Journal of Spatial Analysis

---

Landslide susceptibility mapping is  essential for  land use  planning and decision-making especially in  the mountainous areas. The main objective of this  study is to produce landslide susceptibility maps (LSM) at Dalahoo basin, Iran  using two statistical models such as an  index of entropy and Logistic Regression and to compare the  obtained results. At the  first stage, landslide locations identified by Natural Resources Department of Kermanshah Province is used to prepare of LSM map. Of the 29 lanslides identified, 21 (≈ 70%) locations were used for the landslide susceptibility maps, while the remaining 8 (≈ 30%) cases were used for the model validation. The landslide conditioning factors such as slope degree, slope aspect, altitude, lithology, distance to faults, distance to rivers, distance to roads, land use, and  lithology  were extracted from the spatial database. Using these factors,  landslide susceptibility and weights of each factor were analyzed by index of entropy and Logistic Regression models. Finally, the ROC (receiver operating characteristic) curves for landslide susceptibility maps were drawn and  the areas under the curve (AUC) were calculated. The verification results showed that the index of entropy model (AUC = 86.08%) performed slightly better than conditional probability (AUC = 80. 13%) model. The produced susceptibility maps can be useful for general land use  planning in the Dalahoo basin, Iran.

---

Determining Effective Factors on Forest Fire Using the Compound of Multivariate Adaptive Regression Spline and Genetic Algorithm, a Case Study: Golestan, Iran   
Pahlavani, P., Assistant professor at School of Surveying and Geospatial Engineering, College of Engineering, University of Tehran
Raei, A., PhD Candidate of GIS at School of Surveying and Geospatial Engineering, College of Engineering, University of Tehran
Bigdeli, B., Assistant professor at School of Civil Engineering, Shahrood University of Technology
 
Keywords: Forest Fire, Multivariate adaptive regression spline, Multiple linear regression, Logistic regression, Genetic Algorithm.
 

1. Introduction

Nowadays, Determining the effective factors on fire is so important, because the plenty areas of forests around the world are destroyed annually by fire and recurrence of that in the long term can irreparably damage to the earth and its inhabitants. It helps us to identify most dangerous locations and times in forest fire. Hence, we can prevent many of driving factors of forest fire by law enforcement, efficient forest management policies and more supervision. In the current study, we identified the effective factors on the fire in Golestan forest through integration of three different methods including multiple linear regression, logistic regression and multivariate adaptive regression spline with Genetic Algorithm.

2. Study Area

Golestan Province is in the North of Iran and 18% of it is covered by forests. Golestan Province is a touristic province and several roads pass through its forests and according to statistical records, most of the occurred fires were in proximity of these roads. Our study area is located in 36°53′-37°25′N and 55°5′- 55°50′E and its area is about 3719.5 km2. We selected this area, because includes the most of fires have been occurred in Golestan Province in recent years.

3. Materials and Methods

A big fire was occurred on 12 December, 2010 in our study area and we used it as the dependent variable. The actual burnt area and some other data, such as Digital Elevation Model (DEM), the roads network, the rivers, the land uses, and soil types in the area were provided from Golestan Province Department of Natural Resources. Also, geographic coordination of the synoptic weather stations near the area and their data, including maximum, minimum, and mean temperature; total rainfall, as well as maximum wind speed and azimuth in December 2010 were obtained from National Meteorological Organization of Iran.
The land use and soil layers were in scale of 1:100000 and the roads and the rivers layers were in 1:5000 and all of them were provided in 2006. The region DEM is generated from topographic maps of Iran National Cartographic Center in scale of 1:25000 with positional resolution of 30m and we produced the slope and the aspect layers from it in ArcGIS software with the same resolution. The roads and the rivers were in vector format, hence, we used the Euclidean Distance analysis to generate rasters that each cell of them shows the distance from the nearest road or river.
At first we had 5 weather stations, which is very few for GWR. In this regard, we generated 1000 random points in the area and interpolated data to these points using Ordinary Kriging method with exponential semivariogram model in 30m resolution in ArcGIS software.
The multiple linear regression (MLR) model is the generalization of simple linear regression that is modeling the linear relation between one dependent variable and some independent variables. The general formula of MLR is seen below:
                                                                                                                                    (1)
The unknown coefficients are obtained using least squares adjustment as follows:
                                                                                                                                                      (2)
The logistic regression (LR) model is a nonlinear model for determination of the relation between a binary dependent variable and some independent variables. If we use the values of 0 and 1 for non-fire and fire points respectively, then the probability that a point be a fire point is obtained by Eq. (3):
                                                                                            (3)
If the number of parameters is insignificant compared to the observations, then we use the unconditional maximum likelihood estimation shown by Eq. (4) to compute the unknown coefficients of this model.
                                                                                                                                (4)
The multivariate adaptive regression spline (MARS) model is a flexible non-parametric model that requires no assumption about the relation between the dependent and independent variables. Hence it has a high ability in determination of complex nonlinear relations among the variables. The general formula of MARS is seen below:
                                                                                                             (5)
 is the m’th basic function that is obtained by Eq. (6):
                                                                                                  (6)
These basic functions are chosen in such a way that leads to minimum RMSE of model.
We use the genetic algorithem (GA) with the fitness function of the normalized RMSE to select the optimum combination of effective factors on forest fire.
 

