كليدواژه :
پتانسيل سطح آب زيرزميني , مدل عامل اطمينان , سيستم اطلاعات مكاني (GIS) , مدل بگينگ
چكيده فارسي :
ﺑﺎ ﺗﻮﺟﻪ ﺑﻪ ﺗﻐﯿﯿﺮات اﻗﻠﯿﻤﯽ و رﺷﺪ ﺟﻮاﻣﻊ ﺷﻬﺮي، ﻧﯿﺎز ﺑﻪ آب زﯾﺮزﻣﯿﻨﯽ و اﮐﺘﺸﺎف اﯾﻦ ﻣﻨﺎﺑﻊ رو ﺑﻪ اﻓﺰاﯾﺶ اﺳﺖ؛ ﺑﻨﺎﺑﺮاﯾﻦ ﻫﺪف از ﺗﺤﻘﯿﻖ ﺣﺎﺿﺮ، ﺗﻬﯿﻪ ﻧﻘﺸﻪ ﭘﺘﺎﻧﺴﯿﻞ ﺳﻄﺢ آب زﯾﺮزﻣﯿﻨﯽ ﺑﺎ اﺳﺘﻔﺎده از ﺳﯿﺴﺘﻢ اﻃﻼﻋﺎت ﻣﮑﺎﻧﯽ )GIS( در ﻣﻨﻄﻘﻪاي واﻗﻊ در دﺷﺖ ﺑﻮﺷﻬﺮ ﺑﺎ اﺳﺘﻔﺎده از ﺗﺮﮐﯿﺐ روش آﻣﺎري ﻋﺎﻣﻞ اﻃﻤﯿﻨﺎن ﺑﺎ روش دادهﮐﺎوي ﺑﮕﯿﻨﮓ اﺳﺖ. ﺑﺪﯾﻦ ﻣﻨﻈﻮر در ﮔﺎم اول، 339 ﻣﻮﻗﻌﯿﺖ ﭼﺎه در ﻣﻨﻄﻘﻪ ﻣﻮردﻣﻄﺎﻟﻌﻪ ﻣﺸﺨﺺ ﮔﺮدﯾﺪ و ﺑﻪﺻﻮرت ﺗﺼﺎدﻓﯽ، 238 ﭼﺎه )70 درﺻﺪ( ﺑﻪﻋﻨﻮان ﻧﻘﺎط آﻣﻮزﺷﯽ و 101 ﭼﺎه )30 درﺻﺪ( ﺑﻪﻋﻨﻮان ﻧﻘﺎط اﻋﺘﺒﺎرﺳﻨﺠﯽ ﺗﻌﯿﯿﻦ ﮔﺮدﯾﺪ. در ﮔﺎم ﺑﻌﺪ، 15 ﻋﺎﻣﻞ ﺗﺄﺛﯿﺮﮔﺬار ﺑﺮ ﺗﺠﻤﻊ آب زﯾﺮزﻣﯿﻨﯽ ﻣﺎﻧﻨﺪ ارﺗﻔﺎع، زاوﯾﻪ ﺷﯿﺐ، ﺟﻬﺖ ﺷﯿﺐ، ﻃﻮل ﺷﯿﺐ، اﻧﺤﻨﺎي ﺳﻄﺢ، اﻧﺤﻨﺎي آﺑﺮاﻫﻪ، ﺷﺎﺧﺺ رﻃﻮﺑﺖ ﺗﻮﭘﻮﮔﺮاﻓﯽ، ﻓﺎﺻﻠﻪ از ﮔﺴﻞ، ﺗﺮاﮐﻢ ﮔﺴﻞ، ﻓﺎﺻﻠﻪ از رودﺧﺎﻧﻪ، ﺗﺮاﮐﻢ آﺑﺮاﻫﻪ، ﺑﺎرﻧﺪﮔﯽ، ﻟﯿﺘﻮﻟﻮژي، ﭘﻮﺷﺶ اراﺿﯽ و ﻧﻮع ﺧﺎك در ﻧﺮماﻓﺰار 10.3 ArcGIS و Saga GIS ﺗﻬﯿﻪ ﮔﺮدﯾﺪ. راﺑﻄﻪ ﻣﮑﺎﻧﯽ ﺑﯿﻦ ﭘﺎراﻣﺘﺮﻫﺎي ﻣﺆﺛﺮ و ﻣﻮﻗﻌﯿﺖ ﭼﺎهﻫﺎ ﺑﺎ اﺳﺘﻔﺎده از ﻣﺪل ﻋﺎﻣﻞ اﻃﻤﯿﻨﺎن ﻣﺸﺨﺺ ﮔﺮدﯾﺪ و ﺑﻪﻣﻨﻈﻮر ﭘﯿﺎدهﺳﺎزي ﻣﺪل ﺑﮕﯿﻨﮓ از اﯾﻦ وزنﻫﺎ اﺳﺘﻔﺎده ﺷﺪ. ﺑﻪﻣﻨﻈﻮر ارزﯾﺎﺑﯽ دﻗﺖ ﻣﺪل ﺗﺮﮐﯿﺒﯽ از ﺷﺎﺧﺺﻫﺎي ﺿﺮﯾﺐ ﺗﻌﯿﯿﻦ، RMSE و MAE اﺳﺘﻔﺎده ﺷﺪ و ﻫﻤﭽﻨﯿﻦ ﺑﻪﻣﻨﻈﻮر ارزﯾﺎﺑﯽ دﻗﺖ ﻧﻘﺸﻪﻫﺎي ﺗﻬﯿﻪﺷﺪه از ﻣﻨﺤﻨﯽ ﺗﺸﺨﯿﺺ ﻋﻤﻠﮑﺮد ﻧﺴﺒﯽ )ROC( و ﺳﻄﺢ زﯾﺮ آن )AUC( اﺳﺘﻔﺎده ﮔﺮدﯾﺪ. ﻧﺘﺎﯾﺞ ﺣﺎﺻﻞ از ارزﯾﺎﺑﯽ ﻧﺸﺎن ﻣﯽدﻫﺪ ﮐﻪ ﻣﻘﺎدﯾﺮ ﺷﺎﺧﺺﻫﺎي ﺿﺮﯾﺐ ﺗﻌﯿﯿﻦ، RMSE و MAE ﺑﺮاي دادهﻫﺎي آﻣﻮزﺷﯽ و اﻋﺘﺒﺎرﺳﻨﺠﯽ ﺑﻪ ﺗﺮﺗﯿﺐ ﺑﺮاﺑﺮ 76 درﺻﺪ، 0/247، 73/5 ،0/162 درﺻﺪ، 0/256 و 0/169 اﺳﺖ. ﻧﺘﺎﯾﺞ ارزﯾﺎﺑﯽ ﻣﻨﺤﻨﯽ ROC ﻧﺸﺎن ﻣﯽدﻫﺪ ﮐﻪ ﺳﻄﺢ زﯾﺮ ﻣﻨﺤﻨﯽ ﺑﻪ ﺗﺮﺗﯿﺐ 86/2 و 94/8 درﺻﺪ ﺑﺮاي ﻣﺪلﻫﺎي ﻋﺎﻣﻞ اﻃﻤﯿﻨﺎن و ﺗﺮﮐﯿﺐ ﻣﺪل ﻋﺎﻣﻞ اﻃﻤﯿﻨﺎن ﺑﺎ ﻣﺪل دادهﮐﺎوي ﺑﮕﯿﻨﮓ اﺳﺖ
چكيده لاتين :
