PROVIDING THE FIRE RISK MAP IN FOREST AREA USING A GEOGRAPHICALLY WEIGHTED REGRESSION MODEL WITH GAUSSIN KERNEL AND MODIS IMAGES, A CASE STUDY: GOLESTAN PROVINCE

被引:1
作者
Pour, Ali Shah-Heydari [1 ]
Pahlavani, Parham [1 ]
Bigdeli, Behnaz [2 ]
机构
[1] Univ Tehran, Coll Engn, Sch Surveying & Geospatial Engn, Tehran, Iran
[2] Shahrood Univ Technol, Sch Civil Engn, Shahrood, Iran
来源
ISPRS INTERNATIONAL JOINT CONFERENCES OF THE 2ND GEOSPATIAL INFORMATION RESEARCH (GI RESEARCH 2017); THE 4TH SENSORS AND MODELS IN PHOTOGRAMMETRY AND REMOTE SENSING (SMPR 2017); THE 6TH EARTH OBSERVATION OF ENVIRONMENTAL CHANGES (EOEC 2017) | 2017年 / 42-4卷 / W4期
关键词
Forest Fire; Geographically Weighted Regression; Fire Risk Map; Golestan Forest; Gaussian kernel; SPATIAL-PATTERNS; GIS;
D O I
10.5194/isprs-archives-XLII-4-W4-477-2017
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
According to the industrialization of cities and the apparent increase in pollutants and greenhouse gases, the importance of forests as the natural lungs of the earth is felt more than ever to clean these pollutants. Annually, a large part of the forests is destroyed due to the lack of timely action during the fire. Knowledge about areas with a high-risk of fire and equipping these areas by constructing access routes and allocating the fire-fighting equipment can help to eliminate the destruction of the forest. In this research, the fire risk of region was forecasted and the risk map of that was provided using MODIS images by applying geographically weighted regression model with Gaussian kernel and ordinary least squares over the effective parameters in forest fire including distance from residential areas, distance from the river, distance from the road, height, slope, aspect, soil type, land use, average temperature, wind speed, and rainfall. After the evaluation, it was found that the geographically weighted regression model with Gaussian kernel forecasted 93.4% of the all fire points properly, however the ordinary least squares method could forecast properly only 66% of the fire points.
引用
收藏
页码:477 / 481
页数:5
相关论文
共 20 条
[1]  
Adab H., 2008, 1 INT C CLIM CHANG B, P178
[2]  
Akbari D., 2007, 2 DIS MAN C IR 12 26
[3]  
Almeida R., 1994, FOREST FIRE RISK ARE
[4]   An intelligent system for forest fire risk prediction and fire fighting management in Galicia [J].
Alonso-Betanzos, A ;
Fontenla-Romero, O ;
Guijarro-Berdiñas, B ;
Hernández-Pereira, E ;
Andrade, MIP ;
Jiménez, E ;
Soto, JLL ;
Carballas, T .
EXPERT SYSTEMS WITH APPLICATIONS, 2003, 25 (04) :545-554
[5]   Geographically weighted regression - modelling spatial non-stationarity [J].
Brunsdon, C ;
Fotheringham, S ;
Charlton, M .
JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES D-THE STATISTICIAN, 1998, 47 :431-443
[6]  
Charlton M., 2001, CISC VIS NETW IND GL, P11
[7]   MAPPING PROBABILITY OF FIRE OCCURRENCE IN SAN-JACINTO MOUNTAINS, CALIFORNIA, USA [J].
CHOU, YH ;
MINNICH, RA ;
CHASE, RA .
ENVIRONMENTAL MANAGEMENT, 1993, 17 (01) :129-140
[8]   APPLICATION OF REMOTE-SENSING AND GEOGRAPHIC INFORMATION-SYSTEMS TO FOREST FIRE HAZARD MAPPING [J].
CHUVIECO, E ;
CONGALTON, RG .
REMOTE SENSING OF ENVIRONMENT, 1989, 29 (02) :147-159
[9]   Spatial patterns of fire occurrence in Catalonia, NE, Spain [J].
Díaz-Delgado, R ;
Lloret, F ;
Pons, X .
LANDSCAPE ECOLOGY, 2004, 19 (07) :731-745
[10]   Applying GIS to develop a model for forest fire risk: A case study in Espirito Santo, Brazil [J].
Eugenio, Fernando Coelho ;
dos Santos, Alexandre Rosa ;
Fiedler, Nilton Cesar ;
Ribeiro, Guido Assuncao ;
da Silva, Aderbal Gomes ;
dos Santos, Aureo Banhos ;
Paneto, Greiciane Gaburro ;
Schettino, Vitor Roberto .
JOURNAL OF ENVIRONMENTAL MANAGEMENT, 2016, 173 :65-71