Spatial pattern prediction of forest wildfire susceptibility in Central Yunnan Province, China based on multivariate data

doi:10.21203/rs.3.rs-1958932/v1

Download PDF

Research Article

Spatial pattern prediction of forest wildfire susceptibility in Central Yunnan Province, China based on multivariate data

https://doi.org/10.21203/rs.3.rs-1958932/v1

This work is licensed under a CC BY 4.0 License

You are reading this latest preprint version

Wildfires are an important disturbance factor in forest ecosystems. Assessing the probability of forest wildfires can assist in forest wildfire prevention, control, and supervision. The logistic regression model is widely used to forecast the probability, spatial patterns, and drivers of forest wildfires. This study used logistic regression to establish a spatial prediction model for forest wildfire susceptibility, which was applied to evaluate the risk of forest wildfires in Central Yunnan Province (CYP), China. A forest wildfire risk classification was implemented for CYP using forest burn scar data for 2001 to 2020 and the logistic spatial prediction model for forest wildfire susceptibility. Climate, vegetation, topographical, human activities, and location were selected as forest wildfire prediction variables. The results showed that: (1) The distributions of temperature, vegetation coverage, distance to water bodies, distance to roads, and precipitation were positively correlated with the occurrence of forest wildfires. Elevation, relative humidity, the global vegetation moisture index, wind speed, slope, latitude, and distance to residential areas were negatively correlated with the occurrence of forest wildfires. (2) The results of the logistic spatial prediction model for forest wildfire susceptibility showed a good fit to observed data, with an overall simulation probability of 81.6%. The optimal threshold for spatial prediction for forest wildfire susceptibility in CYP was determined to be 0.414. A significance level of a selected model variable of < 0.05 resulted in an area under the receiver operating characteristic curve (AUC) of 0.882–0.890. (3) Forest wildfire prevention efforts should focus on Southwest Yuxi City and southern Qujing City since they accounted for a high proportion of the areas at high risk of forest wildfires. Other localities should adjust forest wildfire prevention measures according to local conditions and strengthen existing wildfire prevention and emergency resource planning and allocation. (4) Some factors contributing to forest wildfires where different among the different areas. Forest wildfire risk factors had different degrees of impact under different spatial and temporal scales. The spatial relationships between wildfire disasters and influencing factors should be established in areas with heterogeneous environmental conditions for the selection of relevant factors.

Central Yunnan Province

forest wildfire

driving factors

logistic regression

spatial prediction model for forest wildfire susceptibility

forest wildfire risk grade

As an important part of the terrestrial ecosystem, forests play a vital role in the dynamic balance of natural landscapes. However, forest ecosystems are extremely vulnerable to interference from various factors, among which fire is one of the most important (Daubenmire. 1968; Vogl. 1974). Forest fires strongly affect the vegetation and environment of an ecosystem (Flannigan et al. 2000), therefore, the scientific study and evaluation of fire risk play an important role in fire monitoring, prevention, and control, as well as in developing emergency resource planning and allocation measures. The assessment of fire risk in-volves the generation of a qualitative or quantitative index of risk through the analysis of environmental factors that may affect the occurrence and spread of fire. These estimates of risk are then categorized into different grades to describe changes to fire risk in an area (Chuvieco et al. 2010). The assessment of the grade of forest fire risk is an important basis for forest wildfire prevention.

Fire risk assessment and early warning methods began in the late 1920s (Li. 2016), which have been continuously improved with the development of science and technology. The rise of remote sensing technology provides broad data sources for forestry fire risk assessment (Roy et al. 2008; Alonso-Canas and Chuvieco. 2015; Giglio et al. 2018; Roteta. 2019). Also, with the increase of available geographical element data, the factors for constructing a fire risk index are becoming more and more com-prehensive, and many factors such as terrain, vegetation, and cultural facilities are also taken into account (Shi. 2009; Sun and Zhang. 2011; Chas-Amil et al. 2015; Tian et al. 2016;). In some studies, various machine learning methods, such as random forests, deep learning, and neural networks, have been applied to forest fire risk assessment and model building (Cao et al. 2017; Zhang et al. 2019; Sevinca et al. 2020). Although among these methods, machine learning has been shown to provide better model parameterization, it tends to give predicted results without interpretation (Gunning and Aha. 2019), and thus, it fails to provide a clear relationship between forest fires and drivers. Jaiswal et al. (2002) classified forest fire hazard areas in Deja, India based on satellite data but considering only a few driving factors. Zhang et al. (2018, 2019) used mathematical statistics and cluster analysis to evaluate the grades of forest fire risk and established fire risk zoning for townships and for Chifeng City in the Bahrain right flag of Inner Mongolia. Similarly, their study considered a limited number of variables and did not consider their mutual influences. Johnston et al. (2020) established a forest fire risk assessment method suitable for Canada based on the possibility of fire occurrence, exposure, and vulnerability and their potential impacts (Woo et al. 2017; You et al. 2017; Molaudzi et al. 2018). Ye et al.(2017) Used weights-of-evidence to explore the spatial distribution of forest wildfire points in Yunnan Province from 2007 to 2013. These previous studies focused more on the direct effects of anthropogenic impacts on fire risk with less focus on the indirect impacts of the ecology.

In summary, studies conducted both in China and globally have made good progress in the assessment and early warning of fire risk. The assessment of forest fire risk at any spatial scale can be based on short- or long-term indicators or integrated systems. The assessment of forest fire risk has made a great contribution to the prevention of forest fires (Ye et al. 2017). These studies only consider climate factors, the research period is short (about 10 years), and applied a simple spatial weighted overlay method to classify forest fire risks resulting in low prediction accuracies. With the development of the times, it is less difficult to collect anthropogenic data. Therefore, we can collect some anthropogenic factors (such as roads, residential areas, water systems, etc.). Then we expand the study period, and construct the forest wildfire model to improve its pre-diction accuracy.

Due to sufficient sunshine, high temperature and dry air, Yunnan Province is prone to forest wildfires during the dry season, which is the province with the largest number of forest fires in China (Su et al.2015; Yang et al. 2015; He et al. 2017). Central Yunnan Province (Kunming City, Yuxi City, Chuxiong Yi Autonomous Prefecture and Qujing City) contains rich forest re-sources. Through forest wildfire risk assessment, it is of great significance for forest management in this area. Therefore, the study takes central Yunnan as the study area, collects the forest wildfire data during the wildfire prevention period from 2001 to 2020 (December to June of the next year), constructs the spatial prediction model for forest wildfire susceptibility by using climate, vegetation, terrain, human and location factors, evaluates the driving factors of forest wildfire. Factors that were highly corre-lated and contributed to model bias were eliminated. Logistic regression was then used to construct a spatial prediction model for forest fire susceptibility. Finally, the model was applied to assess the long-term probability of forest wildfires in the CYP based on comprehensive factors and forest wildfire risk zoning.

