Search

Daily flow and suspended sediment discharge are two major hydrologıcal variables that affect rivers’ morphology and ecosystem, particularly during flood events. Artificial neural networks (ANNs) have been successfully used to model and predict these variables in recent studies. However, these are implicit and cannot be simply used in practice. In this paper, linear genetic programming (LGP) approach has been suggested to develop explicit models to predict these variables in two rivers in Iran. The explicit relationships (prediction rules) evolved by LGP take the form of equations or program codes, which can be checked for its physical consistency. The results showed that the LGP outperforms ANNs in terms of root mean squared error and coefficient of efficiency.

In this study an energy consumption modelling for long term (December 2006- March 2016) forecasting of monthly natural gas consumption in households and industry area for Yozgat city, Turkey was presented. In this context, it can be said that this paper has two purposes. One of them is the application and accuracy of the artificial neural networks. Estimate performances are compared with each other, and the estimates of the optimal models are evaluated with the monthly recorded natural gas consumption according to root mean square error, mean absolute error, and correlation coefficient. The other purpose of the study is to analysis trend of monthly natural gas consumption of Yozgat by using Mann-Kendall and a new method recently proposed by Şen. The results showed that the artificial neural networks gave satisfactory results in estimating monthly natural gas consumption. In the trend analysis, it was seen that both Mann-Kendall and Şen trend tests gave statistically significant increasing trend at 95% confidence level for monthly natural gas consumption of Yozgat.