چکیده:
ﻳﻜﻲ از ﻣﻬﻢﺗﺮﻳﻦ و ﭘﺮﻛﺎرﺑﺮدﺗﺮﻳﻦ ﻋﻼﺋﻢ ﭘﺎﺳﺦ ﻫﻴﺪروﻟﻮژﻳﻚ ﺣﻮزه، ﻣﻨﺤﻨﻲ ﺗﺪاوم ﺟﺮﻳﺎن اﺳﺖ و در ﻛﺎرﺑﺮد ﻫﺎی ﻫﻴﺪروﻟﻮژﻳﻜﻲ ﺑﻲ ﺷﻤﺎری ﺑﺮای آﻧﺎﻟﻴﺰ ﻓﺮاواﻧﻲ ﺟﺮﻳﺎنﻫﺎی ﻛﻤﻴﻨﻪ و ﺳﻴﻼب ﻣﻮرد اﺳﺘﻔﺎده ﻗﺮار ﻣﻲﮔﻴﺮد. ﺑﺮای ﻧﻤﺎﻳﺶ ﻣﺤﺪودة ﻛﺎﻣﻞ دﺑﻲ رودﺧﺎﻧﻪ، از ﺟﺮﻳﺎن ﻫﺎی ﺣﺪاﻗﻞ ﺗﺎ ﺣﺪاﻛﺜﺮ ﺳﻴﻼب و ﻣﻨﺤﻨﻲ ﺗﺪاوم ﺟﺮﻳﺎن ) (FDCاﺳﺘﻔﺎده ﻣﻲ ﺷﻮد؛ ﺑﻨﺎﺑﺮاﻳﻦ اﺳﺘﺨﺮاج دﻗﻴﻖ اﻳﻦ ﻣﻨﺤﻨﻲ ﻫﺎ ﺑﺎ ﺣﺪاﻗﻞ ﺧﻄﺎ ﺣﺎﺋﺰ اﻫﻤﻴﺖ ﻓﺮاواﻧﻲ اﺳﺖ. در اﻳﻦ ﻣﻄﺎﻟﻌﻪ ﻛﺎراﻳﻲ ﻣﺪل درﺧﺘﻲ M5 در اﺳﺘﺨﺮاج ﻣﻨﺤﻨﻲ ﺗﺪاوم ﺟﺮﻳﺎن در ﻣﻘﺎﻳﺴﻪ ﺑﺎ ﺷﺒﻜﺔ ﻋﺼﺒﻲ ﻣﺼﻨﻮﻋﻲ و ﻣﺎﺷﻴﻦ ﺑﺮدار ﭘﺸﺘﻴﺒﺎن ﺑﺮای اﻳﺴﺘﮕﺎه ﺧﺰاﻧﮕﺎه رودﺧﺎﻧﺔ ارس واﻗﻊ در اﺳﺘﺎن آذرﺑﺎﻳﺠﺎن ﺷﺮﻗﻲ ﺑﺮرﺳﻲ ﺷﺪ. ﺑﺎ ﺗﻮﺟﻪ ﺑﻪ ﻧﺘﺎﻳﺞ ﺑﻪ دﺳﺖ آﻣﺪه در ﻣﺪل درﺧﺘﻲ M5، ﺗﺮﻛﻴﺐ 80 دادهﻫﺎ ﺑﺮای آﻣﻮزش و ﻣﺎﺑﻘﻲ ﺑﺮای ﺗﺴﺖ ﻣﺪل، ﺑﻬﺘﺮﻳﻦ ﻋﻤﻠﻜﺮد را در اراﺋﺔ ﻣﻨﺤﻨﻲ ﺗﺪاوم ﺟﺮﻳﺎن ﺑﺎ RMSE=5/47(m3/s) ،R2=0/992 و (MAE=4/38 (m3/s ﻧﺸﺎن داد. ﺑﺎ ﺑﺮرﺳﻲ ﻧﺘﺎﻳﺞ ﻣﺪل ﻫﺎی ﻣﺨﺘﻠﻒ ﺷﺒﻜﺔ ﻋﺼﺒﻲ، ﺑﻬﺘﺮﻳﻦ ﻣﺪل ﺑﺎ 2 ﻧﺮون ﺑﺮای ﻻﻳﻪ ﻣﺨﻔﻲ ﺑﺎ ﻣﻘﺎدﻳﺮ RMSE=3/91 (m3/s) ،R2=0/997 و (MAE=3/30 (m3/s ﺑﻪ دﺳﺖ آﻣﺪ. ﺑﺮرﺳﻲ ﻋﻤﻠﻜﺮد ﻛﺮﻧﻞ RBF ﻣﺪل ﻣﺎﺷﻴﻦ ﺑﺮدار ﭘﺸﺘﻴﺒﺎن ﻧﺸﺎن داد ﻛﻪ اﻳﻦ ﻣﺪل ﺑﻬﺘﺮﻳﻦ ﻋﻤﻠﻜﺮد را در ﺷﺒﻴﻪ ﺳﺎزی ﻣﻨﺤﻨﻲ ﺗﺪاوم ﺟﺮﻳﺎن داﺷﺖ؛ ﺑﻪ ﻃﻮری ﻛﻪ دارای ﺣﺪاﻗﻞ ﻣﻘﺪار ﻣﺠﺬور ﻣﻴﺎﻧﮕﻴﻦ ﻣﺮﺑﻊ ﻫﺎی ﺧﻄﺎ (RMSE=2/98 (m3/s، ﺑﺎﻻﺗﺮﻳﻦ ﺿﺮﻳﺐ ﻫﻤﺒﺴﺘﮕﻲ R2=0/998 و ﻛﻤﺘﺮﻳﻦ ﻣﻘﺪار ﺧﻄﺎی ﻧﺴﺒﻲ(MAE=2/66 (m3/s ﺑﻮد. ﻣﻘﺎﻳﺴﺔ ﻧﺘﺎﻳﺞ ﺑﻴﻦ اﻧﻮاع ﻣﺪل ﻫﺎی ﻫﻮﺷﻤﻨﺪ ﻣﻮرد ﺑﺮرﺳﻲ، ﺑﻴﺎﻧﮕﺮ اﻳﻦ اﺳﺖ ﻛﻪ ﻫﺮ ﺳﻪ ﻣﺪل در ﺗﺨﻤﻴﻦ ﻣﻘﺎدﻳﺮ دﺑﻲ ﻣﻨﺤﻨﻲ ﺗﺪاوم ﺟﺮﻳﺎن ﻋﻤﻠﻜﺮد ﻣﻨﺎﺳﺒﻲ دارﻧﺪ؛ اﻣﺎ ﻣﺪل درﺧﺘﻲ M5 ﺑﻪ ﻋﻠﺖ ﺳﺎدﮔﻲ ﻣﺤﺎﺳﺒﺎت و اراﺋﺔ رواﺑﻂ ﺷﺪه، ﺑﻪ ﻟﺤﺎظ ﻛﺎرﺑﺮدی ﻗﺎﺑﻠﻴﺖ ﺑﻴﺸﺘﺮی ﻣﻲﺗﻮاﻧﺪ در اﺳﺘﺨﺮاج ﻣﻨﺤﻨﻲ ﺗﺪاوم داﺷﺘﻪ ﺑﺎﺷﺪ.