2.1 Study Area

The CYP incorporates the Kunming, Yuxi, Qujing, and the Chuxiong Yi Autono-mous Prefecture in central Yunnan (Fig. 1), consisting of 42 counties (urban areas) and a total area accounting for 24% of the entire province (Yu et al. 2018). The CYP is located in the low-latitude plateau region, showing the characteristics of monsoon climate. Its annual average temperature is 18.61℃, the climate is warm, the temperature difference between the four seasons is low, and the mean precipitation is 817.83mm (Li.2016). In ad-dition, the dry season and rainy season in central Yunnan are distinct, and the annual precipitation distribution is uneven. Generally, the rainy season is defined from May to October, and the dry season is defined from November to April (Zheng et al. 2017).

The CYP is rich in forest resources, with a forest coverage rate of nearly 47% (Long et al. 2017). The dominant tree species are coniferous forests composed of flammable tree species, including Pinus, Picea, and Eucalyptus (Chen et al. 2012). The special terrain, climate, diversity of vegetation types, and the complexity of fire causes make forest wildfires frequent in central Yunnan, and wildfires mainly occur in winter and spring from December to May, causing immeasurable losses to society. Therefore, we collected data on climate, humanities, topography, and vegetation, and analyzed the probability of forest wild-fires in the study area, hoping to provide a reference.

2.2 Data resources and data preprocessing

Forest wildfires can occur extremely rapidly and different factors affect the occurrence and spatial distribution of forest wildfires (Tian et al. 2014; Bisquert et al; 2014). The present study selected variables falling in the categories of topography, vegetation, climatology, human activities, and location as wildfire risk factors. These factors were combined with forest burn scar data for the analysis of the correlation between impact factors and the occurrence of forest wildfires. Table 1 summarizes the data used in the current study.

Table 1

A summary of datasets used in the current study to analyze the relationships between fire risk factors and the occurrence of forest wildfires in Central Yunnan Province, China
Data Type	Data	Code	Variable unit	Data Source
Burn scar	Burn scar	No	500m	MCD64A1Combustion Data Set LAADS DAAC (nasa.gov)
Topography	Elevation	DEM	30m	30 m elevation in CYP www.gscloud.cn
	Slope	SLOPE
	Aspect	ASPECT
Climatology	Daily Average Precipitation	PCP	0.1mm	China Meteorological Element Station Observation Daily Dataset (Resource and Environment Science and Data Center https://www.resdc.cn/)
	Daily Average Air Temperature	AT	0.1℃
	Daily Average Wind Speed	WS	0.1m/s
	Daily Average Relative Humidity	RH	1%
Vegetation	Fractional Vegetation Cover	FVC	500m	MOD09A1 product https://code.earthengine.google.com/ and https://www.resdc.cn/
	Global vegetation moisture index	GVMI	500m
	Vegetation Type	VT	1000m
Humanity	Distance to River	RIVER	1m	1: 1 million Chinese map digitization Resource and environmental science and data center of Chinese Academy of Sciences (https://www.resdc.cn/)
	Distance to Facility	FAC	1m
	Distance to Road	ROAD	1m
Position	Longitude	LON	/	Automatic generation using ArcGIS software
Position	Latitude	LAT	/	Automatic generation using ArcGIS software

2.2.1 Burn scar and random point data

The present study obtained the MCD64A1 data from the official NASA website (nasa.gov) (Giglio et al. 2018). The MRT (MODIS Reprojection Tool) was used to preprocess the fire area data of Yunnan Central from 2001 to 2020, including batch projection conversion and mosaic, cropping. The maximum value was then synthesized and a binary dependent variable (0 is non-fire, 1 is fire) grid map was generated. Finally, the land use data for 2015 were superimposed on the fire point data layer from 2001 to 2020, and fire data of non- vegetated areas were eliminated to obtain valid burn scar data (Fig. 2a).

The classification of forest fires requires the construction of a certain proportion of non-burn scars. The number and spatial distribution of non-fire areas are important for the construction and evaluation of forest fire index models. The present study generated non-burn scar data by creating random points under the data management module of ArcGIS software according to the ratio of burn scars and non-burn scars 1:1.5 (Fig. 2b).

The present study statistically analyzed the burned area in central Yunnan (Fig. 3). The total fire area monitored from 2001 to 2020 was 3191.25km2, accounting for 3.25% of the total area in central Yunnan. The monitoring results showed relatively little change in burned areas among the different years, except for spike of 506.25 km2 in 2010. An area of 777.70 km2 has been burned more than once over the past 20 years, and one area of 0.26 km2 has experienced 14 periods of repeated burning (Fig. 4). The spatial distribution of the number of burnings in central Yunnan over the study period showed that the areas with repeated forest wildfires are concentrated in the southwest area of Yuxi City and the southern area of Qujing City (Fig. 2a).

2.2.2 Topography

Topography is an important factor affecting the occurrence and spread of forest fires by influencing the type and distribution of vegetation (Rothermel. 1991; Maingi and Henry. 2007). Past studies have shown that precipitation, temperature, evaporation, and humidity change with changing elevation, thereby changing the probability of forest fires (Guo et al. 2016). The degree of exposure of the land surface to solar radiation is affected by the aspect, resulting in differences in forest fire among different aspects (Hu. 2005; Zhang et al. 2014), With consideration of the effect of topographic factors on the risk of forest fires, data were obtained from the geospatial data cloud platform and digital elevation model (DEM) data were analyzed using ArcGIS to extract elevation (DEM) (Fig. 5a), slope (SLOPE) (Fig. 5b), and aspect (ASPECT) (Fig. 5c).

2.2.3 Vegetation

Forest vegetation can affect the risk of forest fire according to forest type, water content, and other properties (Minnich and Bahre. 1995; Pew et al. 2001), The vegetation factors considered in the present study mainly included fractional vegetation cover (FVC) (Fig. 5d), the global vegetation moisture index (Fig. 5e) and vegetation type (Fig. 5f). Data for the FVC were extracted using the Normalized Difference Vegetation Index (NDVI) pixel dichotomy model (Liang. 2011):

$$FVC=\frac{(\text{N}\text{D}\text{V}\text{I}-{NDVI}_{min})}{({NDVI}_{max}-{NDVI}_{min})}$$

In Eq. (1), NDVImax represents the NDVI value of a pixel in a region completely covered by vegetation and NDVImin represents the NDVI value of a pixel in an area covered by bare land or without vegetation. NDVImin and NDVImax are generally assigned the 5% and 95% cumulative probability of NDVI.

The global vegetation moisture index generally refers to the ratio of water content of the vegetation canopy to its dry matter. Three expressions of the index are typically adopted, namely the leaf water content, relative water content, and equivalent water depth (Xu and Zhang. 2020). The present study used the Global Vegetation Moisture Index (GVMI) (Ceccato et al. 2002) instead:

$$GVMI=\frac{\left(NIR+0.1\right)-（SWIR+0.2）}{\left(NIR+0.1\right)+(SWIR+0.2)}$$

NIR and SWIR represent the reflectance values of bands 2 and 6 in the MOD09A1 product, respectively.

