Combination four different ensemble algorithms with the generalized linear model (GLM) for predicting forest fire susceptibility
AbstractIn this study, the generalized linear model (GLM) and four ensemble methods (partial least squares (PLS), boosting, bagging, and Bayesian) were applied to predict forest fire hazard in the Chalus Rood watershed in the Mazandaran Province, Iran. Data from 108 historical forest fire events col...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Taylor & Francis Group
2023-12-01
|
Series: | Geomatics, Natural Hazards & Risk |
Subjects: | |
Online Access: | https://www.tandfonline.com/doi/10.1080/19475705.2023.2206512 |
_version_ | 1797389247020269568 |
---|---|
author | Saeid Janizadeh Sayed M. Bateni Changhyun Jun Jungho Im Hao-Thing Pai Shahab S. Band Amir Mosavi |
author_facet | Saeid Janizadeh Sayed M. Bateni Changhyun Jun Jungho Im Hao-Thing Pai Shahab S. Band Amir Mosavi |
author_sort | Saeid Janizadeh |
collection | DOAJ |
description | AbstractIn this study, the generalized linear model (GLM) and four ensemble methods (partial least squares (PLS), boosting, bagging, and Bayesian) were applied to predict forest fire hazard in the Chalus Rood watershed in the Mazandaran Province, Iran. Data from 108 historical forest fire events collected through field surveys were applied as the basis of the analysis. About 70% of the data were used for training the models, while the remaining 30% was used for testing. A total of 14 environmental, climatic, and vegetation variables were used as input features to the models to predict forest fire probability. After conducting a multicollinearity test on the independent variables, the GLM and the ensemble models were applied for modeling. The efficiency of the models was evaluated using receiver operating characteristic (ROC) curve parameters. Results from the validation process, based on the area under the ROC curve (AUC), showed that the GLM, PLS-GLM, boosted-GLM, Bagging-GLM, and Bayesian-GLM models had efficiencies of 0.79, 0.75, 0.81, 0.84, and 0.85, respectively. The results indicated that all ensemble methods, except the PLS algorithm, improved the performance of the GLM model in modeling forest fire hazards in the Chalus Rood watershed, with the Bayesian algorithm being the most efficient method among them. |
first_indexed | 2024-03-08T22:53:05Z |
format | Article |
id | doaj.art-f66ffa9595144ba69c390b5ce224fb48 |
institution | Directory Open Access Journal |
issn | 1947-5705 1947-5713 |
language | English |
last_indexed | 2024-03-08T22:53:05Z |
publishDate | 2023-12-01 |
publisher | Taylor & Francis Group |
record_format | Article |
series | Geomatics, Natural Hazards & Risk |
spelling | doaj.art-f66ffa9595144ba69c390b5ce224fb482023-12-16T08:49:47ZengTaylor & Francis GroupGeomatics, Natural Hazards & Risk1947-57051947-57132023-12-0114110.1080/19475705.2023.2206512Combination four different ensemble algorithms with the generalized linear model (GLM) for predicting forest fire susceptibilitySaeid Janizadeh0Sayed M. Bateni1Changhyun Jun2Jungho Im3Hao-Thing Pai4Shahab S. Band5Amir Mosavi6Department of Civil and Environmental Engineering and Water Resources Research Center, University of HI at Manoa, Honolulu, Hawaii, USADepartment of Civil and Environmental Engineering and Water Resources Research Center, University of HI at Manoa, Honolulu, Hawaii, USADepartment of Civil and Environmental Engineering, College of Engineering, Chung-Ang University, Seoul, KoreaDepartment of Urban & Environmental Engineering, Ulsan National Institute of Science and Technology, Ulsan, South KoreaInternational Graduate Institute of Artificial Intelligence, National Yunlin University of Science and Technology, TaiwanFuture Technology Research Center, College of Future, National Yunlin University of Science and Technology, Douliou, Yunlin, TaiwanJohn von Neumann Faculty of Informatics, Obuda University, Budapest, HungaryAbstractIn this study, the generalized linear model (GLM) and four ensemble methods (partial least squares (PLS), boosting, bagging, and Bayesian) were applied to predict forest fire hazard in the Chalus Rood watershed in the Mazandaran Province, Iran. Data from 108 historical forest fire events collected through field surveys were applied as the basis of the analysis. About 70% of the data were used for training the models, while the remaining 30% was used for testing. A total of 14 environmental, climatic, and vegetation variables were used as input features to the models to predict forest fire probability. After conducting a multicollinearity test on the independent variables, the GLM and the ensemble models were applied for modeling. The efficiency of the models was evaluated using receiver operating characteristic (ROC) curve parameters. Results from the validation process, based on the area under the ROC curve (AUC), showed that the GLM, PLS-GLM, boosted-GLM, Bagging-GLM, and Bayesian-GLM models had efficiencies of 0.79, 0.75, 0.81, 0.84, and 0.85, respectively. The results indicated that all ensemble methods, except the PLS algorithm, improved the performance of the GLM model in modeling forest fire hazards in the Chalus Rood watershed, with the Bayesian algorithm being the most efficient method among them.https://www.tandfonline.com/doi/10.1080/19475705.2023.2206512Generalized linear modelensemblenatural hazardsChalus Rood watershedforest fire susceptibilityartificial intelligence |
spellingShingle | Saeid Janizadeh Sayed M. Bateni Changhyun Jun Jungho Im Hao-Thing Pai Shahab S. Band Amir Mosavi Combination four different ensemble algorithms with the generalized linear model (GLM) for predicting forest fire susceptibility Geomatics, Natural Hazards & Risk Generalized linear model ensemble natural hazards Chalus Rood watershed forest fire susceptibility artificial intelligence |
title | Combination four different ensemble algorithms with the generalized linear model (GLM) for predicting forest fire susceptibility |
title_full | Combination four different ensemble algorithms with the generalized linear model (GLM) for predicting forest fire susceptibility |
title_fullStr | Combination four different ensemble algorithms with the generalized linear model (GLM) for predicting forest fire susceptibility |
title_full_unstemmed | Combination four different ensemble algorithms with the generalized linear model (GLM) for predicting forest fire susceptibility |
title_short | Combination four different ensemble algorithms with the generalized linear model (GLM) for predicting forest fire susceptibility |
title_sort | combination four different ensemble algorithms with the generalized linear model glm for predicting forest fire susceptibility |
topic | Generalized linear model ensemble natural hazards Chalus Rood watershed forest fire susceptibility artificial intelligence |
url | https://www.tandfonline.com/doi/10.1080/19475705.2023.2206512 |
work_keys_str_mv | AT saeidjanizadeh combinationfourdifferentensemblealgorithmswiththegeneralizedlinearmodelglmforpredictingforestfiresusceptibility AT sayedmbateni combinationfourdifferentensemblealgorithmswiththegeneralizedlinearmodelglmforpredictingforestfiresusceptibility AT changhyunjun combinationfourdifferentensemblealgorithmswiththegeneralizedlinearmodelglmforpredictingforestfiresusceptibility AT junghoim combinationfourdifferentensemblealgorithmswiththegeneralizedlinearmodelglmforpredictingforestfiresusceptibility AT haothingpai combinationfourdifferentensemblealgorithmswiththegeneralizedlinearmodelglmforpredictingforestfiresusceptibility AT shahabsband combinationfourdifferentensemblealgorithmswiththegeneralizedlinearmodelglmforpredictingforestfiresusceptibility AT amirmosavi combinationfourdifferentensemblealgorithmswiththegeneralizedlinearmodelglmforpredictingforestfiresusceptibility |