BIPE: A Bi-Layer Predictive Ensemble Framework for Forest Fire Susceptibility Mapping in Germany
Forest fires diminish forests’ ecological services, including carbon sequestration, water retention, air cooling, and recreation, while polluting the environment and endangering habitats. Despite considerable economic advancements, firefighting strategies remain less than optimal. This paper introdu...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/1/7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841548973395935232 |
|---|---|
| author | Ling Hu Volker Hochschild Harald Neidhardt Michael Schultz Pegah Khosravani Hadi Shokati |
| author_facet | Ling Hu Volker Hochschild Harald Neidhardt Michael Schultz Pegah Khosravani Hadi Shokati |
| author_sort | Ling Hu |
| collection | DOAJ |
| description | Forest fires diminish forests’ ecological services, including carbon sequestration, water retention, air cooling, and recreation, while polluting the environment and endangering habitats. Despite considerable economic advancements, firefighting strategies remain less than optimal. This paper introduces the Bi-layer Predictive Ensemble (BIPE), an innovative machine learning model designed to enhance the accuracy and generalization of forest fire susceptibility mapping. BIPE integrates model-centric and data-driven strategies, employing automated methods such as 10-fold cross-validation and meta-learning to improve stability and generalization. During its 10-fold cross-validation, BIPE demonstrated excellent performance, with the Area Under the Curve (AUC) values ranging from 0.990 to 0.996 and accuracy levels consistently high, around 97%, underscoring its robust class separation ability and strong generalization across different datasets. Our results confirm that BIPE outperforms traditional high-performance models like Support Vector Machine (SVM), Multilayer Perceptron (MLP), Extreme Gradient Boosting (XGBoost), Deep Neural Network (DNN), and Convolutional Neural Network (CNN), showcasing its practical effectiveness and reliability on the data of nonlinear, high-dimensional, and complex interactions. Additionally, our forest fire susceptibility maps offer valuable complementary information for German forest fire management authorities, enhancing their ability to assess and manage fire risks more effectively. |
| format | Article |
| id | doaj-art-1e63e5baf18249cea11332829a2f3e4b |
| institution | Kabale University |
| issn | 2072-4292 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-1e63e5baf18249cea11332829a2f3e4b2025-01-10T13:19:55ZengMDPI AGRemote Sensing2072-42922024-12-01171710.3390/rs17010007BIPE: A Bi-Layer Predictive Ensemble Framework for Forest Fire Susceptibility Mapping in GermanyLing Hu0Volker Hochschild1Harald Neidhardt2Michael Schultz3Pegah Khosravani4Hadi Shokati5Geoinformatics Group, Department of Geosciences, University of Tübingen, Rümelinstraße 19-23, 72072 Tübingen, GermanyGeoinformatics Group, Department of Geosciences, University of Tübingen, Rümelinstraße 19-23, 72072 Tübingen, GermanyGeoecology Group, Department of Geosciences, University of Tübingen, Rümelinstraße 19-23, 72072 Tübingen, GermanyGeoinformatics Group, Department of Geosciences, University of Tübingen, Rümelinstraße 19-23, 72072 Tübingen, GermanySoil Science and Geomorphology, Department of Geosciences, University of Tübingen, Rümelinstraße 19-23, 72072 Tübingen, GermanySoil Science and Geomorphology, Department of Geosciences, University of Tübingen, Rümelinstraße 19-23, 72072 Tübingen, GermanyForest fires diminish forests’ ecological services, including carbon sequestration, water retention, air cooling, and recreation, while polluting the environment and endangering habitats. Despite considerable economic advancements, firefighting strategies remain less than optimal. This paper introduces the Bi-layer Predictive Ensemble (BIPE), an innovative machine learning model designed to enhance the accuracy and generalization of forest fire susceptibility mapping. BIPE integrates model-centric and data-driven strategies, employing automated methods such as 10-fold cross-validation and meta-learning to improve stability and generalization. During its 10-fold cross-validation, BIPE demonstrated excellent performance, with the Area Under the Curve (AUC) values ranging from 0.990 to 0.996 and accuracy levels consistently high, around 97%, underscoring its robust class separation ability and strong generalization across different datasets. Our results confirm that BIPE outperforms traditional high-performance models like Support Vector Machine (SVM), Multilayer Perceptron (MLP), Extreme Gradient Boosting (XGBoost), Deep Neural Network (DNN), and Convolutional Neural Network (CNN), showcasing its practical effectiveness and reliability on the data of nonlinear, high-dimensional, and complex interactions. Additionally, our forest fire susceptibility maps offer valuable complementary information for German forest fire management authorities, enhancing their ability to assess and manage fire risks more effectively.https://www.mdpi.com/2072-4292/17/1/7machine learningforest firesusceptibility mappingensemble model |
| spellingShingle | Ling Hu Volker Hochschild Harald Neidhardt Michael Schultz Pegah Khosravani Hadi Shokati BIPE: A Bi-Layer Predictive Ensemble Framework for Forest Fire Susceptibility Mapping in Germany Remote Sensing machine learning forest fire susceptibility mapping ensemble model |
| title | BIPE: A Bi-Layer Predictive Ensemble Framework for Forest Fire Susceptibility Mapping in Germany |
| title_full | BIPE: A Bi-Layer Predictive Ensemble Framework for Forest Fire Susceptibility Mapping in Germany |
| title_fullStr | BIPE: A Bi-Layer Predictive Ensemble Framework for Forest Fire Susceptibility Mapping in Germany |
| title_full_unstemmed | BIPE: A Bi-Layer Predictive Ensemble Framework for Forest Fire Susceptibility Mapping in Germany |
| title_short | BIPE: A Bi-Layer Predictive Ensemble Framework for Forest Fire Susceptibility Mapping in Germany |
| title_sort | bipe a bi layer predictive ensemble framework for forest fire susceptibility mapping in germany |
| topic | machine learning forest fire susceptibility mapping ensemble model |
| url | https://www.mdpi.com/2072-4292/17/1/7 |
| work_keys_str_mv | AT linghu bipeabilayerpredictiveensembleframeworkforforestfiresusceptibilitymappingingermany AT volkerhochschild bipeabilayerpredictiveensembleframeworkforforestfiresusceptibilitymappingingermany AT haraldneidhardt bipeabilayerpredictiveensembleframeworkforforestfiresusceptibilitymappingingermany AT michaelschultz bipeabilayerpredictiveensembleframeworkforforestfiresusceptibilitymappingingermany AT pegahkhosravani bipeabilayerpredictiveensembleframeworkforforestfiresusceptibilitymappingingermany AT hadishokati bipeabilayerpredictiveensembleframeworkforforestfiresusceptibilitymappingingermany |