Spatially-Explicit Prediction of Wildfire Burn Probability Using Remotely-Sensed and Ancillary Data

Shang, Chaoqun; Wulder, Michael A.; Coops, Nicholas C.; White, Joanne C.; Hermosilla, Txomin

doi:10.1080/07038992.2020.1788385

Cited by 22 publications

(11 citation statements)

References 89 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The RF method presented the best performance in both validation steps. Recent studies have also demonstrated the efficiency of this method for fire risk and hazard mapping using different data sources and at different scales (Leuenberger et al, 2018;Gigović et al, 2019;Gholamnia et al, 2020;Shang et al, 2020;Tonini et al, 2020). This method is probably favored by its characteristics of building several decision trees during the training process by having high tolerance to outliers and noisy data (Oliveira et al, 2012;Rodrigues & De La Riva, 2014;Su et al, 2018).…”

Section: Discussionmentioning

confidence: 99%

“…The AUC can be interpreted as the probability that a randomly picked burned area will be classified as "High BS" compared to an unburned area. Values below 0.6 can be considered as unsuitable; values between 0.6 and 0.7 indicate poor performance; between 0.7 and 0.8, moderate; between 0.8 and 0.9, good performance; and between 0.9 and 1.0 means excellent performance (Tien Bui et al, 2018;Shang et al, 2020).…”

Section: Validation and Assessment Of Burning Susceptibility Map Qualitymentioning

confidence: 99%

See 1 more Smart Citation

Burning Susceptibility Modeling to Reduce Wildfire Impacts: A GIS and Multivariate Statistics Approach

Neto¹,

Leite²,

Santos³

et al. 2022

Floram

View full text Add to dashboard Cite

Forest burning susceptibility mapping is a tool to mitigate wildfires, with several methods to develop them. This study aimed to compare the Analytic Hierarchy Process (AHP), Multiple Linear Regression (MLR), and Random Forest (RF) methods for mapping. Several variables were used to generate the maps. For MLR and RF methods, fire frequency between 1990 and 2010 was used as the response variable in the models. To validate the methods (AHP, MLR and RF), fire data between 2011 and 2018 were used in four stages. RF was the best method employed. Correct and incorrect values for this method were 74% and 26% and AUC 0.66. The sensitivity and specificity for the highest risk class were 31% and 96%. The low sensitivity values can be attributed to the randomness attributed to anthropic fire. The high specificity values point to a good separation of the higher risk class compared to the others.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Validation and Assessment Of Burning Susceptibility Map Qualitymentioning

confidence: 99%

Burning Susceptibility Modeling to Reduce Wildfire Impacts: A GIS and Multivariate Statistics Approach

Neto¹,

Leite²,

Santos³

et al. 2022

Floram

View full text Add to dashboard Cite

show abstract

“…This method is therefore of great significance in forest fire prediction and prevention [18] Much research has been conducted on forest fire prediction models. Logistic regression models are the most commonly used models, and they have the advantage of solving the classification problem [19] [20].…”

Section: Introductionmentioning

confidence: 99%

Chinese forest fire occurrence prediction based on machine learning methods

Feng

Zhao

et al. 2021

Preprint

View full text Add to dashboard Cite

Forest fires can cause serious harm. Scientifically predicting forest fires is an important basis for preventing them. Currently, there is little research on the prediction of long time-series forest fires in China. Choosing a suitable forest fire prediction model and predicting the probability of Chinese forest fire occurrence are of great importance to China’s forest fire prevention and control work. Based on fire hotspot, meteorological, terrain, vegetation, infrastructure, and socioeconomic data collected from 2003 to 2016, we used a random forest model as a feature-selection method to identify 13 major drivers of forest fires in China. The forest fire prediction models developed in this study are based on four machine-learning algorithms: an artificial neural network, a radial basis function network, a support-vector machine, and a random forest. The models were evaluated using the five performance indicators of accuracy, precision, recall, f1 value, and area under the curve. We used the optimal model to obtain the probability of forest fire occurrence in various provinces in China and created a spatial distribution map of the areas with high incidences of forest fires. The results showed that the prediction accuracy of the four forest fire prediction models was between 75.8% and 89.2%, and the area under the curve value was between 0.840 and 0.960. The random forest model had the highest accuracy (89.2%) and area under the curve value (0.96); thus, it was used as the optimal model to predict the probability of forest fire occurrence in China. The prediction results indicate that the areas with high incidences of forest fires are mainly concentrated in north-eastern China (Heilongjiang Province and northern Inner Mongolia Autonomous Region) and south-eastern China (including Fujian Province and Jiangxi Province). In areas at high risk of forest fire, management departments can improve forest fire prevention and control by establishing watch towers and using other monitoring equipment. This study helps in understanding the main drivers of forest fires in China, provides a reference for the selection of high-precision forest fire prediction models, and provides a scientific basis for China’s forest fire prevention and control work.

