ارزيابي پايداري برآوردهاي مدل بيشينه آنتروپي براي مدل‌سازي فرسايش شياري

Assessing the stability of maximum entropy prediction for rill erosion modelling

ﻻزﻣﻪ ﻣﺪﯾﺮﯾﺖ ﻓﺮﺳﺎﯾﺶ ﺧﺎك، اراﺋﻪ راﻫﮑﺎرﻫﺎي ﻣﻨﺎﺳﺒﯽ ﻣﯽ ﺑﺎﺷﺪ ﮐﻪ ﺑﺎ ﺷﻨﺎﺧﺖ از وﺿﻌﯿﺖ ﻓﺮﺳﺎﯾﺶ ﺧﺎك ﺣﺎﺻﻞ ﻣﯽﺷﻮد. ﻫﺪف از ﻣﻄﺎﻟﻌﻪ ﺣﺎﺿﺮ، ﻣﺪل-ﺳﺎزي ﭘﺘﺎﻧﺴﯿﻞ ﻓﺮﺳﺎﯾﺶ ﺷﯿﺎري ﺑﺎ اﺳﺘﻔﺎده از ﻣﺪل ﺑﯿﺸﯿﻨﻪ آﻧﺘﺮوﭘﯽ و ﺑﺮرﺳﯽ ﭘﺎﯾﺪاري ﻣﺪل ﺑﻪﻣﻨﻈﻮر آﮔﺎﻫﯽ از ﺣﺴﺎﺳﯿﺖﭘﺬﯾﺮي اﯾﻦ ﻓﺮﺳﺎﯾﺶ در ﺣﻮﺿﻪ آﺑﺨﯿﺰ ﮔﻞﮔﻞ اﺳﺘﺎن اﯾﻼم اﺳﺖ. ﺑﺪﯾﻦ ﻣﻨﻈﻮر، ﻓﺎﮐﺘﻮرﻫﺎي زﻣﯿﻦ- ﻣﺤﯿﻄﯽ ﺑﺮاي اﺳﺘﻔﺎده در ﻓﺮآﯾﻨﺪ ﻣﺪلﺳﺎزي اﻧﺘﺨﺎب ﺷﺪ. اﻓﺰون ﺑﺮ اﯾﻦ، ﻣﻮﻗﻌﯿﺖ 157 واﻗﻌﻪ ﻓﺮﺳﺎﯾﺶ ﺷﯿﺎري ﺑﺎ اﺳﺘﻔﺎده از ﺳﯿﺴﺘﻢ ﻣﻮﻗﻌﯿﺖ ﯾﺎب ﺟﻐﺮاﻓﯿﺎﯾﯽ )GPS( ﺛﺒﺖ ﺷﺪ. اﯾﻦ وﻗﺎﯾﻊ در ﻗﺎﻟﺐ دو ﮔﺮوه آﻣﻮزش و اﻋﺘﺒﺎرﺳﻨﺠﯽ ﺑﺎ ﻧﺴﺒﺖ 70 ﺑﻪ 30 ﮐﻼسﺑﻨﺪي ﺷﺪ. ﺑﻪﻣﻨﻈﻮر ارزﯾﺎﺑﯽ ﭘﺎﯾﺪاري ﻣﺪل، ﮐﻼسﺑﻨﺪيﻫﺎي ﻣﺬﮐﻮر ﺳﻪ ﺑﺎر ﺗﮑﺮار ﺷﺪ و ﺑﻨﺎﺑﺮاﯾﻦ، ﺳﻪ ﻧﻤﻮﻧﻪ ﻣﺠﻤﻮﻋﻪ داده )D2 ،D1 و D3( آﻣﺎده ﺷﺪ. ارزﯾﺎﺑﯽ ﮐﺎرآﯾﯽ ﻣﺪل ﺑﺎ اﺳﺘﻔﺎده از ﺳﻄﺢ زﯾﺮ ﻣﻨﺤﻨﯽ ROC ﺻﻮرت ﭘﺬﯾﺮﻓﺖ. ﺑﺎ ﺗﻮﺟﻪ ﺑﻪ ﻧﺘﺎﯾﺞ ﭘﺎﯾﺪاري، ﺗﻤﺎﻣﯽ ﻣﺠﻤﻮﻋﻪ دادهﻫﺎ، ﻣﻘﺎدﯾﺮ ﺳﻄﺢ زﯾﺮ ﻣﻨﺤﻨﯽ ﺧﻮﺑﯽ را ﮐﺴﺐ ﻧﻤﻮدﻧﺪ و از ﻧﻈﺮ ﮐﺎرآﯾﯽ ﺑﺮازش )1/3 = RAUC( و ﭘﯿﺶﺑﯿﻨﯽ )3/1 = RAUC( ﭘﺎﯾﺪار ﻣﯽﺑﺎﺷﻨﺪ. ﺑﻪ ﺑﯿﺎن دﯾﮕﺮ، ﻧﺘﺎﯾﺞ ﺛﺎﺑﺖ ﻧﻤﻮد زﻣﺎﻧﯽ ﮐﻪ دادهﻫﺎي واﺳﻨﺠﯽ و اﻋﺘﺒﺎرﺳﻨﺠﯽ ﺗﻐﯿﯿﺮ ﭘﯿﺪا ﻧﻤﻮد ﻣﺪل ﮐﺎﻣﻼً ﭘﺎﯾﺪار ﺑﺎﻗﯽ ﻣﺎﻧﺪ. ﻋﻼوه ﺑﺮ اﯾﻦ، ﻣﺸﺨﺺ ﺷﺪ ﮐﻪ ﻣﺪل ﺣﺪاﮐﺜﺮ آﻧﺘﺮوﭘﯽ )MaxEnt( ﻗﺎدر ﺑﻪ ﺗﻮﻟﯿﺪ ﻧﻘﺸﻪ ﺣﺴﺎﺳﯿﺖﭘﺬﯾﺮي ﻓﺮﺳﺎﯾﺶ ﺷﯿﺎري اﺳﺖ. از ﺳﻮي دﯾﮕﺮ، ﺑﺮ ﻣﺒﻨﺎي آﻧﺎﻟﯿﺰ ﺣﺴﺎﺳﯿﺖ، ﻣﺸﺨﺺ ﺷﺪ ﮐﻪ ﻣﻬﻢ ﺗﺮﯾﻦ اﺟﺰا در ﻣﺪل ﺳﺎزي ﺣﺴﺎﺳﯿﺖ ﭘﺬﯾﺮي ﻓﺮﺳﺎﯾﺶ ﺷﯿﺎري ﺳﻨﮓﺷﻨﺎﺳﯽ و ﻓﺎﺻﻠﻪ از آﺑﺮاﻫﻪ ﻣﯽﺑﺎﺷﺪ. روشﺷﻨﺎﺳﯽ ﺗﻄﺒﯿﻖﯾﺎﻓﺘﻪ ﺑﻪﻋﻨﻮان ﯾﮏ روﯾﮑﺮد ﻣﺆﺛﺮ ﺑﺮاي ﺑﺮﻧﺎﻣﻪرﯾﺰي ﮐﺎرﺑﺮي اراﺿﯽ و ﻣﺪﯾﺮﯾﺖ رﯾﺴﮏ ﻓﺮﺳﺎﯾﺶ ﺳﻮدﻣﻨﺪ ﻣﯽﺑﺎﺷﺪ.

Soil erosion management requires providing appropriate solutions that can be achieved with knowing soil erosion situation. The aim of this study, modeling rill erosion potentially by using maximum entropy (MaxEnt) and investigation of its robustness to knowing about rill erosion susceptibility in the Golgol watershed, Ilam province. To this purpose, different geo-environmental factors were selected to be employed in the modeling process. In addition, 157 rill erosion events were recorded by a global positioning system (GPS). These events were then classified into two classes of training and validation with a ratio of 70:30. To evaluate model robustness, these classifications were repeated three times, and therefore, three sample datasets (D1, D2, and D3), were prepared. The area under receiver operating characteristics (AUC) curve was used for evaluating the performance of the model. Regarding the robustness results, all of the datasets obtained good AUC values and all of them were robust for both the goodness-of-fit (RAUC =1.3) and prediction performance (RAUC =3.1). In other words, the results demonstrated that the model remained quite stable when the calibration and validation data were changed. In addition, we found that the MaxEnt model is capable to produce rill erosion susceptibility map. Furthermore, based on the sensitivity analysis, it found that the most important components in rill erosion susceptibility modeling are lithology and distance from stream. The adopted methodology can be useful as an efficient approach for land use planning and erosion risk management.