عنوان مقاله :
ﺗﺨﻤﯿﻦ ﺑﺎرش درازﻣﺪت ﺷﻬﺮ ﺑﺎﺑﻠﺴﺮ ﺑﺎ اﺳﺘﻔﺎده از ﺑﺮﻧﺎﻣﻪرﯾﺰي ﺑﯿﺎن ژن ﺑﻬﯿﻨﻪﯾﺎﻓﺘﻪ
عنوان به زبان ديگر :
Estimation of Long-Term Rainfall in Babolsar City by Using the Optimized Gene Expression Programming
پديد آورندگان :
اﺳﻤﺎﻋﯿﻠﯽ، ﯾﻮﺳﻒ داﻧﺸﮕﺎه آزاد اﺳﻼﻣﯽ واﺣﺪ ﮐﺮﻣﺎﻧﺸﺎه - ﮔﺮوه ﻣﻬﻨﺪﺳﯽ آب، ﮐﺮﻣﺎﻧﺸﺎه، اﯾﺮان , رجبي، احمد داﻧﺸﮕﺎه آزاد اﺳﻼﻣﯽ واﺣﺪ ﮐﺮﻣﺎﻧﺸﺎه - ﮔﺮوه ﻣﻬﻨﺪﺳﯽ آب، ﮐﺮﻣﺎﻧﺸﺎه، اﯾﺮان , ﯾﻮﺳﻔﻮﻧﺪ، ﻓﺮﯾﺒﺮز داﻧﺸﮕﺎه آزاد اﺳﻼﻣﯽ واﺣﺪ ﮐﺮﻣﺎﻧﺸﺎه - ﮔﺮوه ﻣﻬﻨﺪﺳﯽ آب، ﮐﺮﻣﺎﻧﺸﺎه، اﯾﺮان , ﺷﻌﺒﺎﻧﻠﻮ، ﺳﻌﯿﺪ داﻧﺸﮕﺎه آزاد اﺳﻼﻣﯽ واﺣﺪ ﮐﺮﻣﺎﻧﺸﺎه - ﮔﺮوه ﻣﻬﻨﺪﺳﯽ آب، ﮐﺮﻣﺎﻧﺸﺎه، اﯾﺮان
كليدواژه :
ﺑﺎرش ﺷﻬﺮ ﺑﺎﺑﻠﺴﺮ , ﺑﺮﻧﺎﻣﻪ رﯾﺰي ﺑﯿﺎن ژن , ﺗﺒﺪﯾﻞ ﻣﻮﺟﮏ , ﺳﺮي زﻣﺎﻧﯽ و ﻣﺪلﺳﺎزي
چكيده فارسي :
تخمين و شبيه سازي بارندگي يكي از مهمترين حوزههاي علم هيدرولوژي محسوب ميشود. در اين مطالعه، براي اولين بار بارش دراز مدت شهر بابلسر در يك بازه 68 ساله از سال 1951 تا 2019 به صورت ماهانه توسط يك مدل هوش مصنوعي تركيبي بهينه يافته پيشبيني شد. براي انجام اينكار، مدل برنامه ريزي بيان ژن (GEP) با تبديل موجك (WT) تركيب شدند. براي آموزش مدلهاي هوش مصنوعي از 70 درصد مقادير مشاهداتي و براي آزمون آنها از 30 درصد باقيمانده استفاده گرديد. همچنين، با استفاده از تابع خود همبستگي (ACF) تاخيرهاي موثر دادههاي سري زماني شناسايي شدند و با استفاده از آنها، شش مدل GEP مختلف توسعه داده شدند. تعداد ژن هاي بهينه سازي شده مدل GEP مساوي با چهار انتخاب گرديد. علاوه بر اين تابع Multiplication بهعنوان بهترين تابع اتصال مدل GEP معرفي گرديد. مدل برتر GEP با انجام يك تحليل حساسيت معرفي شد كه مقادير ضريب همبستگي (R) و شاخص پراكندگي (SI) آن بهترتيب مساوي با 0/571 و 0/792 محاسبه شدند. تاخيرهاي شماره (t-1)، (t-2)، (t-12) و (t-24) به عنوان ﻣﻮﺛﺮﺗﺮﯾﻦ ﺗﺎﺧﯿﺮﻫﺎي دادهﻫﺎي ﺳﺮي زﻣﺎﻧﯽ ﻣﻌﺮﻓﯽ ﺷﺪﻧﺪ. ﻻزم ﺑﻪ ذﮐﺮ اﺳﺖ ﮐﻪ در ﺑﯿﻦ ﻣﻮﺟﮏﻫﺎي ﻣﺎدر ﻣﺨﺘﻠﻒ، coif ﺑﻪﻋﻨﻮان ﻣﻮﺟﮏ ﻣﺎدر ﺑﺮﺗﺮ ﻣﻌﺮﻓﯽ ﺷﺪ و ﺳﭙﺲ ﺑﺎ ﻣﺪل GEP ﺗﺮﮐﯿﺐ ﮔﺮدﯾﺪ. ﻣﺪل ﺗﺮﮐﯿﺒﯽ WGEP ﻣﻘﺎدﯾﺮ ﺑﺎرشﻫﺎ را ﺑﺎ دﻗﺖ ﻗﺎﺑﻞ ﻗﺒﻮﻟﯽ ﺷﺒﯿﻪﺳﺎزي ﮐﺮد. ﺑﻪ ﻋﺒﺎرت دﯾﮕﺮ، ﺗﺒﺪﯾﻞ ﻣﻮﺟﮏ دﻗﺖ ﻣﺪل ﺳﺎزي را ﺑﻪ ﺷﮑﻞ ﻣﺤﺴﻮﺳﯽ ﺑﻬﺒﻮد ﺑﺨﺸﯿﺪ. ﺑﻪﻋﻨﻮان ﻣﺜﺎل ﻣﻘﺪار ﺷﺎﺧﺺ ﻋﻤﻠﮑﺮد )VAF( ﺑﺮاي ﻣﺪل GEP و WGEP ﺑﻪﺗﺮﺗﯿﺐ ﻣﺴﺎوي ﺑﺎ 31/710 و 82/064 ﺑﻮدﻧﺪ.
چكيده لاتين :
Estimation and simulation of precipitation is considered as one of the most
issues in the field of hydrology. In this study, for the first time, the longterm
rainfall in Babolsar city during a 68 years period from 1951 to 2019
was predicted by using an optimized hybrid artificial intelligence (AI)
technique. To end this, the gene expression programming (GEP) model
was combined with the wavelet transform. To training the AI models, 70%
of the observed values were utilized and 30% of these values were used
to testing those models. Additionally, the autocorrelation function (ACF)
was applied to identify the most influential lags and then six GEP models
were developed by means of these detected lags. The number of optimized
genes was selected to be four. In addition, the Multiplication function was
introduced as the best linking function of the GEP model. The superior
GEP model was introduced through a sensitivity analysis that the
correlation coefficient (R) and scatter index (SI) for this model were
calculated to be 0.571 and 0.792, respectively. The (t-1), (t-2), (t-12), and
(t-36) time series lags were introduced as the most effective input lags.
The coif was detected as the best mother wavelet to simulate the target
function. The hybrid WGEP model simulated the values of rainfall with
acceptable accuracy. In the other words, the wavelet transform enhanced
the performance of the GEP model significantly. For instance, the value
of variance accounted for (VAF) for the GEP and WGEP models were
respectively computed to be 31.710 and 82.064
عنوان نشريه :
مهندسي آبياري و آب ايران