2.2.4 Climate data

Climatic factors are generally considered to be drivers of forest fires (Turco et al. 2013) and past studies have considered the comprehensive relationships between the risk of forest fire and climatology parameters, such as temperature, precipitation, evaporation, wind speed, and relative humidity, as well as various combinations of these parameters (Sevinca et al. 2020). The present study obtained data for daily average temperature (°C), 24h cumulative precipitation (mm), daily average wind speed (m s − 1), and daily average relative humidity (%) from the Resource and Environment Science and Data Center. The data were processed using ArcGIS and the spatial distributions of annual average precipitation (PCP) (Fig. 5g), annual average air temperature (AT) (Fig. 5h), annual average wind speed (WS) (Fig. 5i), and annual average relative humidity (RH) (Fig. 5j) were established.

2.2.5 Human activities

Human made infrastructure and some socioeconomic factors have a certain impact on the occurrence of forest fires (Cardille et al. 2001). Forest fires occur more often in urban forest junctions in which human activities are more frequent (Gordon et al. 1996). Therefore, the present study selected the distance from residential areas, roads, and water bodies as the variables of the forest fire prediction model. The Euclidean distance in ArcGIS was applied to generate ROAD (Fig. 5k), FAC (Fig. 5l), and RIVER (Fig. 5m) with a resolution of 500 m.

2.2.6 Location of fires

An examination of the data for forest fires in Central Yunnan from 2001 to 2020 showed that there was an uneven distribution of fires in Central Yunnan. The fires were mainly concentrated in Yuxi City and southern Qujing City. Clear differences in the area of forest fires were evident at different longitudes and latitudes, particularly in areas at a low latitude. Therefore, the present study selected the longitude and latitude of each fire as the initial reference factor for establishing the model.

2.3 Methods

The present study used the forest wildfire dataset during the fire prevention period for the CYP from 2001 to 2020. Fifteen factors were selected from the climatological, vegetation, topography, and socio-economic categories as forest wildfire predictor variables. The data of 13 factors were normalized, with the aspect and vegetation type regarded as categorical variables. The resolutions of all data were resampled to 500 m and all factors were unified into the Lambert projection and statistical tests were used to eliminate multicollinearity between the selected predictors. Figure 6 shows a flow diagram of the research process followed.

2.3.1 Logistic Model

The factors affecting the occurrence of forest fires are multi-dimensional. The occurrence of forest wildfires has complex non-parametric relationships with many environmental factors and there are typically differences in the factors influencing fires in different regions. Therefore, a fire forecasting model should be flexible. The non-linear fitting ability of the logistic regression (LR) model can be used to simulate and analyze the categorical dependent variables with only two classification results. The model predicted value is between [0, 1] representing the forecast probability (Bar Massada et al. 2013). The use of the LR model for forest fire risk assessment has been widely recognized and is used both in China and abroad (Saefuddin et al. 2012).

The logistic regression (LR) model was used in the present study to analyze the occurrence of forest fires in the CYP. The occurrence of forest fire was regarded as the dependent variable in the model. Forest fire occurs and does not occur for y = 1 and y = 0, respectively. The probability of forest fire occurrence (y = 1) was set as P, whereas the probability of forest fire not occurring (y = 0) was set as 1 − P. The ratio of forest fire occurrence to non-occurrence was equal to P/ (1 − P) (Chang et al. 2013). Therefore, taking ln (P/ (1 − P)) as the dependent variable of the model, after logistic transformation, the probability evaluation formula of forest fire occurrence can be obtained as:

$$P(y=1)=\frac{{e}^{(b0+b1x1+b2x2+\dots +bnxn)}}{1+{e}^{(b0+b1x1+b2x2+\dots +bnxn)}}$$

In Eq. (3), P is the probability of forest fire, b0, b1, b2... bn are the correlation coefficients of the dependent variables in the binomial logistic regression, n is the number of independent variables, x1, x2, and xn are the occurrence values of forest fires for the various influencing factors, such as slope, elevation, vegetation type, daily average precipitation, distance from residential areas, and roads, etc. In logistic regression, P/(1-P) is the ratio of predicted probability P and is converted into the ratio form. The logarithm (Logit transformation) of the ratio of P, ln (P/ (1 − P)), is the predicted probability. This transformation removes the lower limit of the model: the range of P before and after transformation is [0, 1] and (−∞, +∞), respectively. Since this transformation also reenforces the influence of the independent variable on the dependent variable, it is suitable for the fitting of probabilistic prediction models (Wang. 2020).

2.3.2 Extraction of training and test samples

The present study adopted the occurrence of forest fire as the dependent variable and fire risk factors as the independent variables. The sampling of certain non-burn and burn areas was required in the modeling. There may be spatial autocorrelation between the selected independent variables, which will affect the fitting accuracy of the model. The current study randomly chose fire locations for the extraction of various forest fire factors. This ensured the robustness of the model and the validity of statistical inference (Dimitris et al. 2018). The data were randomly subsampled into model training and verification datasets containing 80% and 20% of the data, respectively. At the same time, the training dataset was further randomly subsampled into model training subsamples and model test subsamples containing 70% and 30% of the original training dataset, respectively. This was performed to reduce the impact of random sampling on the selection of model variables. This process was repeated five times to generate five data subsamples. The logistic model was used for model fitting to generate five intermediate models. The characteristic variables that appeared three or more times in the experimental results were selected for the fitting analysis of the entire sample dataset, following which the optimal model was generated.

2.3.3 Multicollinearity test of fire risk factors

Interactions between independent variables can lead to instability of the linear regression model, resulting in increased deviation of the estimated results and reduced accuracy of model prediction. Therefore, a multicollinearity test should be conducted on the selected model factors when constructing the model. Many methods currently exist to overcome the challenge of multicollinearity. The present study used the variance inflation factor (VIF) diagnostic method (Ma. 2019; Wang. 2017) to assess the multicollinearity of independent variables in the model. The value of VIF is positively related to the collinearity of the model. In general, a VIF = 5 is standard, whereas a VIF ≥ 10 indicates severe collinearity. Based on this general guide, independent variables with significant collinearity can be gradually eliminated. A 5 ≤ VIF < 10 indicates moderate collinearity and that significant collinearity among independent variables should be resolved, whereas 2 < VIF < 5 indicates mild collinearity which can be ignored (Krebs et al. 2012).

