Ensemble machine learning models based on Reduced Error Pruning Tree for prediction of rainfall-induced landslides
In this paper, we developed highly accurate ensemble machine learning models integrating Reduced Error Pruning Tree (REPT) as a base classifier with the Bagging (B), Decorate (D), and Random Subspace (RSS) ensemble learning techniques for spatial prediction of rainfall-induced landslides in the Utta...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2021-05-01
|
| Series: | International Journal of Digital Earth |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/17538947.2020.1860145 |
| _version_ | 1827811165877567488 |
|---|---|
| author | Binh Thai Pham Abolfazl Jaafari Trung Nguyen-Thoi Tran Van Phong Huu Duy Nguyen Neelima Satyam Md Masroor Sufia Rehman Haroon Sajjad Mehebub Sahana Hiep Van Le Indra Prakash |
| author_facet | Binh Thai Pham Abolfazl Jaafari Trung Nguyen-Thoi Tran Van Phong Huu Duy Nguyen Neelima Satyam Md Masroor Sufia Rehman Haroon Sajjad Mehebub Sahana Hiep Van Le Indra Prakash |
| author_sort | Binh Thai Pham |
| collection | DOAJ |
| description | In this paper, we developed highly accurate ensemble machine learning models integrating Reduced Error Pruning Tree (REPT) as a base classifier with the Bagging (B), Decorate (D), and Random Subspace (RSS) ensemble learning techniques for spatial prediction of rainfall-induced landslides in the Uttarkashi district, located in the Himalayan range, India. To do so, a total of 103 historical landslide events were linked to twelve conditioning factors for generating training and validation datasets. Root Mean Square Error (RMSE) and Area Under the receiver operating characteristic Curve (AUC) were used to evaluate the training and validation performances of the models. The results showed that the single REPT model and its derived ensembles provided a satisfactory accuracy for the prediction of landslides. The D-REPT model with RMSE = 0.351 and AUC = 0.907 was identified as the most accurate model, followed by RSS-REPT (RMSE = 0.353 and AUC = 0.898), B-REPT (RMSE = 0.396 and AUC = 0.876), and the single REPT model (RMSE = 0.398 and AUC = 0.836), respectively. The prominent ensemble models proposed and verified in this study provide engineers and modelers with insights for development of more advanced predictive models for different landslide-susceptible areas around the world. |
| first_indexed | 2024-03-11T23:01:19Z |
| format | Article |
| id | doaj.art-30ae93e96a564842aac8d38a55ba7f13 |
| institution | Directory Open Access Journal |
| issn | 1753-8947 1753-8955 |
| language | English |
| last_indexed | 2024-03-11T23:01:19Z |
| publishDate | 2021-05-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | International Journal of Digital Earth |
| spelling | doaj.art-30ae93e96a564842aac8d38a55ba7f132023-09-21T14:57:09ZengTaylor & Francis GroupInternational Journal of Digital Earth1753-89471753-89552021-05-0114557559610.1080/17538947.2020.18601451860145Ensemble machine learning models based on Reduced Error Pruning Tree for prediction of rainfall-induced landslidesBinh Thai Pham0Abolfazl Jaafari1Trung Nguyen-Thoi2Tran Van Phong3Huu Duy Nguyen4Neelima Satyam5Md Masroor6Sufia Rehman7Haroon Sajjad8Mehebub Sahana9Hiep Van Le10Indra Prakash11Ton Duc Thang UniversityAgricultural Research, Education, and Extension Organization (AREEO)Ton Duc Thang UniversityVietnam Academy of Sciences and TechnologyVietnam National UniversityIndian Institute of Technology IndoreJamia Millia IslamiaJamia Millia IslamiaJamia Millia IslamiaUniversity of ManchesterDuy Tan UniversityDDG(R) Geological Survey of IndiaIn this paper, we developed highly accurate ensemble machine learning models integrating Reduced Error Pruning Tree (REPT) as a base classifier with the Bagging (B), Decorate (D), and Random Subspace (RSS) ensemble learning techniques for spatial prediction of