پديد آورندگان :
آوند، محمدتقي داﻧﺸﮕﺎه ﺗﺮﺑﯿﺖ ﻣﺪرس - داﻧﺸﮑﺪة ﻣﻨﺎﺑﻊﻃﺒﯿﻌﯽ و ﻋﻠﻮم درﯾﺎﯾﯽ , جاني زاده، سعيد داﻧﺸﮕﺎه ﺗﺮﺑﯿﺖ ﻣﺪرس - داﻧﺸﮑﺪة ﻣﻨﺎﺑﻊﻃﺒﯿﻌﯽ و ﻋﻠﻮم درﯾﺎﯾﯽ , فرزين، محسن داﻧﺸﮕﺎه ﯾﺎﺳﻮج - داﻧﺸﮑﺪة ﮐﺸﺎورزي و ﻣﻨﺎﺑﻊ ﻃﺒﯿﻌﯽ
كليدواژه :
پتانسيل‌يابي منابع آب زيرزميني , داده‌كاوي , جنگل تصادفي , رگرسيون خطي تعميم يافته , ياسوج-سي‌سخت
چكيده فارسي :
ﺑﺎ اﻓﺰاﯾﺶ ﺟﻤﻌﯿﺖ و ﺗﻮﺳــﻌﮥ ﮐﺸــﺎورزي ﻧﯿﺎز ﺑﻪ ﻣﻨﺎﺑﻊ آﺑﯽ ﺑﻪ ﺷــﺪت اﻓﺰاﯾﺶ ﯾﺎﻓﺘﻪ و ﻣﻨﺎﺑﻊ آب زﯾﺮزﻣﯿﻨﯽ، ﺑﯿﺶ از ﭘﯿﺶ، ﺑﻪﺧﺼــﻮص در ﻣﻨﺎﻃﻖ ﺧﺸـﮏ و ﻧﯿﻤﻪﺧﺸـﮏ ﻣﻮرد ﺗﻮﺟﻪ ﺑﺴـﯿﺎري ﻗﺮار ﮔﺮﻓﺘﻪ اﺳـﺖ. ﻫﺪف از اﯾﻦ ﭘﮋوﻫﺶ ﺗﻬﯿﮥ ﻧﻘﺸـﮥ ﭘﺘﺎﻧﺴـﯿﻞ ﻣﻨﺎﺑﻊ آب زﯾﺮزﻣﯿﻨﯽ ﺑﺎ اﺳﺘﻔﺎده از دو ﻣﺪل دادهﮐﺎوي ﺟﻨﮕﻞ ﺗﺼﺎدﻓﯽ )RF( و آﻣﺎري رﮔﺮﺳﯿﻮن ﺧﻄﯽ ﺗﻌﻤﯿﻢ ﯾﺎﻓﺘﻪ (GLM) در ﻣﺤﺪودة ﯾﺎﺳﻮج-ﺳﯽﺳﺨﺖ ﻣﯽ ﺑﺎ ﺷﺪ. ﺑﺪﯾﻦ ﻣﻨﻈﻮر ﻻﯾﻪﻫﺎي اﻃﻼﻋﺎﺗﯽ ﺷﺎﻣﻞ درﺟﮥ ﺷﯿﺐ، ﺟﻬﺖ ﺷﯿﺐ، ﻃﻮل ﺷﯿﺐ، ارﺗﻔﺎع از ﺳﻄﺢ درﯾﺎ، ﺷﺎﺧﺺ رﻃﻮﺑﺖ ﺗﻮﭘﻮﮔﺮاﻓﯽ، ﻓﺎﺻﻠﻪ از ﮔﺴﻞ، ﻓﺎﺻﻠﻪ از آﺑﺮاﻫﻪ، ﺑﺎرﻧﺪﮔﯽ، ﮐﺎرﺑﺮي اراﺿﯽ، ﺳﻨﮓﺷﻨﺎﺳﯽ، ﺷﺎﺧﺺ ﻣﻮﻗﻌﯿﺖ ﺗﻮﭘﻮﮔﺮاﻓﯽ و ﺷﺎﺧﺺ ﻗﺪرت ﺟﺮﯾﺎن ﺑﻪ ﻋﻨﻮان ﻣﻬﻢﺗﺮﯾﻦ ﻋﻮاﻣﻞ ﻣﺆﺛﺮ ﺑﺮ ﭘﺘﺎﻧﺴــﯿﻞ آب زﯾﺮزﻣﯿﻨﯽ ﺗﻌﯿﯿﻦ ﺷــﺪه و در ﻧﺮماﻓﺰار ArcGIS و SAGAGIS رﻗﻮﻣﯽ و ﺗﻬﯿﻪ ﺷــﺪﻧﺪ. از ﭘﺮاﮐﻨﺶ 362 ﭼ ﺸﻤﮥ ﻣﻮﺟﻮد در ﺳﻄﺢ ﻣﻨﻄﻘﻪ، 70 در ﺻﺪ )253 ﭼ ﺸﻤﻪ( ﺑﻪ ﻋﻨﻮان ﭼ ﺸﻤﻪﻫﺎي آﻣﻮز ﺷﯽ و 30 در ﺻﺪ (109 ﭼ ﺸﻤﻪ) ﺑﻪ ﻋﻨﻮان ﭼﺸﻤﻪﻫﺎي آزﻣﺎﯾﺸﯽ اﺳﺘﻔﺎده ﮔﺮدﯾﺪ. ﻧﺘﺎﯾﺞ ﻧﺸﺎن داد ﮐﻪ ﺳﻄﺢ ﻃﺒﻘﺎت ﺣﻀﻮر آب زﯾﺮزﻣﯿﻨﯽ ﺑﺎ ﭘﺘﺎﻧﺴﯿﻞ ﮐﻢ، ﻣﺘﻮﺳﻂ، زﯾﺎد و ﺧﯿﻠﯽ زﯾﺎد در ﻧﻘﺸﻪ ﺣﺎﺻﻞ از روش ﺟﻨﮕﻞ ﺗﺼﺎدﻓﯽ ﺑﻪ ﺗﺮﺗﯿﺐ 18/89 ،22/22 ،37/78 و 21/11 درﺻﺪ و در روش رﮔﺮﺳﯿﻮن ﺧﻄﯽ ﺗﻌﻤﯿﻢ ﯾﺎﻓﺘﻪ ﺑﻪ ﺗﺮﺗﯿﺐ 31/11 ،32/04 ،14/49 و 22/36 درﺻﺪ ﻣﯽﺑﺎﺷﺪ. ﻫﻤﭽﻨﯿﻦ ﺑﺎ ﺣﺴﺎﺳﯿﺖﺳﻨﺠﯽ ﻋﻮاﻣﻞ ﻣﺆﺛﺮ در ﻫﺮ دو روش، ﻋﺎﻣﻞﻫﺎي ﺑﺎرﻧﺪﮔﯽ، ارﺗﻔﺎع از ﺳﻄﺢ درﯾﺎ و ﻓﺎ ﺻﻠﻪ از ﮔ ﺴﻞ ﺣ ﺴﺎسﺗﺮﯾﻦ ﻋﻮاﻣﻞ ﺗﻌﯿﯿﻦ ﺷﺪﻧﺪ. ارزﯾﺎﺑﯽ دﻗﺖ ﻣﺪلﻫﺎي دادهﮐﺎوي ﻣﻮرد ا ﺳﺘﻔﺎده در اﯾﻦ ﺗﺤﻘﯿﻖ ﻧﯿﺰ ﺑﺎ ا ﺳﺘﻔﺎده از ﻣﻨﺤﻨﯽ ﻋﻤﻠﮑﺮد ﻧ ﺴﺒﯽ (ROC) ﻣﻮرد ﺳﻨﺠﺶ ﻗﺮار ﮔﺮﻓﺖ. ﺳﻄﺢ زﯾﺮ ﻣﻨﺤﻨﯽ (AUC) ﺑﺮاي دو ﻣﺪل RF و GLM ﺑﻪ ﺗﺮﺗﯿﺐ 92 % و 65 % درﺻﺪ را ﻧﺸﺎن ﻣﯽدﻫﺪ، ﺑﻨﺎﺑﺮاﯾﻦ دﻗﺖ ﻣﺪل ﺟﻨﮕﻞ ﺗﺼﺎدﻓﯽ در ﺗﻬﯿﮥ ﻧﻘﺸﮥ ﭘﺘﺎﻧﺴﯿﻞ آب زﯾﺮزﻣﯿﻨﯽ در ﻣﻨﻄﻘﮥ ﻣﻮرد ﻣﻄﺎﻟﻌﻪ ﺑﯿ ﺸﺘﺮ از ﻣﺪل رﮔﺮ ﺳﯿﻮن ﺧﻄﯽ ﺗﻌﻤﯿﻢﯾﺎﻓﺘﻪ ا ﺳﺖ. ﻣﺪلﻫﺎي ﻧﻮﯾﻦ دادهﮐﺎوي و آﻣﺎري در ﺗﻠﻔﯿﻖ ﺑﺎ GIS ﺑﺮاي ﭘﺘﺎﻧ ﺴﻞﯾﺎﺑﯽ ﻣﻨﺎﺑﻊ آب زﯾﺮزﻣﯿﻨﯽ ﻣﯽﺗﻮاﻧﺪ ﺑﺮاي ﻣﺪﯾﺮﯾﺖ ﭘﺎﯾﺪار، ﻣﻮرد ﺗﻮﺟﻪ ﻃﺮاﺣﺎن و ﺗﺼﻤﯿﻢﮔﯿﺮان ﻃﺮحﻫﺎي ﺗﻮﺳﻌﻪاي واﻗﻊ ﮔﺮدد.
