Forest Fire Prediction: A Spatial Machine Learning and Neural Network Approach

Fire, Journal Year: 2024, Volume and Issue: 7(6), P. 205 - 205

Published: June 18, 2024

The study of forest fire prediction holds significant environmental and scientific importance, particularly in regions like South Carolina (SC) with a high incidence rate fires. Despite the limited existing research on fires this area, application machine learning neural network techniques presents an opportunity to enhance prevention control efforts. Utilizing data from SC Forestry Commission for year 2023, models were developed incorporating various factors such as meteorology, terrain, vegetation, infrastructure—key drivers SC. Feature importance analysis was employed construct final model using different approaches including Decision Tree (DT), Random Forest (RF), Logistic Regression (LR), Artificial Neural Network (ANN), Support Vector Machine (SVM), Convolutional (CNN). Correlation coefficients hazard map correlation test. evaluation predictive performance based accuracy scores revealed that DT achieved highest 90.58%, surpassing other models. However, kernel density 2000 test gave better compared any or approach utilized feature importance. Nonetheless, all accuracies exceeding 80%. This finding directed us rather than those just overlap between locations carbon hotspots provided immediate need mitigate loss due locations. These results serve valuable resource SC, demonstrating efficacy test, providing theoretical foundation support future forestry applications region, showing outperforming capability method prioritize areas climate change impact upon prediction.

Language: Английский

---

A compact multi-hazard assessment model to identify urban areas prone to heat islands, floods and particulate matter

International Journal of Disaster Risk Reduction, Journal Year: 2025, Volume and Issue: unknown, P. 105277 - 105277

Published: Feb. 1, 2025

Language: Английский

---

The influence of DEM spatial resolution on landslide susceptibility mapping in the Baxie River basin, NW China

Natural Hazards, Journal Year: 2020, Volume and Issue: 101(3), P. 853 - 877

Published: March 18, 2020

Language: Английский

---

An assessment of metaheuristic approaches for flood assessment

Journal of Hydrology, Journal Year: 2020, Volume and Issue: 582, P. 124536 - 124536

Published: Jan. 2, 2020

Language: Английский

---

A comparison of machine learning models for the mapping of groundwater spring potential

Environmental Earth Sciences, Journal Year: 2020, Volume and Issue: 79(10)

Published: May 1, 2020

Language: Английский

---