کاربرد الگوریتم ژنتیک در برآورد توزیع مکانی پ‌هاش خاک با ترکیب زمین‌آمار و برنامه‌ریزی بیان ژن

آﮔﺎﻫﯽ در ﻣﻮرد ﺗﻮزﯾﻊ ﻣﮑﺎﻧﯽ وﯾﮋﮔﯽﻫﺎی ﺧﺎک ﻧﻘﺶ ﻣﻬﻤﯽ در ﺳﯿﺴﺘﻢ رﺷﺪ و ﻋﻤﻠﮑﺮد ﻣﺤﺼﻮل در ﺑﺨﺶ ﮐﺸﺎورزی دارد. در اﯾﻦ راﺳﺘﺎ ﺟﻬﺖ اﻓﺰاﯾﺶ دﻗﺖ در ﺗﻮزﯾﻊ ﻣﮑﺎﻧﯽ phﺧﺎک ، اﻟﮕﻮرﯾﺘﻢ ژﻧﺘﯿﮏ در ﺗﺮﮐﯿﺐ ﺑﺮآوردﻫﺎی رﮔﺮﺳﯿﻮن ﺧﻄﯽ، ﺑﺮﻧﺎﻣﻪرﯾﺰی ﺑﯿﺎن ژن gep و زﻣﯿﻦآﻣﺎر درونﯾﺎﺑﯽ ﮐﺮﯾﺠﯿﻨﮓ در ﻣﻨﺎﻃﻘﯽ از اﺳﺘﺎن آذرﺑﺎﯾﺠﺎنﺷﺮﻗﯽ ﺷﻬﺮﺳﺘﺎنﻫﺎی ﺑﻨﺎب، ﻋﺠﺐﺷﯿﺮ و ﻣﺮاﻏﻪ ﻣﻮرد اﺳﺘﻔﺎده ﻗﺮار ﮔﺮﻓﺖ. ﻣﺪل ﻧﯿﻢﺗﻐﯿﯿﺮﻧﻤﺎﯾﺨﻄﯽ در درونﯾﺎﺑﯽ ﮐﺮﯾﺠﯿﻨﮓ دارای ﮐﻤﺘﺮﯾﻦ ﻣﻘﺪار ﺧﻄﺎاﺳﺖ. ﺑﺮﻧﺎﻣﻪرﯾﺰی ﺑﯿﺎن ژن و رﮔﺮﺳﯿﻮن ﺧﻄﯽ ﺑﻪﺗﺮﺗﯿﺐ در ﺑﺮآورد ﺗﻮزﯾﻊ ﻣﮑﺎﻧﯽphﺧﺎک، ﮐﻤﺘﺮﯾﻦ و ﺑﯿﺸﺘﺮﯾﻦ ﻣﻘﺪارﺧﻄﺎ را دارﻧﺪ،ﻣﯿﺰان ﮐﺎﻫﺸﻤﯿﺎﻧﮕﯿﻦ ﻣﺮﺑﻊ ﺧﻄﺎ، ﺧﻄﺎی ﺟﺬر ﻣﯿﺎﻧﮕﯿﻦ ﻣﺮﺑﻌﺎت، ﺧﻄﺎی ﺟﺬر ﻣﯿﺎﻧﮕﯿﻦ ﻣﺮﺑﻌﺎت ﻧﺴﺒﯿﺎز رﮔﺮﺳﯿﻮن ﺧﻄﯽ ﺑﻪ زﻣﯿﻦآﻣﺎر ﺑﻬﺘﺮﺗﯿﺐ 27/47،58/67و 26/47درﺻﺪ و ﻣﯿﺰان ﮐﺎﻫﺸﺸﺎﺧﺺ ﭘﺮاﮐﻨﺪﮔﯽ و ﻣﯿﺎﻧﮕﯿﻦ درﺻﺪ ﺧﻄﺎی ﻣﻄﻠﻖ ﺗﻌﺪﯾﻞ ﺷﺪه از رﮔﺮﺳﯿﻮن ﺧﻄﯽ ﺑﻪ ﺑﺮﻧﺎﻣﻪرﯾﺰی ﺑﯿﺎن ژن ﺑﻪﺗﺮﺗﯿﺐ 23/8و 37/03 درﺻﺪ اﺳﺖ.روش ﺗﺮﮐﯿﺒﯿﺒﺎ اﺳﺘﻔﺎده از اﻟﮕﻮرﯾﺘﻢ ژﻧﺘﯿﮏ ﻧﺴﺒﺖ ﺑﻪ ﺳﻪ ﻧﻮع ﻣﺪلﺳﺎزی، ﺧﻄﺎی ﺑﺮآورد ﺗﻮزﯾﻊ ﻣﮑﺎﻧﯽ phﺧﺎک را ﮐﺎﻫﺶ ﻣﯽدﻫﺪ،ﺑﻪﻋﻨﻮان ﻧﻤﻮﻧﻪ ﻣﯿﺰان ﮐﺎﻫﺸ ﻤﯿﺎﻧﮕﯿﻦ ﻣﺮﺑﻊ ﺧﻄﺎ، ﺧﻄﺎی ﺟﺬر ﻣﯿﺎﻧﮕﯿﻦ ﻣﺮﺑﻌﺎت، ﺧﻄﺎی ﺟﺬر ﻣﯿﺎﻧﮕﯿﻦ ﻣﺮﺑﻌﺎت ﻧﺴﺒﯿﺎز ﻣﺪﻟﺒﺮﻧﺎﻣﻪرﯾﺰی ﺑﯿﺎن ژن ﺑﻪ روش ﺗﺮﮐﯿﺒﯽ ﺑﻪﺗﺮﺗﯿﺐ ﺑﺮاﺑﺮ ﺑﺎ 11/23،76/33و 10 درﺻﺪ اﺳﺖ. ﺑﺮآوردﻫﺎی phﺑﺎ روش ﺗﺮﮐﯿﺒﯽ در ﻣﺤﺪوده ﻗﻠﯿﺎﯾﯽ ﻣﯽﺑﺎﺷﺪ ﮐﻪ ﺑﺎ ﻣﻘﺎدﯾﺮ اﻧﺪازهﮔﯿﺮی ﺷﺪﻫﻬﻢ ﺧﻮاﻧﯽ دارد. ﮐﻤﯿﻨﻪ و ﺑﯿﺸﯿﻨﻪ ﻣﻘﺪار ﻗﺪر ﻣﻄﻠﻖ اﺧﺘﻼف ﺑﯿﻦ ﻣﻘﺎدﯾﺮ اﻧﺪازهﮔﯿﺮی و ﺗﺨﻤﯿﻨﯽ در ﻧﻘﺎط ﻣﻮردﺑﺮرﺳﯽ ﺑﻪﺗﺮﺗﯿﺐ در ﺑﻨﺎب 0/09 و ﻋﺠﺐﺷﯿﺮ 0/25 ﻣﯽﺑﺎﺷﺪ.ﻣﻌﯿﺎر ﻣﯿﺎﻧﮕﯿﻦ درﺻﺪ ﺧﻄﺎی ﻣﻄﻠﻖ در روش ﺗﺮﮐﯿﺒﯽ در ﻣﺤﺪوده ﻗﺎﺑﻞﻗﺒﻮل از ﻧﻈﺮ ﻋﻤﻠﮑﺮد اﺳﺖ و اﯾﻦ ﻣﺴﺌﻠﻪ ﮐﺎراﯾﯽ روش ﻣﻮرداﺳﺘﻔﺎده را در ﺑﺮآورد ﺗﻮزﯾﻊ ﻣﮑﺎﻧﯽ پﻫﺎﺷﺨﺎک ﻧﺸﺎن ﻣﯽ دﻫﺪ.