Due to climate change and growth of urban communities, the need for groundwater and exploration of these resources are increasing. Therefore, the purpose of this study was to provide a groundwater potential mapping using the geographic information system (GIS) in a region located in Booshehr plain using an ensemble of certainty factor (CF) method with Bagging data mining method. For this purpose, in the first step, 339 well locations were identified in the study area, of which 238 wells (70%) were randomly selected as training points and 101 wells (30%) were selected as validation points. In the next step, 15 factors affecting groundwater such as altitude, slope angle, slope direction, slope length, plan curvature, profile curvature, topographic wetness index, distance from fault, fault density, distance from river, drainage density, rainfall, lithology, Soil and land cover were prepared in ArcGIS 10.3 and Saga GIS software. The spatial relationship between the effective parameters and the location of the wells was determined using a CF model. These weights were used to implement the Bagging model. In order to validate the accuracy of the ensemble model, the RMSE and MAE indices were used. Also, in order to validate the accuracy of the maps, ROC and AUC were used. The results of this study showed that the values of RMSE and MAE indices for training and validation are equal to 0.247, 0.162, 0.256 and 0.169 respectively. The evaluation results of the ROC curve indicated that the AUC was 86.2 and 94.8%, respectively, for CF models and the ensemble of CF model with the Bagging model.
