Comparing the performance of Artificial Neural Network (ANN) to predict the long term Meteorological Drought using Climatic Parameters and teleconnection (case study: South of Qazvin Province)
Volume 70, Issue 4, Winter 2018, Pages 1015-1030
https://doi.org/10.22059/jrwm.2018.122721.862
Fatemeh Maghsoud, Mohammad Reza Yazdani, Mohammad Rahimi, Arash Malekian, ali asghar zolfaghari
Abstract Overview, drought is effected an unusual dry period which is enough continued and causes imbalance in the hydrologic status, as depletion of surface water and groundwater resources. The purpose of this research is modeling meteorological drought prediction using Neural Network- Multi layer Perceptron, parameters and climatic signals in three time scales include short, middle and long term in a rain-gauge station located at south plain of Qazvin Province. Three different scenarios were tested as inputs model. Optimal combination of variables was determinate by Gamma-Test after identification of input variables using cross-correlation. Results showed, influence of climatic signals increased and against the influence of meteorological parameters decreased when time scale were increased from short-term to long-term. MEI (Multivariate ENSO Index) and rainfall were introduced as the most effective climatic signals and meteorological parameter for each scale, respectively. Neural Network modeling which has hidden layer with enough neurons, Sigmoid Function in middle layer and linear function at output layer was used. The most appropriate of the number neurons was determined in each scenario and wasn’t observed significant correlation between increasing or decreasing the error and number of neurons. Finally, the most appropriate network structure was determined based on evaluation indexes in three scenarios and each time scale.
Application of Artificial Neural Networks in Simulating and Forecasting of Meteorological Drought Decile Percentage Index (Case study: Sistan & Balouchestan Province)
Volume 67, Issue 1, Spring 2014, Pages 127-139
https://doi.org/10.22059/jrwm.2014.50834
Arash Malekian, Mahrou Dehbozorgi, Amir Houshang Ehsani, Amir Reza Keshtkar
Abstract Consecutive droughts in Sistan and Baloochestan province cause water resources restriction and this is
a very significant problem for this region. In this study, in order to forecast the drought cycle in 9
climatological stations in the province, we used Artificial Neural Networks. The input data were
average of annual rainfall data in all stations and also deciles precipitation index, which the first 30
years from 1971 to 2000 used for training the network and the last 8 years from 2001 to 2008 for
simulating it. The network consists of Multilayer Perceptron (MLP) and Back Propagation Algorithm
(BP) and also sigmoid transfer function. Number of Neurons in hidden layer was 10 with 1-10-1
structure and was calculated based on the lowest RMSE. Then drought prediction was done in neural
network with the trained algorithm and without using actual and observed data in 2009 to 2012.
Results showed that, the network was able to simulate and forecast DPI index with 97% regression
and average RMSE error less than 5%. According to drought indices, results showed that the drought
will have an increasing trend in all stations in this region in 2009 to 2011. Therefore, by using this
method, drought can be predicted in later years without any need to have actual meteorological data
and also can be used in water resources management, drought management and climate changes.