2.3.4 Receiver operating characteristic curve test

The receiver operating characteristic curve (ROC) is a comprehensive indicator that reflects the sensitivity and specificity of continuous variables. The area under the curve (AUC), can be used to analyze the prediction accuracy of the model, with the value of the AUC positively related to the diagnostic accuracy of the model. The AUC ranges from 0.5 to 1, with an AUC > 0.8 indicating good model predictive ability (Deng et al. 2012). The ROC curve inspection method has become widely used in prediction of forest fire risk (Wang et al. 2020; Li et al. 2021). The present study used the area under the ROC curve (AUC) to analyze and evaluate the accuracy of the forest fire prediction model.

3.1 Subsection

3.1.1 Subsubsection

The present study used ArcGIS to merge the attributes of each layer of forest wildfire driving variables in the CYP with those of burning scars and random points. The forest wildfire driving factors were extracted according to the coordinates of burning scars and random points and SPSS was used to conduct statistical analyses of the integrated data. The variance inflation factor (VIF) in SPSS was used to assess multicollinearity among independent and dependent variables and independent variables with significant collinearity were eliminated.

According to the research results, all variables passed the multiple common linearity test. Therefore, the factors driving forest wildfires that passed the multicollinearity test were used as explanatory variables to establish a forest wildfire model for the CYP.

3.1.2 Significance test

SPSS software was used to test the significance of the independent variables in the five samples. The logistic regression model was applied to the 15 variables that passed the multicollinearity test to fit five training samples. Table 2 shows the results of the fitting analysis.

Table 2

Results of fitting independent variables in the logistic model. Please refer to Table 1 for definitions of variable codes.
Variable	Sample1	Sample2	Sample3	Sample4	Sample5	Times
WS	+	+	+	+	+	5
AT	+	+	+	+	+	5
PCP	+	+	+	+	+	5
RH	-	+	+	+	+	4
DEM	+	+	+	+	+	5
SLOPE	+	+	+	+	+	5
ASPECT	-	-	-	-	-	0
FVC	+	+	-	+	+	4
GVMI	+	-	+	-	+	3
VT	-	-	+	-	+	2
RIVER	+	+	+	+	+	5
FAC	+	+	-	+	-	3
ROAD	+	+	+	—	+	5
LAT	+	+	+	+	+	5
LON	-	+	-	-	-	1
* Note: “+” and “− “indicate that the factor appeared and did not appear in the model, respectively.

Table 2. shows that among the five intermediate models, daily average wind speed, daily average precipitation, daily average temperature, daily average relative humidity, elevation, slope, fractional vegetation cover, global vegetation moisture index, distance to residential areas, distance to water systems, distance to roads, and latitude all appeared more than three times. The above variables could then be used to perform binomial logistic regression on the full sample dataset to eliminate the slope, aspect, vegetation types, and longitude that do not meet the model requirements.

3.2 ROC curve test

MATLAB software was used to construct the ROC curve, and the ROC curve was used to test the goodness of fit of the model and to calculate the optimal critical value for forest wildfires in the CYP. Figure 7 represents the ROC curve of the five sub-samples and full-sample dataset.

Table 3

Evaluation index of the logistic model
Sample		Sample 1	Sample 2	Sample 3	Sample 4	Sample 5	Full Sample
AUC		0.890	0.882	0.885	0.890	0.882	0.884
Significance Level		< 0.001	< 0.001	< 0.001	< 0.001	< 0.001	< 0.001
Critical Value		0.442	0.377	0.403	0.387	0.437	0.414
Prediction Accuracy (%)	Training Sample	81.6	82.0	81.7	81.4	81.8	81.6
Prediction Accuracy (%)	Test Sample	82.3	81.1	81.9	82.7	81.6	81.6
As shown in Table 3, the area under the ROC curve (AUC) of the five sub-samples and the full sample ranged from 0.882 to 0.890, with the significance level P less than 0.001. The model showed a high prediction accuracy and statistical significance. Therefore, the model could be used to predict the occurrence of forest wildfires in the CYP and the critical value of wildfire occurrence was 0.414.

3.3 Establishment of the probability model of forest wildfire occurrence

The extracted training sample data were imported into the SPSS software for binomial classification logistic regression to obtain the parameters of the forest wildfire risk probability model (Table 4).

Table 4

Fitting parameters of logistic model.
Explanatory Variable	Regression Coefficient	Criterion Error	Wald	Degree of Freedom	Significant	Correlation
WS	-0.350	0.208	2.840	1	0.092	-
RH	-4.271	0.289	217.830	1	0.000	-
DEM	-3.106	0.216	206.119	1	0.000	-
SLOPE	-1.138	0.187	37.015	1	0.000	-
FVC	0.968	0.284	11.641	1	0.001	+
GVMI	-1.919	0.326	34.673	1	0.000	-
RIVER	1.437	0.093	239.597	1	0.000	+
FAC	-2.270	0.634	12.818	1	0.000	-
ROAD	3.858	0.821	22.091	1	0.000	+
AT	4.468	0.178	629.828	1	0.000	+
PCP	5.834	0.177	1086.104	1	0.000	+
LAI	-6.546	0.301	473.997	1	0.000	-
Constant	2.069	0.364	32.346	1	0.000	/
* Note: “+” and “− “indicate positive and negative correlation, respectively.

According to the selection of model variables and the regression coefficients of the full sample model, the probability model of forest wildfire occurrence in CYP was established as:

$$P\left(y=1\right)=\frac{{e}^{2.069-0.350WS-4.271RH-3.106DEM-1.138SLOPE+0.968FVC-1.919GVMI+1.437RIVER-2.270FAC+3.858ROAD+4.468AT+5.834PCP-6.546LAT}}{1+{e}^{2.069-0.350WS-4.271RH-3.106DEM-1.138SLOPE+0.968FVC-1.919GVMI+1.437RIVER-2.270FAC+3.858ROAD+4.468AT+5.834PCP-6.546LAT}}$$

3.4 Assessment of model accuracy

The probability of forest wildfires in the CYP was categorized into five levels with equal intervals. This categorization was used to assess the percentages of the burn scars of the model falling into different forest wildfire occurrence probability intervals. Figure 8 shows a histogram of the burn scars falling into the forest wildfire occurrence probability intervals in the CYP.

As shown in Fig. 8, most of the burn scars used for inspection were concentrated between 0.4–1, with only a few burn scars occurring in the intervals of < 0.2 and 0.2–0.4, indicating that the model has a high degree of credibility.

3.5 Forest wildfire risk grade and spatial analysis in the CYP

The Kriging interpolation method in the ArcGIS software was used to interpolate the probability of forest wildfire occurrence in CYP according to the prediction results of the logistic model. As shown in Fig. 9, the probability of wildfire was divided into five intervals: (1) extremely low; (2) low; (3) medium; (4) high; (5) extremely high.

