Back to Search Start Over

Genetic and firefly metaheuristic algorithms for an optimized neuro-fuzzy prediction modeling of wildfire probability.

Authors :
Jaafari, Abolfazl
Razavi Termeh, Seyed Vahid
Bui, Dieu Tien
Source :
Journal of Environmental Management. Aug2019, Vol. 243, p358-369. 12p.
Publication Year :
2019

Abstract

In the terrestrial ecosystems, perennial challenges of increased frequency and intensity of wildfires are exacerbated by climate change and unplanned human activities. Development of robust management and suppression plans requires accurate estimates of future burn probabilities. This study describes the development and validation of two hybrid intelligence predictive models that rely on an adaptive neuro-fuzzy inference system (ANFIS) and two metaheuristic optimization algorithms, i.e., genetic algorithm (GA) and firefly algorithm (FA), for the spatially explicit prediction of wildfire probabilities. A suite of ten explanatory variables (altitude, slope, aspect, land use, rainfall, soil order, temperature, wind effect, and distance to roads and human settlements) was investigated and a spatial database constructed using 32 fire events from the Zagros ecoregion (Iran). The frequency ratio model was used to assign weights to each class of variables that depended on the strength of the spatial association between each class and the probability of wildfire occurrence. The weights were then used for training the ANFIS-GA and ANFIS-FA hybrid models. The models were validated using the ROC-AUC method that indicated that the ANFIS-GA model performed better (AUC success rate = 0.92; AUC prediction rate = 0.91) than the ANFIS-FA model (AUC success rate = 0.89; AUC prediction rate = 0.88). The efficiency of these models was compared to a single ANFIS model and statistical analyses of paired comparisons revealed that the two meta-optimized predictive models significantly improved wildfire prediction accuracy compared to the single ANFIS model (AUC success rate = 0.82; AUC prediction rate = 0.78). We concluded that such predictive models may become valuable toolkits to effectively guide fire management plans and on-the-ground decisions on firefighting strategies. • Fine-tuning of ANFIS parameters using genetic and firefly optimization algorithms. • Overcoming the potential bias inherent in the over-fitted single ANFIS model. • Proving AUC>0.88 for wildfire prediction using the hybrid intelligence models. [ABSTRACT FROM AUTHOR]

Details

Language :
English
ISSN :
03014797
Volume :
243
Database :
Academic Search Index
Journal :
Journal of Environmental Management
Publication Type :
Academic Journal
Accession number :
136615536
Full Text :
https://doi.org/10.1016/j.jenvman.2019.04.117