پديد آورندگان :
موحدي نسب، سميه داﻧﺸﮕﺎه ﮔﻨﺒﺪ ﮐﺎووس , فتح آبادي، ابوالحسن داﻧﺸﮕﺎه ﮔﻨﺒﺪ ﮐﺎووس - ﮔﺮوه ﻣﺮﺗﻊ و آﺑﺨﯿﺰداري , سيديان، مرتضي داﻧﺸﮕﺎه ﮔﻨﺒﺪ ﮐﺎووس - ﮔﺮوه ﻣﺮﺗﻊ و آﺑﺨﯿﺰداري , حشمت پور، علي داﻧﺸﮕﺎه ﮔﻨﺒﺪ ﮐﺎووس - ﮔﺮوه ﻣﺮﺗﻊ و آﺑﺨﯿﺰداري
كليدواژه :
چند متغيره , دومتغيره , فرسايش خندقي , منحنيROC
چكيده فارسي :
در اﯾﻦ ﺗﺤﻘﯿﻖ اﻗﺪام ﺑﻪ ﭘﻬﻨﻪ ﺑﻨﺪي ﺧﻄﺮ ﻓﺮﺳﺎﯾﺶ ﺧﻨﺪﻗﯽ ﺑﺎ اﺳﺘﻔﺎده از روش ﻫﺎي ﻧﺴﺒﺖ ﻓﺮاواﻧﯽ، ﺷﺎﺧﺺ آﻣﺎري، رﮔﺮﺳﯿﻮن ﻟﺠﺴـﺘﯿﮏ و ﺟﻨﮕﻞ ﺗﺼﺎدﻓﯽ در ﻣﻨﻄﻘﮥ آي ﺗﻤﺮ اﺳﺘﺎن ﮔﻠﺴﺘﺎن ﺷﺪ. ﭘﺲ از ﺗﻬﯿﮥ ﻧﻘﺸﮥ ﭘﺮاﮐﻨﺶ ﺧﻨﺪق ﻫﺎ، ﻧﻘﺸﮥ 13 ﻋﺎﻣﻞ ﻣﺆﺛﺮ ﺑﺮ ﻓﺮآﯾﻨﺪ ﺧﻨﺪﻗﯽ ﺷﺪن ﺷﺎﻣﻞ: زﻣﯿﻦ ﺷﻨﺎﺳﯽ، ﻓﺎﺻﻠﻪ از ﮔﺴﻞ، ﺗﺮاﮐﻢ ﮔﺴﻞ، ارﺗﻔﺎع، ﻃﻮل ﺷﯿﺐ، درﺻﺪ ﺷﯿﺐ، ﺟﻬﺖ ﺷﯿﺐ، اﻧﺤﻨﺎي ﺻﺤﻔﻪ، اﻧﺤﻨﺎي ﭘﺮوﻓﯿﻞ، ﻓﺎﺻﻠﻪ از ﺟﺎده، ﮐﺎرﺑﺮي اراﺿﯽ، ﺷﺎﺧﺺ ﻗﺪرت ﺟﺮﯾﺎن و ﺷﺎﺧﺺ رﻃﻮﺑﺖ ﺗﻮﭘﻮﮔﺮاﻓﯿﮏ ﺗﻬﯿﻪ ﺷﺪﻧﺪ. ﺧﻨﺪق ﻫﺎي ﻣﺸﺎﻫﺪاﺗﯽ ﺑﻪ دو دﺳﺘﻪ آﻣـﻮزش و اﻋﺘﺒﺎرﺳﻨﺠﯽ ﺗﻘﺴﯿﻢ و ﺑﺎ ﻣﻘﺎﯾﺴﮥ ﻧﻘﺸﮥ ﭘﺮاﮐﻨﺶ ﺧﻨﺪق ﻫﺎ ﺑـﺎ ﻧﻘﺸـﮥ ﻫـﺮ ﯾـﮏ از 13 ﻓـﺎﮐﺘﻮر ﻣﺴـﺘﻘﻞ، وزن ﻫـﺎي روش ﻫـﺎي دوﻣﺘﻐﯿـﺮه و ﭘﺎراﻣﺘﺮﻫﺎي روش ﻫﺎي ﭼﻨﺪ ﻣﺘﻐﯿﺮه ﺑﺮآورد ﮔﺮدﯾﺪ. ﻧﺘﺎﯾﺞ ﻧﺸـﺎن داد ﻣﻘـﺪار ﻣﺴـﺎﺣﺖ زﯾـﺮ ﻣﻨﺤﻨـﯽ ROC دادهﻫـﺎي اﻋﺘﺒﺎرﺳـﻨﺠﯽ ﺑـﺮاي روش ﻫﺎي ﺟﻨﮕﻞ ﺗﺼﺎدﻓﯽ (0/94)، رﮔﺮﺳﯿﻮن ﻟﺠﺴﺘﯿﮏ (0/86)، ﻧﺴﺒﺖ ﻓﺮاواﻧﯽ (0/74) و ﺷﺎﺧﺺ آﻣﺎري (0/78)، ﺑﻪدﺳﺖ آﻣﺪ. ﻫﻤﭽﻨﯿﻦ ﮐﻤﺘﺮﯾﻦ ﻣﺴﺎﺣﺖ ﻃﺒﻘﻪ ﺑﺎ ﺣﺴﺎﺳﯿﺖ ﺧﯿﻠﯽ ﺑﺎﻻ ﺑﻪ ﺗﺮﺗﯿﺐ ﺑﺮاي روش ﻫﺎي ﺟﻨﮕﻞ ﺗﺼﺎدﻓﯽ، ﻧﺴﺒﺖ ﻓﺮاواﻧﯽ و رﮔﺮﺳﯿﻮن ﻟﺠﺴﺘﯿﮏ ﺑﻪدﺳـﺖ آﻣﺪ. در ﻣﺠﻤﻮع در اﯾﻦ ﺗﺤﻘﯿﻖ روش ﺟﻨﮕﻞ ﺗﺼﺎدﻓﯽ ﺑﻬﺘﺮﯾﻦ ﻋﻤﻠﮑﺮد را داﺷﺖ و ﭘﺲ از اﯾـﻦ ﻣـﺪل، روش ﻫـﺎي رﮔﺮﺳـﯿﻮن ﻟﺠﺴـﺘﯿﮏ و ﺷﺎﺧﺺ آﻣﺎري ﻋﻤﻠﮑﺮد ﺑﻬﺘﺮي ﻧﺴﺒﺖ ﺑﻪ ﺳﺎﯾﺮ روش ﻫﺎ داﺷﺘﻪ اﻧﺪ.
چكيده لاتين :
In this study using Frequency Ratio (FR), Statistical Index (SI), Weights Of Evidence(WOF), Logistic Regression (LR), Random Forest (RF) models the probability of gully formation was calculated in Aytamar watershed and susceptibility maps was prepared. First the thematic maps of 13 gully conditioning factors including lithological formations, distance to faults, faults density, altitude, slope-length, slope angle, slope aspect, plan curvature, profile curvature, distance to roads, land use, distance to rivers, stream power index and topographic wetness index was prepared. Then landslide inventory map was combined with each gully conditioning factor and all models weights and parameters were calculated. Area under curve for test data was calculated as 0.74, 0.78, 0.75, 0.86 and 0.96 for Frequency Ratio (FR), Statistical Index (SI), Weights Of Evidence(WOF), Logistic Regression (LR), Random Forest (RF) models, respectively. Random forest, Frequency Ratio and Logistic Regression have the least the area of high susceptibility zone, respectively. With respect three validation criteria multivariate methods including Random Forest and Logistic Regression had the best performance among all models.
