پديد آورندگان :
غلامي، عيسي داﻧﺸﮕﺎه ﺗﺮﺑﯿﺖ ﻣﺪرس - داﻧﺸﮑﺪة ﻣﻨﺎﺑﻊ ﻃﺒﯿﻌﯽ , وفاخواه، مهدي داﻧﺸﮕﺎه ﺗﺮﺑﯿﺖ ﻣﺪرس - داﻧﺸﮑﺪة ﻣﻨﺎﺑﻊ ﻃﺒﯿﻌﯽ - گروه آبخيزداري , علوي، جليل داﻧﺸﮕﺎه ﺗﺮﺑﯿﺖ ﻣﺪرس - داﻧﺸﮑﺪة ﻣﻨﺎﺑﻊ ﻃﺒﯿﻌﯽ - گروه جنگلداري
كليدواژه :
سيل‌گيري , داده‌كاوي , مدل‌هاي داده محور , مدل‌سازي , منحني تشخيص عملكرد , استان گيلان
چكيده فارسي :
ﺑﻪ دﻟﯿﻞ ﮐﻤﺒﻮد اﻃﻼﻋﺎت در اﮐﺜﺮ ﺣﻮزهﻫﺎي آﺑﺨﯿﺰ، ﺑﺴﯿﺎري از ﻣﺤﻘﻘﯿﻦ ﺑﺮاي ﻣﻄﺎﻟﻌﻪﻫﺎي ﻫﯿﺪروﻟﻮژﯾﮑﯽ و ﺳﯿﻞﮔﯿﺮي ﺑﻪ اﺳﺘﻔﺎده از ﺗﺠﺰﯾﻪ و ﺗﺤﻠﯿﻞﻫﺎي ﻣﮑﺎﻧﯽ در ﺳﯿﺴﺘﻢ اﻃﻼﻋﺎت ﺟﻐﺮاﻓﯿﺎﯾﯽ روي آوردﻧﺪ. ﭘﮋوﻫﺶ ﺣﺎﺿﺮ ﺑﻪ ﻣﻨﻈﻮر ﻣﻘﺎﯾﺴﮥ ﮐﺎراﯾﯽ ﺳﻪ ﻣﺪل ﻣﺎﺷﯿﻦ ﺑﺮدار ﭘﺸﺘﯿﺒﺎن )SVM(، ﺧﻄﯽ ﺗﻌﻤﯿﻢ ﯾﺎﻓﺘﻪ )GLM( و ﺟﻤﻌﯽ ﺗﻌﻤﯿﻢ ﯾﺎﻓﺘﻪ )GAM( در ﺗﻬﯿﮥ ﻧﻘﺸﮥ ﺳﯿﻞﮔﯿﺮي اﺳﺘﺎن ﮔﯿﻼن ﺑﺮﻧﺎﻣﻪرﯾﺰي ﺷﺪه اﺳﺖ. ﺑﺪﯾﻦ ﻣﻨﻈﻮر ﻻﯾﻪﻫﺎي اﻃﻼﻋﺎﺗﯽ درﺟﮥ ﺷﯿﺐ، ﺟﻬﺖ ﺷﯿﺐ، ﺷﮑﻞ ﺷﯿﺐ، ارﺗﻔﺎع از ﺳﻄﺢ درﯾﺎ، ﻓﺎﺻﻠﻪ از رودﺧﺎﻧﻪ، ﺗﺮاﮐﻢ زﻫﮑﺸﯽ، زﻣﯿﻦ ﺷﻨﺎﺳﯽ، ﮐﺎرﺑﺮي اراﺿﯽ، ﺷﺎﺧﺺ رﻃﻮﺑﺖ ﺗﻮﭘﻮﮔﺮاﻓﯽ و ﺷﺎﺧﺺ ﺗﻮان آﺑﺮاﻫﻪ در ﻣﺤﯿﻂ ﺳﺎﻣﺎﻧﮥ اﻃﻼﻋﺎت ﺟﻐﺮاﻓﯿﺎﯾﯽ )ﻧﺮماﻓﺰارﻫﺎي ArcGIS و SAGA-GIS( ﺗﻬﯿﻪ ﺷﺪﻧﺪ. ﺳﭙﺲ ﺑﺮ اﺳﺎس اﻃﻼﻋﺎت 220 ﻧﻘﻄﮥ ﺳﯿﻞﮔﯿﺮ، از 70 درﺻﺪ ﺗﻌﺪاد ﮐﻞ ﻧﻘﺎط ﺑﻪ ﻣﻨﻈﻮر واﺳﻨﺠﯽ و 30 درﺻﺪ ﺑﺎﻗﯿﻤﺎﻧﺪه ﺑﺮاي اﻋﺘﺒﺎرﺳﻨﺠﯽ و ارزﯾﺎﺑﯽ ﮐﺎرآﯾﯽ ﻣﺪلﻫﺎ ﻣﻮرد اﺳﺘﻔﺎده ﻗﺮار ﮔﺮﻓﺖ. ﻧﺘﺎﯾﺞ ارزﯾﺎﺑﯽ دﻗﺖ ﻣﺪلﻫﺎ ﺑﻪ ﺗﺮﺗﯿﺐ ﺑﺎ اﺳﺘﻔﺎده از ﺷﺎﺧﺺﻫﺎي ﺳﻄﺢ زﯾﺮ ﻣﻨﺤﻨﯽ )AUC( و ﮐﺎﭘﺎ )Kappa( ﻧﺸﺎن داد ﮐﻪ از ﻧﻈﺮ ﺷﺎﺧﺺ ﺳﻄﺢ زﯾﺮ ﻣﻨﺤﻨﯽ )AUC(، ﻣﺪل ﻣﺎﺷﯿﻦ ﺑﺮدار ﭘﺸﺘﯿﺒﺎن )SVM( ﺑﺎ 0/835 و ﻣﺪل ﺟﻤﻌﯽ ﺗﻌﻤﯿﻢ ﯾﺎﻓﺘﻪ )GAM( ﺑﺎ 0/827 داراي دﻗﺖ ﺧﯿﻠﯽ ﺧﻮب و ﻣﺪل ﺧﻄﯽ ﺗﻌﻤﯿﻢ ﯾﺎﻓﺘﻪ )GLM( ﺑﺎ 0/79 داراي دﻗﺖ ﺧﻮب ﻣﯽﺑﺎﺷﺪ. از ﻧﻈﺮ ﺷﺎﺧﺺ ﮐﺎﭘﺎ )Kappa( ﻣﺪل ﻣﺎﺷﯿﻦ ﺑﺮدار ﭘﺸﺘﯿﺒﺎن )SVM( ﺑﺎ 0/58 داري دﻗﺖ ﺧﻮب، ﻣﺪل ﺟﻤﻌﯽ ﺗﻌﻤﯿﻢ ﯾﺎﻓﺘﻪ )GAM( ﺑﺎ 0/53 و ﻣﺪل ﺧﻄﯽ ﺗﻌﻤﯿﻢ ﯾﺎﻓﺘﻪ )GLM( ﺑﺎ 0/48 داراي دﻗﺖ ﻗﺎﺑﻞ ﻗﺒﻮل ﻣﯽﺑﺎﺷﻨﺪ. ﺑﻨﺎﺑﺮاﯾﻦ ﺑﺮ اﺳﺎس ﺷﺎﺧﺺﻫﺎي ﻣﺬﮐﻮر ﻣﺪل ﻣﺎﺷﯿﻦ ﺑﺮدار ﭘﺸﺘﯿﺒﺎن )SVM( ﻧﺴﺒﺖ ﺑﻪ دو ﻣﺪل دﯾﮕﺮ در ﺷﻨﺎﺳﺎﯾﯽ ﻣﻨﺎﻃﻖ ﺳﯿﻞﮔﯿﺮ ﮐﺎراﯾﯽ ﺑﺎﻻﺗﺮي دارد. ﻫﻤﭽﻨﯿﻦ ﻋﻮاﻣﻞ ﻓﺎﺻﻠﻪ از رودﺧﺎﻧﻪ، ارﺗﻔﺎع از ﺳﻄﺢ درﯾﺎ و ﺷﯿﺐ ﺑﯿﺸﺘﺮﯾﻦ ﺗﺄﺛﯿﺮ را ﺑﺮ ﺳﯿﻞﮔﯿﺮي ﻣﻨﻄﻘﮥ ﻣﻮرد ﻣﻄﺎﻟﻌﻪ دارﻧﺪ.
چكيده لاتين :
Due to the lack of information in most of the watersheds, many researchers attempt to use spatial analysis within Geographic Information System (GIS) in hydrological and Flood Prone (FP) area studies. The present study was designed to compare the efficiency of three models i.e. Support Vector Machine (SVM), Generalized Linear Model (GLM) and Generalized Additive Model (GAM) for preparing the flood susceptibility mapping in Guilan province, Iran.
For this purpose, slope, aspect, plan curvature, elevation, distance from the river, drainage density, geology, land use, Topographic Wetness Index (TWI) and Stream Power Index (SPI) layers were derived in GIS (ArcGIS and SAGA-GIS). Using 220 flood locations, 70% and 30% out of total flood locations were then used to calibrate and to validate the performance of the models, respectively. The evaluation results of the models accuracy using the area under the curve (AUC) and Kappa indices showed that in terms of AUC, the SVM with 0.835 and the GAM with 0.827, and the GLM with of 0.79 performed very good and good classes, respectively. In terms of Kappa index, the SVM with 0.58, GAM with 0.53 and GLM with 0.48 are performed good and acceptable classes, respectively. Therefore, based on the mentioned indices, the SVM superior to other two models for identifying the flood susceptibility areas.
