention by creating a landslide susceptibility map is one way to anticipate losses due to landslides. The search for the best method for predicting landslides using machine learning with several tree boosting m...
| Main Authors: | , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
Institute of Electrical and Electronics Engineers Inc.
2023
|
| Subjects: | |
| Online Access: | https://repository.ugm.ac.id/285849/1/Tree%20Boosting%20Methods%20Comparison.pdf |
| _version_ | 1797037891894902784 |
|---|---|
| author | Arifianto, Rokhmat Wahyunggoro, Oyas Mustika, I. Wayan Adimedha, Tyto Baskara |
| author_facet | Arifianto, Rokhmat Wahyunggoro, Oyas Mustika, I. Wayan Adimedha, Tyto Baskara |
| author_sort | Arifianto, Rokhmat |
| collection | UGM |
| description | Landslides in Indonesia occur almost every year and cause large material losses. Early prevention by creating a landslide susceptibility map is one way to anticipate losses due to landslides. The search for the best method for predicting landslides using machine learning with several tree boosting methods has been carried out, but the comparison between the tree boosting methods is unknown. This study aims to compare the tree boosting methods in their use for creating landslide susceptibility maps. The case study used in this research is Kejajar District, Wonosobo. There are 25 data features used to determine landslide. The landslide data in this study is 84 polygons. The tree boosting methods used include XGBoost, LGBM, Adaboost and Catboost. Hyperparameter tuning and k-fold cross validation were used to get the best model. The results of the comparison show that LGBM is the best method with accuracy, recall, f1 score, and ROC AUC values of 0.9903, 0.9360, 0.9154, and 0.9648 respectively. It indicates that the boosting method using LGBM can provide good results for creating a landslide susceptibility map. |
| first_indexed | 2024-03-14T00:11:00Z |
| format | Conference or Workshop Item |
| id | oai:generic.eprints.org:285849 |
| institution | Universiti Gadjah Mada |
| language | English |
| last_indexed | 2024-03-14T00:11:00Z |
| publishDate | 2023 |
| publisher | Institute of Electrical and Electronics Engineers Inc. |
| record_format | dspace |
| spelling | oai:generic.eprints.org:2858492024-03-05T02:07:13Z https://repository.ugm.ac.id/285849/ Tree Boosting Methods Comparison for Landslide Susceptibility Maps, Case Study: Kejajar, Wonosobo Arifianto, Rokhmat Wahyunggoro, Oyas Mustika, I. Wayan Adimedha, Tyto Baskara Electrical and Electronic Engineering not elsewhere classified Landslides in Indonesia occur almost every year and cause large material losses. Early prevention by creating a landslide susceptibility map is one way to anticipate losses due to landslides. The search for the best method for predicting landslides using machine learning with several tree boosting methods has been carried out, but the comparison between the tree boosting methods is unknown. This study aims to compare the tree boosting methods in their use for creating landslide susceptibility maps. The case study used in this research is Kejajar District, Wonosobo. There are 25 data features used to determine landslide. The landslide data in this study is 84 polygons. The tree boosting methods used include XGBoost, LGBM, Adaboost and Catboost. Hyperparameter tuning and k-fold cross validation were used to get the best model. The results of the comparison show that LGBM is the best method with accuracy, recall, f1 score, and ROC AUC values of 0.9903, 0.9360, 0.9154, and 0.9648 respectively. It indicates that the boosting method using LGBM can provide good results for creating a landslide susceptibility map. Institute of Electrical and Electronics Engineers Inc. 2023 Conference or Workshop Item PeerReviewed application/pdf en https://repository.ugm.ac.id/285849/1/Tree%20Boosting%20Methods%20Comparison.pdf Arifianto, Rokhmat and Wahyunggoro, Oyas and Mustika, I. Wayan and Adimedha, Tyto Baskara (2023) Tree Boosting Methods Comparison for Landslide Susceptibility Maps, Case Study: Kejajar, Wonosobo. In: Proceedings of the 2023 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology, IAICT 2023, 13 Juli 2023 - 15 Juli 2023, Bali Indonesia. https://ieeexplore.ieee.org/document/10205882 |
| spellingShingle | Electrical and Electronic Engineering not elsewhere classified Arifianto, Rokhmat Wahyunggoro, Oyas Mustika, I. Wayan Adimedha, Tyto Baskara Tree Boosting Methods Comparison for Landslide Susceptibility Maps, Case Study: Kejajar, Wonosobo |
| title | Tree Boosting Methods Comparison for Landslide Susceptibility Maps, Case Study: Kejajar, Wonosobo |
| title_full | Tree Boosting Methods Comparison for Landslide Susceptibility Maps, Case Study: Kejajar, Wonosobo |
| title_fullStr | Tree Boosting Methods Comparison for Landslide Susceptibility Maps, Case Study: Kejajar, Wonosobo |
| title_full_unstemmed | Tree Boosting Methods Comparison for Landslide Susceptibility Maps, Case Study: Kejajar, Wonosobo |
| title_short | Tree Boosting Methods Comparison for Landslide Susceptibility Maps, Case Study: Kejajar, Wonosobo |
| title_sort | tree boosting methods comparison for landslide susceptibility maps case study kejajar wonosobo |
| topic | Electrical and Electronic Engineering not elsewhere classified |
| url | https://repository.ugm.ac.id/285849/1/Tree%20Boosting%20Methods%20Comparison.pdf |
| work_keys_str_mv | AT arifiantorokhmat treeboostingmethodscomparisonforlandslidesusceptibilitymapscasestudykejajarwonosobo AT wahyunggorooyas treeboostingmethodscomparisonforlandslidesusceptibilitymapscasestudykejajarwonosobo AT mustikaiwayan treeboostingmethodscomparisonforlandslidesusceptibilitymapscasestudykejajarwonosobo AT adimedhatytobaskara treeboostingmethodscomparisonforlandslidesusceptibilitymapscasestudykejajarwonosobo |