Flow duration curve is one of the most important and applicable signals of hydrologic response of a basin. This curve was used for analyzing the frequency of low and flood flows of a river in many hydrologic uses. Also, the flow duration curve (FDC) was used to display the complete domain of river discharge from minimum up to maximum flood. Therefore, accurate derivation of this curves with the least error is necessary. In this study, applicability of M5 Tree Model in derivation of flow duration curve in Khazangah station located on Aras River, East Azerbaijan province was investigated and compared with the results of Artificial Neural Network (ANN) and Support Vector Machine (SVM) models. The results of M5Tree Model showed competition of 80 percent of data for training and the remaining for the testing has the best performance in presenting the flow duration curve with values of R2=0.992, RMSE=5.47 m3/s and MAE=4.38 m3/s. The results of different structures of Neural Network showed the best model (2 neurons for hidden layer) was obtained with values of R2=0.997, RMSE=3.91 m3/s and MAE=3.30 m3/s. Also the performance of RBF kernel of Support Vector Machine Showed this model has the best ability in simulation of flow duration curve, so that this model has lowest error values of RMSE=2.98 m3/s, MAE=2.66 m3/s and highest value of R2=0.998.
Comparison the results between the intelligence models showed that each three models have proper performance in determining the discharge values of flow duration curve. From the practical view, M5Tree Model has more applicability in derivation of flow duration curve because of the simplicity of the proposed equations and calculations.