چكيده لاتين :
Increasing population and agricultural development need dramatically water resources groundwater resources, therefore, are increasingly being considered, especially in arid and semi-arid regions. Aim of this research is mapping potential of groundwater resources on Yasouj-Sisakht region using data mining method Random Forest (RF) and Generalized Linear Statistical Model (GLM). For this purpose. For this purpose, information layers including slope, slope direction, slope length, aspect, topographic wetness index (TWI), distance from fault, distance from the stream, rainfall, land use, lithology, topographic position index (TPI) and stream power index (SPI) as the main factors influencing groundwater potential were identified and developed in ArcGIS and SAGAGIS software. From the distribution of 263 springs in the area, 70% (253 springs) were used as educational springs and 30% (109 springs) were used as experimental springs. The results showed that the level of underground water with low, medium, high and very high potential in the map of the random forest was 37.78, 22.22, 18.89 and 21.11%, respectively, and in the generalization linear model were 14.49, 32.04, 31.11 and 22.36%, respectively. Moreover, Sensitivity Analysis show that the factors affecting both methods are rainfall, altitude and distance from the fault factors. The accuracy of the data mining models used in this research was also evaluated using a relative performance curve (ROC). The area under curve (AUC) for both RF and GLM models is 92% and 65%, respectively. The accuracy of RF model, therefore, mapping groundwater potential in the study area is more than GLM model.
