Logo image
Back
Exploring the multidimensional effects of human activity and land cover on fire occurrence for territorial planning
Journal article   Peer reviewed

Exploring the multidimensional effects of human activity and land cover on fire occurrence for territorial planning

Jaime Carrasco, Mauricio Acuna, Alejandro Miranda, Gabriela Alfaro, Cristobal Pais and Andrés Weintraub
Journal of Environmental Management, Vol.297, pp.1-11
2021
DOI: https://doi.org/10.1016/j.jenvman.2021.113428
PMID: 34375228
url
https://doi.org/10.1016/j.jenvman.2021.113428View
Published Version

Abstract

Fire occurrence probability fire risk Machine learning RUSBoost Territorial planning under fire risk wildland urban interface
The strong link between climate change and increased wildfire risk suggests a paradigm change on how humans must co-exist with fire and the environment. Different studies have demonstrated that human-induced fire ignitions can account for more than 90 % of forest fires, so human co-existence with wildfires requires informed decision making via preventive policies in order to minimize risk and adapt to new conditions. In this paper, we address the multidimensional effects of three groups of drivers (human activity, geographic and topographic, and land cover) that can be managed to assist in territorial planning under fire risk. We found critical factors of strong interactions with the potential to increase the likelihood of starting a fire. Our solution approach included the application of a Machine Learning method called Random Undersampling and Boosting (RUSBoost) to assess risk (fire occurrence probability), which was subsequently accompanied by a sensitivity analysis that revealed interactions of various levels of risk. The prediction performance of the proposed model was assessed using several statistical measures such as the Receiver Operating Characteristic curve (ROC) and the Area Under the Curve (AUC). The results confirmed the high accuracy of our model, with an AUC of 0.967 and an overall accuracy over test data of 93.01 % after applying a Bayesian approach for hyper-parameter optimization. The study area to test our solution approach comprised the entire geographical territory of central Chile. •Fire occurrence models can be used to inform preventive measures.•A fire occurrence model was developed that can help with territorial planning.•Risk thresholds are determined by human activity and land cover features.•Land cover types (natural or artificial) play an important role in fire ignition.•Four regions are delineated based on the interaction of the variables and fire risk.

Details

Metrics

25 Record Views
31 Times Cited - Web of Science

InCites Highlights

These are selected metrics from InCites Benchmarking & Analytics tool, related to this output

Collaboration types
Domestic collaboration
International collaboration
Web Of Science research areas
Environmental Sciences

UN Sustainable Development Goals (SDGs)

This output has contributed to the advancement of the following goals:

#13 Climate Action
#15 Life on Land

Source: SDGs from InCites

Logo image