The generated data for wildfire risk grades in the CYP were used to estimate the wildfire risk for different areas in the CYP (Table 5) and the area percentage of all levels of fire risk in the four cities in the CYP (Table 6). As shown in Table 5, the areas of fire risk grades 1 to 5 in the CYP were 48,344.50 km2, 20,400.00 km2, 13,102.75 km2, 7,531.25 km2, and 8,645.5 km2, respectively. Among these areas, the total areas of medium, high, and extremely high fire risk accounted for29.87% of the entire area of the CYP.

Table 5

Wildfire danger area statistics
Probability of forest wildfire	Forest Wildfire Danger Grade	Area(km²)	Area Percentage(%)
< 0.2	Extremely Low	48344.50	49.32%
0.2–0.4	Low	20400.00	20.81%
0.4–0.6	Medium	13102.75	13.37%
0.6–0.8	High	7531.25	7.68%
> 0.8	Extremely High	8645.5	8.82%

Table 6

Percentage of wildfire risk areas in city of CYP
Grade City	Extremely Low	Low	Medium	High	Extremely High	Total
Chuxiong Yi Autonomous Prefecture	31.56%	41.67%	21.65%	4.72%	0.40%	100%
Kunming	78.19%	16.04%	5.04%	0.73%	0%	100%
Yuxi	1.36%	7.96%	21.42%	26.60%	42.67%	100%
Qujing	71.11%	10.58%	7.08%	5.69%	5.54%	100%

The results showed a clear risk of forest wildfire in central CYP. Areas of extremely high and high wildfire risk were mainly distributed in southwestern Yuxi City and southern Qujing City. The percentages of total area of high and the extremely high fire risk in Yuxi City were 26.60% and 42.67%, respectively, whereas that of Qujing City reached 11.23%. Areas with high fire risk were evident in the southern and central parts of the Chuxiong Yi Autonomous Prefecture. Areas of medium fire risk were mainly distributed in the Chuxiong Yi Autonomous Prefecture, northern Yuxi City, southern Kunming City and central Qujing City. Areas of low and extremely low fire risk were distributed mainly in Kunming, Chuxiong Yi Autonomous Prefecture and the central and northern part of Qujing, with those in Kunming, Chuxiong Yi Autonomous Prefecture, and Qujing reaching 94.23%, 73.23%, and 81.69%, respectively. Areas of low and extremely low fire risk were widely distributed in these three cities, but at a lower proportion in Yuxi at only 9.32%.

The present study is the first to use the spatial prediction model for forest wildfire susceptibility to conduct a systematic forest wildfire risk assessment in the CYP. The CYP is a key forest wildfire risk area in Yunnan Province due to its unique climate, topography, forest types, and human production activities. The diversity and complexity of forest wildfires in the CYP increases the complexity of forest wildfire prevention in central Yunnan. Therefore, the present study considered more comprehensive wildfire risk factors, including climate, topography, vegetation, anthropogenic, and geographic factors.

4.1 Model reliability

The present study selected a series of static and dynamic data falling within the categories of vegetation, topography, climatology, human activities, and geography as the independent variables for the logistic forest wildfire risk probability model in the CYP. The assessments of multicollinearity and significance indicted that aspect, vegetation types, and longitude that did not meet the requirements of the model could be eliminated. The selected variables and the regression coefficients of the full sample were then used to construct a spatial prediction model for forest wildfire susceptibility for the CYP. When the significance levels of the selected model variables were less than 0.05, the AUC values of the group were high at between 0.882–0.890, the AUC value of the full sample reached 0.884, and the prediction accuracy of the sample group and the full data sample model were around 81.6%. Past studies that applied the logistic model similarly obtained relatively high AUC values (Deng et al.2012; Wang et al. 2017; Wang. 2020). The obtained AUC > 0.8 indicated the good predictive ability of the model (Li et al. 2021). In addition, the histogram shown in Fig. 7 indicated that most of the wildfire points used for inspection were concentrated between 0.4 and 1, with only a few fire points at < 0.2 and between 0.2–0.4. This result indicated that the high fire risk areas identified in the present study correspond to areas of frequent forest fires according to observed records. Therefore, the logistic model constructed in the present study is highly reliable and can be used as an analysis tool for exploring fire risk.

4.2 The variables driving forest wildfires

The study found that climate is an important factor leading to forest wildfires, which is consistent with the findings of GUO et al. (2017). Among them, the temperature is positively correlated with the occurrence of forest wildfires, which is consistent with the research results of Tian et al. (2014). Relative humidity showed a positive correlation, but this was inconsistent with the results of some studies (Bravo et al. 2010; Zumbrunen et al. 2011; Liu et al. 2018), which may be due to the difference in the results due to the different temperature zones in the study area (Wilgen et al. 2000; Miller et al. 2009). Similarly, precipitation is also positively correlated with the occurrence of forest wildfires, which is consistent with the findings of Spessa et al. (2005) and Randerson et al. (2005). Wind speed had no significant effect on the occurrence of forest wildfires. Among topographic factors, altitude and slope are negatively correlated with forest wildfire occurrence, which is consistent with the research results of Syphard et al. (2008), which means that the probability of forest wildfire occurrence is lower in areas with high altitude.

The distance from residential areas was identified to have a negative correlation with the occurrence of forest wildfires, with the probability of forest wildfires higher in areas with frequent human activities. This result can be attributed to the active role of human populations in starting forest wildfires. This result was consistent with those by Guo et al. (2016). In addition, the results of the present study found that the distance to roads was positively correlated with the occurrence of forest wildfires, indicating a higher probability of wildfires in areas further away from roads. This can be attributed to road networks mainly being concentrated in industrially developed areas in which firefighting resources are concentrated. In contrast, fires spread easily in remote forest areas in which fire protection resources are scattered (Guo et al. 2017). Vegetation moisture content and vegetation humidity showed no significant relationship and a negative correlation with the occurrence of forest fires, respectively. In general, the influence of vegetation factors on the occurrence of forest fire was not very significant, inconsistent with the conclusion of Wen (2019). Among all the independent variables, latitude appeared to have the most significant negative correlation with the occurrence of forest wildfires. This result indicated that a single fire risk factor has different effects under different spatial and temporal scales, further emphasizing the complexity of processes leading to the induction and spread of forest wildfire. Areas with high heterogeneity of environmental conditions require scientific analysis of the spatial relationship between fire occurrence and influencing factors based on actual conditions and the optimal selection of related factors.

4.3 The spatial differences of forest wildfire risk grade

Areas of extremely high and high fire risk are mainly distributed in southwest Yuxi City and southern Qujing City. Among them, the high and extremely high fire risk areas of Yuxi Cit y account for 26.60% and 42.67% of the total area, respectively, consistent with the conclusions of Wang (2020) and Feng et al. (2014). However, the results of the study for Yuxi City differ from those of Zhang et al. (1994), with the city indicating a relatively low risk. The conflicting results may be due to the complex wildfire environment formed by the CYP.