genetic algorithm application for soil phspatial distribution estimation with geostatistics and gene expression programmingcombination

awareness about spatial distribution of soil properties plays an important role in the system of crop growth and yield in the agricultural field. in this regard, genetic algorithm was used to increase the accuracy in spatial distribution of soil phwhich combines the estimates of linear regression, gene expression programming gep and geostatistics kriging interpolation with data related to some parts of east azerbaijan province bonab,maragheh and ajabshir . the linear model of kriging interpolation had the minimum error. gene expression programming and linear regression had the lowest and highest error for soil ph spatial distribution estimation, respectively, for example the mean square error, root mean square error, relative root mean square errordecreasing from linear regression to geostatistics was 47.67%,27.58%, 26.47% and scatter index and adopted mean absolute percentage error decreasing from linear regression to gep was 23.8% and 37.03%, respectively. the use of genetic algorithm in combination method reduced the error of spatial distribution compared to the tree types of models, for example mean square error, root mean square error, relative root mean square errordecreasing from gep to combination method was 23.33%, 11.76%,10%, respectively. the estimates of soil ph with combination method are in the alkaline range, which is consistent with the obtained data.  the minimum and maximum value of the absolute difference between measured and estimated data were at point in bonab 0.09 and ajabshir 0.25 , respectively. the mean absolute percentage error of combination method was in acceptable range and this shows the efficiency of combination method for soil ph spatial distribution estimation.