TY - JOUR
T1 - Enhancing predictive ability of optimized group method of data handling (GMDH) method for wildfire susceptibility mapping
AU - Tran, Trang Thi Kieu
AU - Bateni, Sayed M.
AU - Rezaie, Fatemeh
AU - Panahi, Mahdi
AU - Jun, Changhyun
AU - Trauernicht, Clay
AU - Neale, Christopher M.U.
N1 - Publisher Copyright:
© 2023 Elsevier B.V.
PY - 2023/8/15
Y1 - 2023/8/15
N2 - Wildfire is one of the most significant environmental challenges and causing damage to ecosystems, habitats, infrastructure and especially human lives. Thus, spatial assessment of fire risk is vital to reduce the impacts of wildfires. This paper introduces an effective wildfire susceptibility mapping framework by applying a group method of data handling (GMDH) with three metaheuristic methods of biogeography-based optimization (BBO), imperialist competitive algorithm (ICA), and teacher-learning-based optimization (TLBO). A total of 13 wildfire influencing factors, including elevation, slope, aspect, plan curvature, profile curvature, topographic wetness index, valley depth, wind speed, normalized difference vegetation index, rainfall, temperature, distance to roads, and distance to rivers were used in the proposed models for wildfire susceptibility mapping of Oahu Island in Hawaii, USA. The predictive performance of models was evaluated by the root mean square error (RMSE), mean squared error (MSE), and area under the receiver operating characteristic curve (AUC). The findings demonstrated that the three hybrid models outperformed the standalone GMHD in the study area. For example, in the validation phase, the models of GMDH-TLBO, GMDH-ICA, GMDH-BBO, and GMDH produced AUC values of 0.81, 0.80, 0.79, and 0.75, respectively. The MSE values for the GMDH, GMDH-ICA, GMDH-BBO, and GMDH-TLBO models were 0.048, 0.026, 0.030, and 0.020 and the RMSE values were 0.2119, 0.162, 0.17, and 0.142, respectively. Thus, the GMDH-TLBO and GMDH were the most and least effective algorithms because they had the highest and lowest predictive accuracy. Moreover, distance to road is the most effective factor for detecting wildfire-prone areas. It is followed by temperature, slope, and elevation. By localizing the input data, the methodology can be applied to other regions for wildfire susceptibility mapping, facilitating wildfire mitigation and prevention.
AB - Wildfire is one of the most significant environmental challenges and causing damage to ecosystems, habitats, infrastructure and especially human lives. Thus, spatial assessment of fire risk is vital to reduce the impacts of wildfires. This paper introduces an effective wildfire susceptibility mapping framework by applying a group method of data handling (GMDH) with three metaheuristic methods of biogeography-based optimization (BBO), imperialist competitive algorithm (ICA), and teacher-learning-based optimization (TLBO). A total of 13 wildfire influencing factors, including elevation, slope, aspect, plan curvature, profile curvature, topographic wetness index, valley depth, wind speed, normalized difference vegetation index, rainfall, temperature, distance to roads, and distance to rivers were used in the proposed models for wildfire susceptibility mapping of Oahu Island in Hawaii, USA. The predictive performance of models was evaluated by the root mean square error (RMSE), mean squared error (MSE), and area under the receiver operating characteristic curve (AUC). The findings demonstrated that the three hybrid models outperformed the standalone GMHD in the study area. For example, in the validation phase, the models of GMDH-TLBO, GMDH-ICA, GMDH-BBO, and GMDH produced AUC values of 0.81, 0.80, 0.79, and 0.75, respectively. The MSE values for the GMDH, GMDH-ICA, GMDH-BBO, and GMDH-TLBO models were 0.048, 0.026, 0.030, and 0.020 and the RMSE values were 0.2119, 0.162, 0.17, and 0.142, respectively. Thus, the GMDH-TLBO and GMDH were the most and least effective algorithms because they had the highest and lowest predictive accuracy. Moreover, distance to road is the most effective factor for detecting wildfire-prone areas. It is followed by temperature, slope, and elevation. By localizing the input data, the methodology can be applied to other regions for wildfire susceptibility mapping, facilitating wildfire mitigation and prevention.
KW - Geo-environmental factors
KW - Group method of data handling
KW - Hawaii
KW - Optimization
KW - Wildfire susceptibility mapping
UR - http://www.scopus.com/inward/record.url?scp=85164270513&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85164270513&partnerID=8YFLogxK
U2 - 10.1016/j.agrformet.2023.109587
DO - 10.1016/j.agrformet.2023.109587
M3 - Article
AN - SCOPUS:85164270513
SN - 0168-1923
VL - 339
JO - Agricultural and Forest Meteorology
JF - Agricultural and Forest Meteorology
M1 - 109587
ER -