On the one hand, previous studies considered fewer fire risk factors and used the clustering method, which is unsuitable for the manipulation of large sample datasets. On the other hand, the time that has lapsed between the current study and the two previous studies is relatively long, and the wildfire risk factors and internal connections in the study area may have changed during this period. Therefore, the impact of these factors on the occurrence of forest wildfires may have also changed, which may have eventually led to an increase in the fire risk level of Yuxi City.

One factor that may explain the increased risk of forest wildfire in Yuxi City and Qujing City may be the increased strength of the European low-pressure trough and the South Asian high from February to April, thereby preventing the southward movement of cold air. The climate of the CYP is regulated by the South Asian high-pressure system, resulting in sunny conditions and hot temperatures with little rainfall. These conditions result in a high incidence of forest wildfires during the fire prevention period (Yang et al. 2013).

Therefore, communication and consultation with climate departments should be strengthened in areas of high fire risks. In addition, all emergency preparations should be established beforehand to proactively prevent and mitigate problems.

The present study used satellite wildfire data during the wildfire prevention period in the CYP from 2001 to 2020 as well as a series of static and dynamic data incorporating vegetation, topography, climatology, and human activities in the corresponding period to construct a logistic forest wildfire risk model. The model was applied to classify forest wildfire risk levels in the CYP. The conclusions of the present study are listed below.

(1) When the significance levels of the selected model variables were below 0.05, the AUC value of the model reached 0.884, indicating the high reliability of the model. Therefore, the model can be used to explore wildfire risk.

(2) Latitude had the greatest impact on the occurrence of forest wildfires. The distributions of temperature, vegetation coverage, distance to water bodies, distance to roads, and precipitation were positively correlated with the occurrence of forest wildfires. Elevation, relative humidity, the global vegetation moisture index, wind speed, slope, latitude, and distance to residential areas were negatively correlated with the occurrence of forest wildfires.

(3) The area of high forest wildfire risk in the CYP was relatively low. The areas of extremely low, low, medium, high, and extremely high fire risk accounted for 49.32%, 20.81%, 13.37%, 7.68%, and8.82%, of the total area, respectively.

(4) The CYP shows a clear risk of forest wildfires. The areas of extremely high and high fire risk are mainly distributed in southwest Yuxi City and southern Qujing City. The areas of medium fire risk are mainly located in the Chuxiong Yi Autonomous Prefecture, northern Yuxi City, southern Kunming City, and central Qujing City. Therefore, forest wildfire prevention efforts should be concentrated in southern central Qujing city, Yuxi City, and central Chuxiong Yi Autonomous Prefecture. Forest wildfire prevention efforts should correspond to local conditions and should follow rational emergency resources planning and allocation.

(5) The factors driving the occurrence of forest wildfires were found to be both the same and different among the different study areas. The unity in driving factors could be related to climate factors being the most important drivers of the occurrence of a forest wildfires. The differences could be attributed to regional differences among driving factors. Wildfire risk factors showed different degrees of influence on the occurrence of forest wildfire at different spatial and temporal scales. This conclusion further verifies the complexity of the underlying mechanism of forest wildfire induction and spread. Therefore, relevant driving factors should be selected according to regional characteristics within forest wildfire risk assessment.

Acknowledgements: This study was funded by the Multi-government International Science and Technology Innovation Cooperation Key Project of the National Key Research and Development Program of China (grant number 2018YFE0184300). The study was co-funded by RFBR (grant number 19-55-80010\19), MOST (grant number 2018YFE0184300) and NRF (grant number 120456) according to the research project number 19-55-80010\19, National Natural Science Foundation of China (grant number 41561048) and the Yunnan Provincial University Science and Technology Innovation Team (IRTSTYN).

