+ Site Statistics
+ Search Articles
+ PDF Full Text Service
How our service works
Request PDF Full Text
+ Follow Us
Follow on Facebook
Follow on Twitter
Follow on LinkedIn
+ Subscribe to Site Feeds
Most Shared
PDF Full Text
+ Translate
+ Recently Requested

The Use of Artificial Neural Networks (Ann) for Prediction of Time SERIES MONTHLY AIR TEMPERATURE AND ASSESSMENT OF DIFFERENT NEURON NUMBERS ON THE PREDICTION ACCURACY



The Use of Artificial Neural Networks (Ann) for Prediction of Time SERIES MONTHLY AIR TEMPERATURE AND ASSESSMENT OF DIFFERENT NEURON NUMBERS ON THE PREDICTION ACCURACY



Fresenius Environmental Bulletin 24(10A): 3258-3265



Artificial Neural Networks (ANN) can successfully model the complex relationships that may exist within a data set. Fundamental processing units of ANN are non-linear computational neurons. Initially, it has been used in mathematical modeling studies of neurons in the human brain but recently, it has been used in various branches such as physics, mathematics, electric and computer engineering and agriculture as a research topic. In this study, the processing structure of ANN has been shown with an application on the estimation of long term monthly temperature data (from 1950 to 2011) of Sanliurfa province located between Euphrates and Tigris rivers, as part of the so called Fertile Cresent, and also a very important agricultural center of Turkey. The data was splitted into two parts; one from 1950 to 2006, used as training data to calibrate the ANN model while the remaining part of the data set, from 2006 to 2011 was utilized as test set for the validation of the constructed model. The model performance was compared using different numbers of neurons (75, 90, 110, 120, 125, 150, 175). Accuracies of the models with different number of neurons were evaluated using indices such as R-2, MSE, RMSE and MAPE. Overall, the study results showed that ANN can be successfully used for the estimation of long term climate data. The best results were obtained with neuron numbers of 120 giving the best fit between estimated and actual observation of annual monthly temperature, providing higher R-2 and lowest MSE, RMSE and MAPE values.

Please choose payment method:






(PDF emailed within 1 workday: $29.90)

Accession: 066307644

Download citation: RISBibTeXText


Related references

Time series prediction of morbidity using artificial neural networks. Meditsinskaia Tekhnika 2013(1): 35-38, 2013

Assessing the quality of eight different maximum temperature time series as inputs when using artificial neural networks to forecast monthly rainfall at Cape Otway, Australia. Atmospheric Research 166: 141-149, 2015

Prediction of rainfall time series using modular artificial neural networks coupled with data pre-processing techniques. Journal of Hydrology 389.1-2, 2010

Software Design Challenges in Time Series Prediction Systems Using Parallel Implementation of Artificial Neural Networks. Thescientificworldjournal 2016: 6709352, 2016

Urban Residential Water Demand Prediction Based on Artificial Neural Networks and Time Series Models. Water Resources Management 29(10): 3651-3662, 2015

Prediction of rainfall time series using modular artificial neural networks coupled with data-preprocessing techniques. Journal of Hydrology 389(1-2): 146-167, 2010

Prediction of monthly mean daily diffuse solar radiation using artificial neural networks and comparison with other empirical models. Energy Policy 36(10): 3833-3837, 2008

Suspect screening of large numbers of emerging contaminants in environmental waters using artificial neural networks for chromatographic retention time prediction and high resolution mass spectrometry data analysis. Science of the Total Environment 538: 934-941, 2015

Artificial neural networks improve the accuracy of cancer survival prediction. Cancer 79(4): 857-862, 1997

Complex Rotation Quantum Dynamic Neural Networks (CRQDNN) using Complex Quantum Neuron (CQN): Applications to time series prediction. Neural Networks 71: 11-26, 2015

Prediction of wax disappearance temperature using artificial neural networks. Journal of Petroleum Science and Engineering 108: 74-81, 2013

Dewpoint temperature prediction using artificial neural networks. Journal of Applied Meteorology and Climatology 47(6): 1757-1769, 2008

Prediction of soil temperature using artificial neural networks. Journal of Agrometeorology 3(1/2): 169-173, 2001

Time Series Prediction and Neural Networks. Journal of Intelligent and Robotic Systems 31(1-3): 91-103, 2001

Artificial neural networks for prediction of antibacterial activity in series of imidazole derivatives. Combinatorial Chemistry and High Throughput Screening 7(4): 327-336, 2004