Enhancing forest fire susceptibility mapping in Xichang City, China using DBSCAN-based non-fire point selection integrated with deep neural network
Forest fire susceptibility mapping plays a crucial role in forest management and disaster prevention. However, existing research often neglects the selection of non-fire data during model construction, resulting in limited prediction accuracy. To address this issue, we propose an innovative DBSCAN-D...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2025-12-01
|
| Series: | Geomatics, Natural Hazards & Risk |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/19475705.2024.2443465 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846093596784066560 |
|---|---|
| author | Lingxiao Xie Rui Zhang Jichao Lv Age Shama Yunjie Yang |
| author_facet | Lingxiao Xie Rui Zhang Jichao Lv Age Shama Yunjie Yang |
| author_sort | Lingxiao Xie |
| collection | DOAJ |
| description | Forest fire susceptibility mapping plays a crucial role in forest management and disaster prevention. However, existing research often neglects the selection of non-fire data during model construction, resulting in limited prediction accuracy. To address this issue, we propose an innovative DBSCAN-DNN model that optimizes non-fire data selection to enhance mapping precision. Using VIIRS and GLC_FCS30D datasets, we created a spatial database for Xichang’s dry seasons from 2012 to 2022, incorporating topography, meteorology, vegetation, and human activities. Based on this, we employed the DBSCAN algorithm to cluster the fire points and accurately delineated the affected areas. Subsequently, we selected non-fire samples from outside these regions for training the DNN model. Through comparative experiments, we found that the DBSCAN-DNN model exhibited excellent performance in predicting forest fire susceptibility in Xichang City, with an AUC value of 0.925 and significant improvements in accuracy (0.834), precision (0.800), recall (0.891), F1-score (0.843), and Kappa coefficient (0.669). Additionally, we conducted a SHAP analysis to delve into the contributions and interactions of various factors influencing fire susceptibility. This finding offers valuable insights for selecting non-fire sample data in the forest fire susceptibility mapping model. |
| format | Article |
| id | doaj-art-b750ee802c2840f2a4e0e25e3f02d42d |
| institution | Kabale University |
| issn | 1947-5705 1947-5713 |
| language | English |
| publishDate | 2025-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Geomatics, Natural Hazards & Risk |
| spelling | doaj-art-b750ee802c2840f2a4e0e25e3f02d42d2025-01-02T16:53:26ZengTaylor & Francis GroupGeomatics, Natural Hazards & Risk1947-57051947-57132025-12-0116110.1080/19475705.2024.2443465Enhancing forest fire susceptibility mapping in Xichang City, China using DBSCAN-based non-fire point selection integrated with deep neural networkLingxiao Xie0Rui Zhang1Jichao Lv2Age Shama3Yunjie Yang4Faculty of Geosciences and Engineering, Southwest Jiaotong University, Chengdu, ChinaFaculty of Geosciences and Engineering, Southwest Jiaotong University, Chengdu, ChinaFaculty of Geosciences and Engineering, Southwest Jiaotong University, Chengdu, ChinaFaculty of Geosciences and Engineering, Southwest Jiaotong University, Chengdu, ChinaFaculty of Geosciences and Engineering, Southwest Jiaotong University, Chengdu, ChinaForest fire susceptibility mapping plays a crucial role in forest management and disaster prevention. However, existing research often neglects the selection of non-fire data during model construction, resulting in limited prediction accuracy. To address this issue, we propose an innovative DBSCAN-DNN model that optimizes non-fire data selection to enhance mapping precision. Using VIIRS and GLC_FCS30D datasets, we created a spatial database for Xichang’s dry seasons from 2012 to 2022, incorporating topography, meteorology, vegetation, and human activities. Based on this, we employed the DBSCAN algorithm to cluster the fire points and accurately delineated the affected areas. Subsequently, we selected non-fire samples from outside these regions for training the DNN model. Through comparative experiments, we found that the DBSCAN-DNN model exhibited excellent performance in predicting forest fire susceptibility in Xichang City, with an AUC value of 0.925 and significant improvements in accuracy (0.834), precision (0.800), recall (0.891), F1-score (0.843), and Kappa coefficient (0.669). Additionally, we conducted a SHAP analysis to delve into the contributions and interactions of various factors influencing fire susceptibility. This finding offers valuable insights for selecting non-fire sample data in the forest fire susceptibility mapping model.https://www.tandfonline.com/doi/10.1080/19475705.2024.2443465Forest fire susceptibility mappingdisaster preventiondeep neural networkDBSCAN clusteringnon-fire point selection |
| spellingShingle | Lingxiao Xie Rui Zhang Jichao Lv Age Shama Yunjie Yang Enhancing forest fire susceptibility mapping in Xichang City, China using DBSCAN-based non-fire point selection integrated with deep neural network Geomatics, Natural Hazards & Risk Forest fire susceptibility mapping disaster prevention deep neural network DBSCAN clustering non-fire point selection |
| title | Enhancing forest fire susceptibility mapping in Xichang City, China using DBSCAN-based non-fire point selection integrated with deep neural network |
| title_full | Enhancing forest fire susceptibility mapping in Xichang City, China using DBSCAN-based non-fire point selection integrated with deep neural network |
| title_fullStr | Enhancing forest fire susceptibility mapping in Xichang City, China using DBSCAN-based non-fire point selection integrated with deep neural network |
| title_full_unstemmed | Enhancing forest fire susceptibility mapping in Xichang City, China using DBSCAN-based non-fire point selection integrated with deep neural network |
| title_short | Enhancing forest fire susceptibility mapping in Xichang City, China using DBSCAN-based non-fire point selection integrated with deep neural network |
| title_sort | enhancing forest fire susceptibility mapping in xichang city china using dbscan based non fire point selection integrated with deep neural network |
| topic | Forest fire susceptibility mapping disaster prevention deep neural network DBSCAN clustering non-fire point selection |
| url | https://www.tandfonline.com/doi/10.1080/19475705.2024.2443465 |
| work_keys_str_mv | AT lingxiaoxie enhancingforestfiresusceptibilitymappinginxichangcitychinausingdbscanbasednonfirepointselectionintegratedwithdeepneuralnetwork AT ruizhang enhancingforestfiresusceptibilitymappinginxichangcitychinausingdbscanbasednonfirepointselectionintegratedwithdeepneuralnetwork AT jichaolv enhancingforestfiresusceptibilitymappinginxichangcitychinausingdbscanbasednonfirepointselectionintegratedwithdeepneuralnetwork AT ageshama enhancingforestfiresusceptibilitymappinginxichangcitychinausingdbscanbasednonfirepointselectionintegratedwithdeepneuralnetwork AT yunjieyang enhancingforestfiresusceptibilitymappinginxichangcitychinausingdbscanbasednonfirepointselectionintegratedwithdeepneuralnetwork |