Application of Wavelet Neural Network in Estimation of Average Air-temperature
Standard weather station evaluates air-temperature and it is major descriptor for earth environment condition. Thus, estimation and estimation of average daily temperature is one of the main perquisites for agriculture programming and also water source management which is possible by empirical, quas...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Gorgan University of Agricultural Sciences and Natural Resources
2022-07-01
|
| Series: | Environmental Resources Research |
| Subjects: | |
| Online Access: | https://ijerr.gau.ac.ir/article_6612_69a13d98246cbc78a96ec669d2db352f.pdf |
| _version_ | 1797311406570209280 |
|---|---|
| author | reza dehghani fatemeh dehghani |
| author_facet | reza dehghani fatemeh dehghani |
| author_sort | reza dehghani |
| collection | DOAJ |
| description | Standard weather station evaluates air-temperature and it is major descriptor for earth environment condition. Thus, estimation and estimation of average daily temperature is one of the main perquisites for agriculture programming and also water source management which is possible by empirical, quasi-empirical l and intelligent method. This study evaluates the application wavelet neural network (WNN) to estimation of average daily air-temperature in Sari weather station and also compares its efficiency with artificial neural network (ANN). It was used thermograph data of Sari weather station for modeling. Relative humidity, maximum temperature, minimum temperature, wind velocity and daily evaporation were considered as network input and air-temperature was considered as network output during 2010 to 2020 years. Criteria including correlation coefficient, root mean square error (RMSE), Nash-Sutcliffe (NS) coefficient were used to evaluate and comparison of models efficiency. Results showed that WNN model had better performance rather than ANN for modeling, so that WNN model showed the most coefficient of determination (0.999), RMSE (0.001) and NS (0.998) which was initiated in accuracy stage. In conclusion, results showed higher precision of WNN model in estimation air-temperature. |
| first_indexed | 2024-03-08T01:58:11Z |
| format | Article |
| id | doaj.art-c781a159bd3c46c2ab8d38fd99be0cc5 |
| institution | Directory Open Access Journal |
| issn | 2783-4832 2783-4670 |
| language | English |
| last_indexed | 2024-03-08T01:58:11Z |
| publishDate | 2022-07-01 |
| publisher | Gorgan University of Agricultural Sciences and Natural Resources |
| record_format | Article |
| series | Environmental Resources Research |
| spelling | doaj.art-c781a159bd3c46c2ab8d38fd99be0cc52024-02-14T08:34:18ZengGorgan University of Agricultural Sciences and Natural ResourcesEnvironmental Resources Research2783-48322783-46702022-07-0110229130010.22069/ijerr.2023.20800.13866612Application of Wavelet Neural Network in Estimation of Average Air-temperaturereza dehghani0fatemeh dehghani1PhD. Water Engineering, Faculty of Agriculture, Lorestan University, IranB.Sc. student, Civil engineering, Lorestan University, IranStandard weather station evaluates air-temperature and it is major descriptor for earth environment condition. Thus, estimation and estimation of average daily temperature is one of the main perquisites for agriculture programming and also water source management which is possible by empirical, quasi-empirical l and intelligent method. This study evaluates the application wavelet neural network (WNN) to estimation of average daily air-temperature in Sari weather station and also compares its efficiency with artificial neural network (ANN). It was used thermograph data of Sari weather station for modeling. Relative humidity, maximum temperature, minimum temperature, wind velocity and daily evaporation were considered as network input and air-temperature was considered as network output during 2010 to 2020 years. Criteria including correlation coefficient, root mean square error (RMSE), Nash-Sutcliffe (NS) coefficient were used to evaluate and comparison of models efficiency. Results showed that WNN model had better performance rather than ANN for modeling, so that WNN model showed the most coefficient of determination (0.999), RMSE (0.001) and NS (0.998) which was initiated in accuracy stage. In conclusion, results showed higher precision of WNN model in estimation air-temperature.https://ijerr.gau.ac.ir/article_6612_69a13d98246cbc78a96ec669d2db352f.pdfair-temperatureartificial neural networkestimationsariwavelet neural network |
| spellingShingle | reza dehghani fatemeh dehghani Application of Wavelet Neural Network in Estimation of Average Air-temperature Environmental Resources Research air-temperature artificial neural network estimation sari wavelet neural network |
| title | Application of Wavelet Neural Network in Estimation of Average Air-temperature |
| title_full | Application of Wavelet Neural Network in Estimation of Average Air-temperature |
| title_fullStr | Application of Wavelet Neural Network in Estimation of Average Air-temperature |
| title_full_unstemmed | Application of Wavelet Neural Network in Estimation of Average Air-temperature |
| title_short | Application of Wavelet Neural Network in Estimation of Average Air-temperature |
| title_sort | application of wavelet neural network in estimation of average air temperature |
| topic | air-temperature artificial neural network estimation sari wavelet neural network |
| url | https://ijerr.gau.ac.ir/article_6612_69a13d98246cbc78a96ec669d2db352f.pdf |
| work_keys_str_mv | AT rezadehghani applicationofwaveletneuralnetworkinestimationofaverageairtemperature AT fatemehdehghani applicationofwaveletneuralnetworkinestimationofaverageairtemperature |