A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
A Forest Fire Prediction Method for Lightning Stroke Based on Remote Sensing Data
Forest fires ignited by lightning accounted for 68.28% of all forest fires in the Greater Khingan Mountains (GKM) region of northeast China. Forecasting the incidence of lightning-triggered forest fires in the region is imperative for mitigating deforestation, preserving biodiversity, and safeguarding distinctive natural habitats and resources. Lightning monitoring data and vegetation moisture content have emerged as pivotal factors among the various influences on lightning-induced fires. This study employed innovative satellite remote sensing technology to swiftly acquire vegetation moisture content data across extensive forested regions. Firstly, the most suitable method to identify the lightning strikes that resulted in fires and two crucial lightning parameters correlated with fire occurrence are confirmed. Secondly, a logistic regression method is proposed for predicting the likelihood of fires triggered by lightning strikes. Finally, the method underwent verification using five years of fire data from the GKM area, resulting in an AUC value of 0.849 and identifying the primary factors contributing to lightning-induced fires in the region.
A Forest Fire Prediction Method for Lightning Stroke Based on Remote Sensing Data
Forest fires ignited by lightning accounted for 68.28% of all forest fires in the Greater Khingan Mountains (GKM) region of northeast China. Forecasting the incidence of lightning-triggered forest fires in the region is imperative for mitigating deforestation, preserving biodiversity, and safeguarding distinctive natural habitats and resources. Lightning monitoring data and vegetation moisture content have emerged as pivotal factors among the various influences on lightning-induced fires. This study employed innovative satellite remote sensing technology to swiftly acquire vegetation moisture content data across extensive forested regions. Firstly, the most suitable method to identify the lightning strikes that resulted in fires and two crucial lightning parameters correlated with fire occurrence are confirmed. Secondly, a logistic regression method is proposed for predicting the likelihood of fires triggered by lightning strikes. Finally, the method underwent verification using five years of fire data from the GKM area, resulting in an AUC value of 0.849 and identifying the primary factors contributing to lightning-induced fires in the region.
A Forest Fire Prediction Method for Lightning Stroke Based on Remote Sensing Data
Zhejia Zhang (author) / Ye Tian (author) / Guangyu Wang (author) / Change Zheng (author) / Fengjun Zhao (author)
2024
Article (Journal)
Electronic Resource
Unknown
Metadata by DOAJ is licensed under CC BY-SA 1.0
Forest Fire Prediction Based on Time Series Networks and Remote Sensing Images
| DOAJ | 2024
Forest Fire Monitoring Using Remote Sensing
| British Library Conference Proceedings | 1992
Monitoring device for preventing forest fire based on remote sensing technology
| European Patent Office | 2022