Conflict of Interest: The authors declare that they have no competing interests

Alonso-Canas I, Chuvieco E (2015) Global burned area mapping from ENVISAT-MERIS and MODIS active fire data. Remote Sensing of Environment. 163: 140–152.
Bar Massada A, Syphard AD, Stewart SI, Radeloff VC (2013) Wildfire ignition-distribution modelling: a comparative study in the Huron-Manistee National Forest, Michigan, USA. International Journal of Wildland Fire. 22(2): 174-183.
Bisquert M, Sánchez J, Caselles V (2014) Modeling fire danger in Galicia and Asturias (Spain) from MODIS images. Remote Sensing. 6(1): 540-554.
Bravo S, Kunst C, Grau R, Aráoz E (2010) Fire-rainfall relationships in Argentine Chaco savannas. Journal of Arid Environments. 74(10): 1319-1323.
Cao Y, Wang M, Liu K (2017) Wildfire Susceptibility Assessment in Southern China: A Comparison of Multiple Methods. International Journal of Disaster Risk Science. 8(2):164-181.
Cardille JA, Ventura SJ, Turner MG (2001) Environmental and social factors influencing wildfires in the upper midwest, united states. Ecological Applications. 11(1): 111-127.
Ceccato P, Gobron N, Flasse S, Pinty B, Tarantola S (2002) Designing a spectral index to estimate vegetation water content from remote sensing data: Part 1: Theoretical approach. Remote Sensing of Environment. 82(2-3): 188-197.
Chang Y, Zhu Z, Bu R, Chen H, Feng Y, Li Y, Hu Y, Wang Z (2013) Predicting fire occurrence patterns with logistic regression in Heilongjiang Province, China. Landscape Ecology. 28(10): 1989-2004.
Chas-Amil ML, Prestemon JP, McClean CJ. Touza J (2015) Human-ignited wildfire patterns and responses to policy shifts. Applied Geography.56: 164-176.
Chen F, Lin XD, Niu SK, Wang S (2012) Influence of climate change on forest fire in Yunnan Province，southwestern China. Journal of Beijing Forestry University. 34(6):7-15.
Chuvieco E, Aguado I, Yebra M, Nieto H, Salas J, Martin MP, Vilar, Martinez J, Martin S, Ibarra P (2010) Development of a framework for fire risk assessment using remote sensing and geographic information system technologies. Ecological Modelling. 221(1): 46-58.
Daubenmire RF (1968) Ecology of Fire in Grasslands. Advances in Ecological Research. 5: 209-266.
Deng O, Li YQ, Feng ZK, Zhang DY (2012) Model and zoning of forest fire risk in Heilongjiang province based on spatial Logistic. Transactions of the Chinese Society of Agricultural Engineering. 28(8): 200-205. (in Chinese)
Feng ZX, Lu YS, Sun YB, Xu Q, Jiang P (2014) Assessment of power grid risk caused by wildfire disaster in Yunnan Province. Journal of Natural Disasters. 23(5):219-224. (in Chinese)
Flannigan MD, Stocks BJ, Wotton BM (2000) Climate change and forest fires. Science of the Total Environment. 262(3):221-229.
Giglio L, Boschetti L, Roy DP, Humber ML, Justice CO (2018) The Collection 6 MODIS burned area mapping algorithm and product. Remote Sensing of Environment. 217: 72–85.
Gordon AD (1996) A survey of constrained classification. Computational Statistics & Data Analysis. 21(1): 17-29.
Gunning D, Aha D (2019) DARPA’s explainable artificial intelligence (XAI) program. AI Magazine. 40(2): 44-58.
Guo F, Selvalakshmi S, Lin F, Wang G, Wang W, Su Z, Liu A (2016) Geospatial information on geographical and human factors improved anthropogenic fire occurrence modeling in the Chinese boreal forest. Canadian Journal of Forest Research. 46(4): 582-594.
Guo F, Su Z, Tigabu M, Yang X, Lin F, Liang H, Wang G (2017) Spatial modelling of fire drivers in urban-forest ecosystems in China. Forests. 8(6): 180-198.
Guo F, Su Z, Wang G, Sun L, Lin, F, Liu A (2016) Wildfire ignition in the forests of southeast China: identifying drivers and spatial distribution to predict wildfire likelihood. Applied Geography. 66:12-21.
He YC, Xu H, Cheng JX (2017) Analysis of the temporal and spatial distribution of forest fire in Yunnan province. Journal of Central South University of Forestry & Technology. 37 (5): 36-41. (in Chinese)
Hu HQ (2005) Fire ecology and management. Beijing:Chinese Forestry Press, 2005:2-34. (in Chinese)
Jaiswal RK, Mukherjee S, Raju KD, Saxena R (2002) Forest fire risk zone mapping from satellite imagery and GIS. International Journal of Applied Earth Observation and Geoinformation. 4(1): 1–10.
Johnston LM, Wang XL, Erni S, Taylor SW, McFayden CB, Oliver JA, Stockdale C, Christianson A, Boulanger Y, Gauthier S, Arsenault D, Wotton M, Parisien M-A, Flannigan MD (2020) Wildland fire risk research in Canada. Environmental Reviews. 28(7): 1-23.
Krebs P, Koutsias N, Conedera M (2012) Modelling the eco-cultural niche of giant chestnut trees: new insights into land use history in southern Switzerland through distribution analysis of a living heritage. Journal of Historical Geography. 38(4): 372-386.
Kuhn M, Johnson K (2018) Applied Predictive Modeling. New York, Springer. Biometrics, 2018, 74: 378-384.
Li C (2016) Research of water requirement of Tobacco in the Middle of Yunnan Province under Climate change. Kunming University of Science and Technology. (in Chinese)
Li HP, Long ZH, Yang ZH, Xu ZQ, Li YZ (2021) Analysis of forest fire risk in Sichuan Liangshan based on Logistic model. Journal of Safety and Environment. 21(02):498-505. (in Chinese)
Li XL (2016) Synergy of Multi-factors for Forest Fire Prediction and Detection Based on MODIS Data.University of Science and Technology of China. (in Chinese)
Liang Y, Yong H, Nurgu L (2011) Correlation analysis of forest fires and meteorological factors in the northern Xinjiang forest region. Xinjiang Agricultural Sciences.,48(03):539-543. (in Chinese)
Liu KZ, Zhao FJ, Wang MY, Zhang MY (2018) ZINB-based research on a model for forecasting occurrence of forest fires in Daxing’anling Area in summer. Forestry Machinery & Woodworking Equipment. 46(6):8-12.
Long TT, Shan BJ, Tian FX, Wang QH (2017) Research on Social Vulnerability of Forest Fire Environmental Disaster in Central Yunnan Urban Agglomeration. Forest Fire Prevention, ,2017(04):11-14. (in Chinese)
Ma WY (2019) Study on Driving Factors and Forecast Models of Forest Fire in Large-scale Areas. Beijing Forestry University. (in Chinese)
Maingi JK, Henry MC (2007) Factors influencing wildfire occurrence and distribution in eastern Kentucky, USA. International Journal of Wildland Fire. 16(1): 393-393.
Miller JD, Safford HD, Crimmins M, Thode AE (2009) Quantitative evidence for increasing forest fire severity in the Sierra Nevada and Southern Cascade Mountains, California and Nevada, USA. Ecosystems. 12(1):16-32.
Minnich RA, Bahre CJ (1995) Wildland fire and chaparral succession along the California Baja-California boundary. International Journal of Wildland Fire. 5(1): 13-24.
Molaudzi OD, Adelabu SA (2018) Review of the use of remote sensing for monitoring wildfire risk conditions to support fire risk assessment in protected areas. South African Journal of Geomatics. 7(3): 222-242.
Pew K, Larsen CP (2001) GIS analysis of spatial and temporal patterns of human-caused wildfires in the temperate rain forest of Vancouver Island, Canada. Forest Ecology and Management.140(1): 1-18.
Randerson JT, van der Werf GR, Collatz GJ, Giglio L, Still CJ, Kasibhatla P, Miller JB, White JWC, DeFries RS, Kasischke ES (2005) Fire emissions from C3 and C4 vegetation and their influence on interannual variability of atmospheric CO2 and δ13CO2. Global Biogeochemical Cycles. 19(2):1-13.
Roteta E, Bastarrika A, Padilla M, Storm T, Chuvieco E (2019) Development of a Sentinel-2 burned area algorithm: Generation of a small fire database for sub-Saharan Africa. Remote Sensing of Environment. 222: 1–17.
Rothermel RC (1991) Predicting Behavior and Size of Crown Fires in the Northern Rocky Mountains. Ogden, UT: U.S. Department of Agriculture, Forest Service, Intermountain Forest and Range Experiment Station. INT-RP-438.
Roy DP, Boschetti L, Justice CO, Ju J (2008) The collection 5 MODIS burned areaproduct — global evaluation by comparison with the MODIS active fire product.Remote Sens. Environ. Remote Sensing of Environment. 112(9): 3690–3707.
Saefuddin A, Setiabudi NA, Fitrianto A (2012) On comparison between logistic regression and geographically weighted logistic regression:with application to indonesian poverty data. World Applied Sciences Journal. 19(2): 205-210.
Sevinca V, Kucuk O, Goltas M (2020) A Bayesian network model for prediction and analysis of possible forest fire causes. Forest Ecology and Management. 457:117723. doi:10.1016/j.foreco.2019.117723
Shi PJ (2009) Theory and Practice on disaster system research in a fifth time. Journal of Natural Disasters. 18(05):1-9. (in Chinese)
Spessa A, McBeth B, Prentice C (2005) Relationships among fire frequency, rainfall and vegetation patterns in the wet-dry tropics of Northern Australia: an analysis based on NOAA-AVHRR Data. Global Ecology and Biogeography. 14(5):439-454.
Su LJ, He YJ, Chen SZ (2015) Temporal and spatial characteristics and risk analysis of forest fires in China from 1950 to 2010. Scientia Silvae Sinicae. 051(1):88-96. (in Chinese)
Sun YR, Zhang G (2011) Characteristics of the Spatial-temporal Distribution for Artificial Fire Sources on Forest Fires in Hunan. Chinese Agricultural Science Bulletin. 27(28):103-108. (in Chinese)
Syphard AD, Radeloff VC, Keuler NS, Taylor RS, Hawbaker TJ, Stewart SI, Clayton MK (2008) Predicting spatial patterns of fire on a southern California landscape. International Journal of Wildland Fire. 17(5), 602-613.
Tian X, Zhao FJ, Shu LF, Wang MY (2014) Changes in forest fire danger for south-western China in the 21st century. International Journal of Wildland Fire. 23(2): 185-195.
Tian XR, Dai X, Wang MY, Zhao FJ, Shu LF (2016) Forest fire risk assessment for China under different climate scenarios. Chinese Journal of Applied Ecology. 27(03): 769-776. (in Chinese)
Turco M, Llasat MC, Hardenberg J, Provenzale A (2013) Impact of climate variability on summer fires in a Mediterranean environment (northeastern Iberian Peninsula). Climatic Change. 116(3-4): 665-678.
Vogl RJ (1974) Effects of Fire on Grasslands. Fire and Ecosystems. 139-194.
Wang S, Zhang G, Tan SQ, Wang P, Wu X (2020) Assessment of forest fire risk in Hunan province based on spatial logistic model. Journal of Central South University of Forestry & Technology. 40(9):88-95. (in Chinese)
Wang WG (2017) Study on the assessment of fire risk and Zoning in Gansu Province. Northwest Normal University. 17(06):4-6. (in Chinese)
Wang Z (2020) Spatial modeling and grade evaluation of forest and grass fire danger in Yunnan Province. Journal of Nanjing Forestry University (Natural Science Edition). 44(02):141-149. (in Chinese)
Wang Z (2020) Spatial modeling and grade evaluation of forest and grass fire danger in Yunnan Province. Journal of Nanjing Forestry University (Natural Science Edition). 44(02):141-149. (in Chinese)
Wen CB (2019) Methodology and application for wildfire risk assessment based on remote sensing techniques. University of Electronic Science and Technology of China. 2019 (01):1-84. (in Chinese)
Wilgen NV (2000) A fire history of the savanna ecosystems in the Kruger National Park, South Africa, between 1941 and 1996. South African Journal of Science. 96(4):167-178.
Woo H, Chung W, Graham JM, Lee B (2017) Forest fire risk assessment using point process modelling of fire occurrence and Monte Carlo fire simulation. International Journal of Wildland Fire. 26(9): 789- 805.
Xu H, Zhang PL (2020) Fire risk assessment of water protection areas based on multi-source data. Geomatics World. 27(01):48-53. (in Chinese)
Yang G, Shu LF, Sun SQ, Di XY, Liu C (2015) Temporal-spatial distribution regularities of forest fire casualties in China. Journal of Catastrophology. 30 (2): 21-25. (in Chinese)
Yang HG, Li G, Xie, FY (2013) Analysis on the meteorological risk influencing factors of Yuxi Forest fire. Yunnan Science and Technology Management. 2013(02): 28-31. (in Chinese)
Ye J, Wu M, Deng Z, Xu S, Zhou R, Clarke KC (2017) Modeling the spatial patterns of human wildfire ignition in Yunnan province, China. Applied Geography. 89: 150-162.
You W, Lin L, Wu L, Ji ZR, Yu JA, Zhu JQ, Fan YJ, He DJ (2017) Geographical information system-based forest fire risk assessment integrating national forest inventory data and analysis of its spatiotemporal variability. Ecological Indicators. 77: 176-184.
Yu YH, Wang JL, Li XP (2018) Monitoring the occurrence of drought in central Yunnan province based on MODIS data. Journal of Irrigation and Drainage. 37(11):91-98. (in Chinese)
Zhang G, Wang M, Liu K (2019) Forest Fire Susceptibility Modeling Using a Convolutional Neural Network for Yunnan Province of China. International Journal of Disaster Risk Science.10(3):386-403.
Zhang H, Qi P, Guo G (2014) Improvement of fire danger modelling with geographically weighted logistic model. International Journal of Wildland Fire. 23(8): 1130-1146.
Zhang H, Wang X, Zhang X, Yu HZ, Zhou M, Wang YX (2019) Forest fire danger rating and fire hazard assessment in Chifeng city of Inner Mongolia. Journal of Southwest Forestry University. 39(02):143-150. (in Chinese)
Zhang H, Yu YK, Jing YH, Ma YJ, Zhou M (2018) Forest fire danger rating and fire division of Bahrain right Banner in Inner Mongolia. Forestry Resources Management. (01): 103-108. (in Chinese)
Zhang YT, Duan X, Li JF (1994) The partition in the forest conflagration and climate in the middle of Yunnan province. Journal of Southwest Forestry College. 14(3): 172~176. (in Chinese)
Zheng YJ, Miao YC, Liu SH, He P, Wang S (2017) Analysis of Meteorological Variables in Dianzhong Region in Recent 51 Years. Acta Scientiarum Naturalium Universitatis Pekinensis. 53(01):8-18. (in Chinese)
Zumbrunnen T, Pezzatti GB, Menéndez P, Bugmann H, Bürgi M, Conedera M (2011) Weather and human impacts on forest fires:100 years of fire history in two climatic regions of Switzerland. Forest Ecology and Management. 261(12):2188-2199.