rainfall-induced landslides in the Uttarkashi district, located in the Himalayan range, India. To do so, a total of 103 historical landslide events were linked to twelve conditioning factors for generating training and validation datasets. Root Mean Square Error (RMSE) and Area Under the receiver operating characteristic Curve (AUC) were used to evaluate the training and validation performances of the models. The results showed that the single REPT model and its derived ensembles provided a satisfactory accuracy for the prediction of landslides. The D-REPT model with RMSE = 0.351 and AUC = 0.907 was identified as the most accurate model, followed by RSS-REPT (RMSE = 0.353 and AUC = 0.898), B-REPT (RMSE = 0.396 and AUC = 0.876), and the single REPT model (RMSE = 0.398 and AUC = 0.836), respectively. The prominent ensemble models proposed and verified in this study provide engineers and modelers with insights for development of more advanced predictive models for different landslide-susceptible areas around the world.http://dx.doi.org/10.1080/17538947.2020.1860145machine learningensemble modelingbaggingdecoraterandom subspace |
| spellingShingle | Binh Thai Pham Abolfazl Jaafari Trung Nguyen-Thoi Tran Van Phong Huu Duy Nguyen Neelima Satyam Md Masroor Sufia Rehman Haroon Sajjad Mehebub Sahana Hiep Van Le Indra Prakash Ensemble machine learning models based on Reduced Error Pruning Tree for prediction of rainfall-induced landslides International Journal of Digital Earth machine learning ensemble modeling bagging decorate random subspace |
| title | Ensemble machine learning models based on Reduced Error Pruning Tree for prediction of rainfall-induced landslides |
| title_full | Ensemble machine learning models based on Reduced Error Pruning Tree for prediction of rainfall-induced landslides |
| title_fullStr | Ensemble machine learning models based on Reduced Error Pruning Tree for prediction of rainfall-induced landslides |
| title_full_unstemmed | Ensemble machine learning models based on Reduced Error Pruning Tree for prediction of rainfall-induced landslides |
| title_short | Ensemble machine learning models based on Reduced Error Pruning Tree for prediction of rainfall-induced landslides |
| title_sort | ensemble machine learning models based on reduced error pruning tree for prediction of rainfall induced landslides |
| topic | machine learning ensemble modeling bagging decorate random subspace |
| url | http://dx.doi.org/10.1080/17538947.2020.1860145 |
| work_keys_str_mv | AT binhthaipham ensemblemachinelearningmodelsbasedonreducederrorpruningtreeforpredictionofrainfallinducedlandslides AT abolfazljaafari ensemblemachinelearningmodelsbasedonreducederrorpruningtreeforpredictionofrainfallinducedlandslides AT trungnguyenthoi ensemblemachinelearningmodelsbasedonreducederrorpruningtreeforpredictionofrainfallinducedlandslides AT tranvanphong ensemblemachinelearningmodelsbasedonreducederrorpruningtreeforpredictionofrainfallinducedlandslides AT huuduynguyen ensemblemachinelearningmodelsbasedonreducederrorpruningtreeforpredictionofrainfallinducedlandslides AT neelimasatyam ensemblemachinelearningmodelsbasedonreducederrorpruningtreeforpredictionofrainfallinducedlandslides AT mdmasroor ensemblemachinelearningmodelsbasedonreducederrorpruningtreeforpredictionofrainfallinducedlandslides AT sufiarehman ensemblemachinelearningmodelsbasedonreducederrorpruningtreeforpredictionofrainfallinducedlandslides AT haroonsajjad ensemblemachinelearningmodelsbasedonreducederrorpruningtreeforpredictionofrainfallinducedlandslides AT mehebubsahana ensemblemachinelearningmodelsbasedonreducederrorpruningtreeforpredictionofrainfallinducedlandslides AT hiepvanle ensemblemachinelearningmodelsbasedonreducederrorpruningtreeforpredictionofrainfallinducedlandslides AT indraprakash ensemblemachinelearningmodelsbasedonreducederrorpruningtreeforpredictionofrainfallinducedlandslides |