Showing 3 results for Artificial Neural Network
Arash Malekian, Mahro Dehbozorgi, Amir Hoshang Ehsani,
Volume 15, Issue 36 (6-2015)
Abstract
Drought is one of the most destructive natural disasters in human societies that cause irreparable impacts on agriculture, environment, society and economics. So, awareness of occurrence of droughts can be effective in reducing losses. In this study, in order to modeling and forecasting drought severity in a 37 year time period (1971-2007) in 21 meteorological stations, located in the cold semi-arid region of north-west Iran, artificial neural networks was used. The input data was annual rainfall data and annual drought precipitation index for all stations that 80% of the data (1971-2000) used for training the network and other 20% (2001-2007) used for testing it and in the next step drought severity predicted for the years 2008 to 2012 by the trained algorithm without using actual and existed data in this period. The appropriate structure for the network, based on Multi Layer Perceptron with three hidden layer, Back Propagation algorithm, Sigmoid transfer function and 10 neurons in middle layer. The results show that the artificial neural networks are well able to predict the non-linear relationship between rainfall and drought as it can simulate drought precipitation index values largely consistent with the real values with more than 97% regression and less than 5% error. So, drought can be predicted by this method in future and also it is useful in water resources management, drought management and climate change.
, ,
Volume 17, Issue 47 (12-2017)
Abstract
Suspended particles management is one of the important issues in controlling the air pollution of cities. These particles cause and develop heart and respiratory diseases in people. Mashhad is considered as one of the main and populous cities of Iran. Because of its climatic conditions and its tourism, the city is at the highest risk of this type of pollution. We attempted to use the multi-layer perceptron (MLP) artificial neural network and a Markov chain model to predict PM10 concentrations the city. We applied hourly data of CO, SO2, PM2.5 and temperature in late March and April 2015. Out of 1488 data series, 1300 data were used for network training and 188 data were used for validation. The results indicated the optimal performance of these methods in predicting of the amount of pollutants and also the probability of occurrence of hours with different quality of contamination. The best MLP artificial neural network model predicted the amount of pollutant particles with a coefficient of determination (R2) 0.88, index of agreement of 0.91 and a mean square error of 2.26. Also, the Markov model with average absolute error predicted about 0.1 percent of the probability of transferring the condition and the continuation of different states of air pollution caused by suspended particles.
Dr Javad Sadidi, Dr Hani Rezayan, Mr Mohammad Reza Barshan,
Volume 17, Issue 47 (12-2017)
Abstract
Due to the complexity of air pollution action, artificial intelligence models specifically, neural networks are utilized to simulate air pollution. So far, numerous artificial neural network models have been used to estimate the concentration of atmospheric PMs. These models have had different accuracies that scholars are constantly exceed their efficiency using numerous parameters. The current research aims to compare Elman and Jordan recurrent networks for error distribution and validation to estimate atmospheric particular matters concentration in Ahvaz city. The used parameters are relative humidity, air pressure, and temperature and aerosol optical depth. The latter one is extracted from MODIS sensor images and air pollution monitoring stations. The results show that Jordan model with RMSE of 219.9 milligram per cubic meter has more accuracy rather than Elman model with RMSE of 228.5. The value of R2 index that shows the linear relation between the estimated from the model and observed values for Jordan is equal to 0.5 that implies 50% estimation accuracy. The value is because of MODIS spatial resolution, inadequacy in numbers as well as spatial distribution of meteorological station inside the study area. According to the results of the current research, it seems that air pollution monitoring stations have to increase in terms of numbers and suitable spatial distribution. Also, other ancillary data like volunteer geographic air pollution data entry using mobile connected cheap sensors as portable stations may be used to implement more accurate simulation for air pollution.
