Mojtaba Nassaji zavareh; Bagher Ghermezcheshmeh; Fatemeh Rahimzadeh
Abstract
Daily constant discharges are needed estimating daily discharge in the hydrological model. The different number of statistical years, statistical deficiencies, and measurement error leads to the formation of time series with an uncommon time base. Hence the reconstruction of daily discharge data is of ...
Read More
Daily constant discharges are needed estimating daily discharge in the hydrological model. The different number of statistical years, statistical deficiencies, and measurement error leads to the formation of time series with an uncommon time base. Hence the reconstruction of daily discharge data is of paramount importance. In this research, daily discharge was reconstructed in two stages in one of the upstream of Karoun River. In both stages of research, daily discharge data from two upstream stations were used to reconstruct daily discharge of the downstream station using artificial neural networks, neuro-fuzzy and two variables regression methods. In the second stage, the magnitudes of discharge, based on dry, normal and wet years was used to reconstruct the daily discharge. The results showed higher accuracy in the artificial neural network and neuro-fuzzy methods compared to two variable regression methods in the reconstruction of daily discharge. Multi-layer perceptron model has better potential among all different method of artificial neural network and neuro-fuzzy models. Classification of discharge into dry, normal, and wet years decreases error in the reconstruction of daily discharge. Based on the mean relative error (MRE), error in reconstruction of daily discharge is the least in normal, wet, and dry years, respectively
Zakariya Asadolahi; Mahdi Vafakhah; Seyed Hamidreza Sadeghi
Abstract
Todays, dynamic models are supposed as the most important tools in erosion and sediment phenomenadue to their complexities and existence of many affecting factors. Towards, the present study wasconducted in the Kojour watershed for daily sediment modeling using daily rainfall, discharge andsediment during ...
Read More
Todays, dynamic models are supposed as the most important tools in erosion and sediment phenomenadue to their complexities and existence of many affecting factors. Towards, the present study wasconducted in the Kojour watershed for daily sediment modeling using daily rainfall, discharge andsediment during 2007 to 2010. The modeling process was carried out all data and the monthly andseasonally classification data in linear and nonlinear models. The results indicated that daily linear andnon-linear models did not indicate a suitable model. The monthly and seasonally classification of thedata led to achievement of better models with determination coefficient significant at 5 percent leveland relative error less than 40 percent as compared with those obtained from no classification. It wasalso found out that daily sediment of Kojour watershed was affected by discharge occurred event dayand before four days. The discharge occurred event day is the most effective factor in 80% selectedmodels in the study watershed. The nonlinear models were better estimation than linear models inJuly, September, December and March and autumn but linear models were better than nonlinearmodels in other months and seasons.