ﺑﺮرﺳﯽ ﺗﺄﺛﯿﺮ ﭘﯿﺶﭘﺮدازش دادهﻫﺎ و ﻋﻮاﻣﻞ ﻣﺪلﺳﺎزي ﺑﺮﻧﺎﻣﻪرﯾﺰي ﺑﯿﺎن ژن در دﻗﺖ ﭘﯿﺶﺑﯿﻨﯽ ﺳﺮي ﻫﺎي زﻣﺎﻧﯽ

Assessment effects of data preprocessing and modeling parameters of Gene Expression Programming on accuracy of time series forecasting

ﺳﺮي زﻣﺎﻧﯽ ﻫﯿﺪروﻟﻮژﯾﮏ ﻋﺎﻣﻠﯽ واﺑﺴﺘﻪ ﺑﻪ زﻣﺎن اﺳﺖ ﮐﻪ ﯾﺎﻓﺘﻦ ﻧﺤﻮه ﺗﻐﯿﯿﺮات و ﭘﯿﺶﺑﯿﻨﯽ آن ﻣﻬﻢ ﺗﺮﯾﻦ ﻫﺪف ﺗﺠﺰﯾﻪ وﺗﺤﻠﯿﻞ ﺳﺮي ﻫﺎي زﻣﺎﻧﯽ اﺳﺖ. ﻫﺪف اﯾﻦ ﺗﺤﻘﯿﻖ ﺑﺮرﺳﯽ ﻫﻢ زﻣﺎن ﺧﺼﻮﺻﯿﺎت ﺳﺮي زﻣﺎﻧﯽ و ﭘﯿﺶﭘﺮدازش آن ﻫﺎ و ﭘﺎراﻣﺘﺮﻫﺎي ﻣﻬﻢ ﻣﺪل ﺑﺮﻧﺎﻣﻪرﯾﺰي ﺑﯿﺎن ژن ﺟﻬﺖ ﭘـﯿﺶ ﺑﯿﻨـﯽ ﻫـﺎي ﺑـﺎ دﻗﺖ ﺑﺎﻻ در ﻣﺮاﺣﻞ آﻣﻮزش و ﺻﺤﺖﺳﻨﺠﯽ اﺳﺖ. در اﯾﻦ ﭘﮋوﻫﺶ ازﺳﺮي ﻫﺎي زﻣﺎﻧﯽ ﻋﻤﻖ آب زﯾﺮزﻣﯿﻨﯽ اﯾﺴﺘﮕﺎه دﺷﺖ ﭼﻤﭽﻤﺎل واﻗﻊ در اﺳﺘﺎن ﮐﺮﻣﺎﻧﺸﺎ ﺑﺎ دوره زﻣﺎﻧﯽ 12ﺳﺎﻟﻪ و اﻗﻠﯿﻢ ﮐﻮﻫﺴﺘﺎﻧﯽ و ﺳﺮي زﻣﺎﻧﯽ ﻣﺎﻫﺎﻧﻪ دﻣﺎي آﻻﺳﮑﺎ ﺑﺎ دوره زﻣﺎﻧﯽ 50ﺳﺎﻟﻪ و اﻗﻠﯿﻢ ﺳﺮد و ﺧﺸﮏ اﺳﺘﻔﺎده ﺷﺪه اﺳﺖ. ﺑـﺮاي ﻣـﺪل ﺳﺎزي ﺳﺮي ﻫﺎي زﻣﺎﻧﯽ ﻣﺬﮐﻮر از ﻧﺮم اﻓﺰار Genexprotools5.0 اﺳﺘﻔﺎده ﺷﺪه اﺳﺖ. ﻧﺘﺎﯾﺞ اﯾﻦ ﺗﺤﻘﯿﻖ، ﻧﺸﺎن داد ﺗﻨﺎوﺑﯽ ﺑﻮدن ﺧﺼﻮﺻﯿﺎت داده ﻣﻮﺟﻮد در ﺳﺮي زﻣﺎﻧﯽ دﻣﺎ، ﺳﺒﺐ ﺑﺮوز ﻧﺘﺎﯾﺞ ﻫﻤﺒﺴـﺘﮕﯽ ﺑـﺎﻻي 90% در ﻣﺮاﺣـﻞ ﻣﺨﺘﻠـﻒ آﻣﻮزش و ﺻﺤﺖ ﺳﻨﺠﯽ ﮔﺮدﯾﺪ ﺑﻪ ﻃﻮري ﮐﻪ اﺛﺮ ﭘﺎراﻣﺘﺮﻫﺎي ﻣﺨﺘﻠﻒ ﺑﯿﺎن ژن ﮐﻤﺘﺮ از 10درﺻﺪ در ﺑﻬﺒﻮد ﻧﺘﺎﯾﺞ اﺳﺖ. از ﺳﻮي دﯾﮕﺮ ﺑﺎ ﺑﺮرﺳﯽ ﺳـﺮ ي زﻣـﺎﻧ ﯽ ﻋﻤﻖ آب زﯾﺮزﻣﯿﻨﯽ ﮐﻪ ﻓﺎﻗﺪ ﺧﺼﻮﺻﯿﺖ ﺗﻨﺎوﺑﯽ و داراي ﺷﮑﻞACF ﻧﺰوﻟﯽ اﺳﺖ، ﻧﺘﺎﯾﺞ ﭘﯿﺶﺑﯿﻨﯽ ﻣﺪل GEP ﺑﺎ ﻫﺮ ﭘﺎراﻣﺘﺮ ﺗﺄﺛﯿﺮﮔﺬار ﺑﯿﺎن ژن، R ﺑـﯿﺶ از 44% در ﻣﺮﺣﻠﻪ ﺻﺤﺖ ﺳﻨﺠﯽ ﺣﺎﺻﻞ ﻧﺸﺪ. اﯾﻦ ﺑﺪان ﻣﻌﻨﯽ اﺳﺖ ﮐﻪ ﭘﯿﺶﭘﺮدازش ﺳﺮي زﻣﺎﻧﯽ اﺛﺮﮔﺬاري ﺑﯿﺸﺘﺮي در ﻧﺘﺎﯾﺞ ﭘﯿﺶﺑﯿﻨﯽ دارد. ﺑﻪ ﻃﻮري ﮐـﻪ ﺑـﺎ ﺣﺬف ﺗﺮم ﺗﻨﺎوب ﻧﺘﺎﯾﺞ ﭘﯿﺶﺑﯿﻨﯽ در ﻫﻤﻪ ﻣﺮاﺣﻞ ﻣﺪلﺳﺎزي ﺑﻪ ﻃﺮز ﻣﻌﻨﯽداري ﮐﺎﻫﺶ ﻣﯽﯾﺎﺑﺪ. در اﯾﻦ ﺣﺎﻟﺖ ﺑﻬﺘﺮﯾﻦ R ﺑـﺮاي ﻗﺴـﻤﺖ ﺻـﺤﺖ ﺳـﻨﺠﯽ 50 درصد است

Hydrological time-series is a time-dependent hydrological variable that finding the model of changes and predicting is the most important goal of time-series analysis. The purpose of this study is to simultaneously study the characteristics of time series and their prediction and the important parameters of the GEP for high-precision predictions in the training and validation. In this study, groundwater depth time-series of Chamchamal plain station located in Kermanshah province with a 12-year period and mountainous climate and the monthly time-series of Alaska temperature with a 50-year period and cold and dry climate have been used. Genexprotools5.0 software has been used to model time-series by GEP. The results of studying with GEP showed that the periodicity of data properties that existed in the time series of temperature caused correlation results above 90% in different stages of training and validation. So that the effect of different parameters of GEP is less than 10% in improving results. On the other hand, by examining the time-series of groundwater depth, which lacks periodicity and has a descending ACF shape, the prediction results of the GEP with any effective expression parameter, R more than 44% in the validation wasn't obtained. This means that the time-series preprocessing has a greater impact on the prediction results. So that by eliminating the semester, the prediction results in all stages of modeling are significantly reduced. In this case, the best R for the validation is 50%.