4. Results and Discussion

In this paper we study the dependence of the forest fire to 14 factors shown in table 1, in the study area. Our results are shown in figures 1 to 3.
 
Table 1. The studied factors in the present research

Factor	Num.	Factor	Num.	Factor	Num.
Aspect	11	Maximum Wind Speed (m/s)	6	Maximum Temperature (℃)	1
Slope	12	Soil Type	7	Minimum Temperature (℃)	2
Elevation (m)	13	Land Use	8	Mean Temperature (℃)	3
Distance from The Residential Zones (m)	14	Distance from The Roads (m)	9	Total Rainfall (mm)	4
		Distance from The Rivers (m)	10	Maximum Wind Azimuth	5

 
 
  
Figure 1. (a) The best and the mean values of fitness, (b) The last best individuals, (c) The average distance between individuals, (d) The fitness of each individual in the last generation using MLR
 
Figure 2. (a) The best and the mean values of fitness, (b) The last best individuals, (c) The average distance between individuals, (d) The fitness of each individual in the last generation using LR
 

Figure 3. (a) The best and the mean values of fitness, (b) The last best individuals, (c) The average distance between individuals, (d) The fitness of each individual in the last generation using MARS

5. Conclusion

This research shows that both of the biophysical and anthropogenic factors have significant effects on forest fire in our study area. Just two factors were identified as impressive factors in all three cases including the minimum temperature and the maximum speed of wind. This study concluded to the NRMSE=0.4291 and R2=0.9862 for the multiple linear regression, NRMSE=0.9416 and R2=0.9912 for the logistic regression and NRMSE=0.1757 and R2=0.9886 for the multivariate adaptive regression spline and totally the multivariate adaptive regression spline method showed a better performance in comparison to the other two methods.
 

---

This study aimed to systematically explain the potential of the landslide occurrence to provide a prediction model of the possibility of this phenomenon in the Yamchi catchment in Ardebil province. In this regard, both approaches of discrete and continuous variables were used by means of overlay and logistic regression, respectively. Independent variables included elevation, slope, aspect, lithology, annual rainfall, roughness, general curvature, topographic wetness index, vegetation index, distance to fault, distance to stream and distance to road. The results, firstly, revealed the areas with high landslide potential by the matching layers of independent variables with the landslide layer in the geographical information system (GIS). These areas were in the middle elevation, high slopes, northern slope, high roughness, erodible formations, high rainfall, medium vegetation, surroundings of faults and rivers. Secondly, the results of the logistics regression model by providing a prediction equation of probability of landslide occurrence showed that the resulting model with pseudo r² and ROC 0.22 and 0.86, respectively, had good power and efficiency to predict landslide through the catchment. In addition, the resulting beta coefficients for independent variables indicated that the importance of the variables was as follows: vegetation index distance to road, rain, lithology, distance to fault, elevation, topographic wetness index, roughness index, aspect, slope, and distance to river. In the end, the need to pay serious attention to the supporting and protection of vegetation cover of the mid -range and upstream of the catchment was determined because of unstable geomorphic conditions of these areas.
 

---

Considering that there are different forms of mass movements in the ChamGardlan watershed, especially along communication routes, agricultural and residential areas, it is necessary to create refugee maps Therefore, it is impossible to examine the factors influencing its situation in order to prevent and control this phenomenon. Therefore, during the field visits, geographical, physiography, land use, vegetation cover, soil, climatology, geography and geomorphology maps were produced in the GIS environment. The method of this research has been accomplished base of distinction of the geomorphological units while using aerial photos and crossing  basis maps. Then, the effective factors on the occuration of mass movements were studied using logistic regression equations. So that, the factors such as slope, geological formation type, pedologic, climatic, etc. were taked into consideration as independant variables, and mass movements occurance frequency as function of mentioned factors.The result indicated that the effective factors related to frequency of land sliding happening in the area in arrangement, are slope, geological formation type and mass  movements  type (both kind and amount of salts in soil) and also landuse.