Download PDF

Editorial decision: Minor revisions
02 Oct, 2022
Reviewers agreed at journal
16 Sep, 2022
Reviewers invited by journal
18 Aug, 2022
Editor assigned by journal
16 Aug, 2022
First submitted to journal
13 Aug, 2022

You are reading this latest preprint version

Spatial pattern prediction of forest wildfire susceptibility in Central Yunnan Province, China based on multivariate data

Status:

Version 1

Abstract

Figures

1 Introduction

2 Materials And Methods

2.1 Study Area

2.2 Data resources and data preprocessing

2.2.1 Burn scar and random point data

2.2.2 Topography

2.2.3 Vegetation

2.2.4 Climate data

2.2.5 Human activities

2.2.6 Location of fires

2.3 Methods

2.3.1 Logistic Model

2.3.2 Extraction of training and test samples

2.3.3 Multicollinearity test of fire risk factors

2.3.4 Receiver operating characteristic curve test

3 Results

3.1 Subsection

3.1.1 Subsubsection

3.1.2 Significance test

3.2 ROC curve test

3.3 Establishment of the probability model of forest wildfire occurrence

3.4 Assessment of model accuracy

3.5 Forest wildfire risk grade and spatial analysis in the CYP

4 Discussion

4.1 Model reliability

4.2 The variables driving forest wildfires

4.3 The spatial differences of forest wildfire risk grade

5 Conclusions

Declarations

References

Status:

Version 1