show abstract

“…Many scholars have used a variety of climatic conditioning factors such as temperature (Tehrany et al 2019;Zhang et al 2019;Pham et al 2020), precipitation (Jaafari et al 2017;Zhang et al 2019), wind speed (Jaafari et al 2017;Tehrany et al 2019), and humidity (Tehrany et al 2019). Fuel loads are another conditioning factor that can be grouped into two subcategories, namely Normalized Difference Vegetation Index (NDVI) (Tehrany et al 2019;Zhang et al 2019), and land use/land cover (De Vasconcelos et al 2001;Jaafari et al 2017;Pham et al 2020;Shang et al 2020). The previous research on bushfires also used different human activity factors such as distance to roads (De Vasconcelos et al 2001;Jaafari et al 2017;Valdez et al 2017;Jaafari et al 2018;Pham et al 2020), distance to populated areas (Jaafari et al 2017;You et al 2017;Hong et al 2019) and distance to rivers (Valdez et al 2017;Jaafari et al 2017;Jaafari et al 2018;Jaafari et al 2019c;Zhang et al 2019).…”

Section: Introductionmentioning

confidence: 99%

Gene expression programming and ensemble methods for bushfire susceptibility mapping: a case study of Victoria, Australia

Hosseini

Lim

2021

Geomatics, Natural Hazards and Risk

View full text Add to dashboard Cite

Bushfire susceptibility mapping helps the government authorities predict and provide the required disaster management plans to reduce the adverse impacts from bushfires. In this paper, we investigated Gene Expression Programming (GEP) and ensemble methods to create bushfire susceptibility maps for Victoria, Australia, as a case study. Bushfire susceptibility maps indicate that the eastern part of Victoria where forests are predominant has the highest probability of bushfire. Western part of Victoria which is covered by cropland, shrubland and grassland has the lowest bushfire probability. Two ensemble methods, namely an ensemble of GEP and Frequency Ratio (GEPFR) and an ensemble of Logistic Regression and Frequency Ratio (LRFR), were proposed and compared with stand-alone GEP and stand-alone Frequency Ratio (FR) methods. The proposed methods were evaluated by Area Under Curve (AUC). AUCs of GEPFR, LRFR, GEP and FR are 0.860, 0.852, 0.850, and 0.840, respectively. It can be concluded that GEPFR outperforms the other three methods, and the ensemble methods outperform the standalone methods. GEPFR, LRFR and GEP produced the bushfire probability with an accuracy in the range of 90.79%À92.27%, and therefore they are equally useful for policy makers and managers to have better natural hazard management plans.

show abstract

Spatially-Explicit Prediction of Wildfire Burn Probability Using Remotely-Sensed and Ancillary Data

Abstract: Pr evision spatialement explicite de la probabilit e de feux de forêt a l'aide de s eries temporelles d'images satellitaires et de donn ees auxiliaires

Cited by 22 publications

References 89 publications

Burning Susceptibility Modeling to Reduce Wildfire Impacts: A GIS and Multivariate Statistics Approach

Burning Susceptibility Modeling to Reduce Wildfire Impacts: A GIS and Multivariate Statistics Approach

Chinese forest fire occurrence prediction based on machine learning methods

Gene expression programming and ensemble methods for bushfire susceptibility mapping: a case study of Victoria, Australia

Contact Info

Product

Resources

About