Next Article in Journal
Integrative Transcriptomic and Metabolomic Approaches to Deep Pink Flower Color in Prunus campanulata and Insights into Anthocyanin Biosynthesis
Next Article in Special Issue
A Comparative Review of Wildfire Danger Rating Systems: Focus on Fuel Moisture Modeling Frameworks
Previous Article in Journal
The Impact of Sanitary Felling During Large-Scale Disturbances on Regulating Ecosystem Services in Norway Spruce-Dominated Pre-Alpine Beech Forests of Slovenia
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Forests
Volume 16
Issue 11
10.3390/f16111632
forests-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

A Spatiotemporal Wildfire Risk Prediction Framework Integrating Density-Based Clustering and GTWR-RFR

by
Shaofeng Xie
,
Huashun Xiao
*,
Gui Zhang
and
Haizhou Xu
School of Advanced Interdisciplinary Studies, Central South University of Forestry and Technology, Changsha 410004, China
*
Author to whom correspondence should be addressed.
Forests 2025, 16(11), 1632; https://doi.org/10.3390/f16111632
Submission received: 15 September 2025 / Revised: 19 October 2025 / Accepted: 22 October 2025 / Published: 26 October 2025
(This article belongs to the Special Issue Ecological Monitoring and Forest Fire Prevention)
Browse Figures
Versions Notes

Abstract

Accurate wildfire prediction and identification of key environmental drivers are critical for effective wildfire management. We propose a spatiotemporally adaptive framework integrating ST-DBSCAN clustering with GTWR-RFR. In this hybrid model, Random Forest captures local nonlinear relationships, while GTWR assigns adaptive spatiotemporal weights to refine predictions. Using historical wildfire records from Hunan Province, China, we first derived wildfire occurrence probabilities via ST-DBSCAN, avoiding the need for artificial non-fire samples. We then benchmarked GTWR-RFR against seven models, finding that our approach achieved the highest accuracy (R2 = 0.969; RMSE = 0.1743). The framework effectively captures spatiotemporal heterogeneity and quantifies dynamic impacts of environmental drivers. Key contributing drivers include DEM, GDP, population density, and distance to roads and water bodies. Risk maps reveal that central and southern Hunan are at high risk during winter and early spring. Our approach enhances both predictive performance and interpretability, offering a replicable methodology for data-driven wildfire risk assessment.
Keywords: wildfire risk prediction; spatiotemporal non-stationarity; GTWR-RFR; ST-DBSCAN; environmental drivers wildfire risk prediction; spatiotemporal non-stationarity; GTWR-RFR; ST-DBSCAN; environmental drivers

Share and Cite

MDPI and ACS Style

Xie, S.; Xiao, H.; Zhang, G.; Xu, H. A Spatiotemporal Wildfire Risk Prediction Framework Integrating Density-Based Clustering and GTWR-RFR. Forests 2025, 16, 1632. https://doi.org/10.3390/f16111632

AMA Style

Xie S, Xiao H, Zhang G, Xu H. A Spatiotemporal Wildfire Risk Prediction Framework Integrating Density-Based Clustering and GTWR-RFR. Forests. 2025; 16(11):1632. https://doi.org/10.3390/f16111632

Chicago/Turabian Style

Xie, Shaofeng, Huashun Xiao, Gui Zhang, and Haizhou Xu. 2025. "A Spatiotemporal Wildfire Risk Prediction Framework Integrating Density-Based Clustering and GTWR-RFR" Forests 16, no. 11: 1632. https://doi.org/10.3390/f16111632

APA Style

Xie, S., Xiao, H., Zhang, G., & Xu, H. (2025). A Spatiotemporal Wildfire Risk Prediction Framework Integrating Density-Based Clustering and GTWR-RFR. Forests, 16(11), 1632. https://doi.org/10.3390/f16111632

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop