Neural Network and Regression Methods for Estimation of the Average Daily Temperature of Hyderabad for the Years 2018-2020
A qualitative study on temperature distribution has been executed in Hyderabad by several researchers. This study, however, is the first attempt to study temperature distribution quantitatively. Two different methods, i.e., Artificial Neural Network (ANN) and Regression Analysis (RA), have been used...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Society of Economic Geologists and Mineral Technologists
2021-07-01
|
| Series: | International Journal of Economic and Environment Geology |
| Subjects: | |
| Online Access: | https://www.econ-environ-geol.org/index.php/ojs/article/view/592 |
| _version_ | 1819161009942691840 |
|---|---|
| author | Adeel Tahir Mamnoon Akhtar Zaheer Ud Din Muhammad Sarim |
| author_facet | Adeel Tahir Mamnoon Akhtar Zaheer Ud Din Muhammad Sarim |
| author_sort | Adeel Tahir |
| collection | DOAJ |
| description | A qualitative study on temperature distribution has been executed in Hyderabad by several researchers. This study, however, is the first attempt to study temperature distribution quantitatively. Two different methods, i.e., Artificial Neural Network (ANN) and Regression Analysis (RA), have been used to determine the average daily temperature distribution for Hyderabad, a city in Pakistan. Both the methods are used to predict the average daily temperature of the years; 2018, 2019, and 2020. In Neural Network (NN) analysis, the network was trained and validated for three years with temperature recorded from 2015-2017. With the help of training and validation parameters of the hidden layer, the average daily temperature was predicted for 2018-2020. Based on input parameters (dew point, relative humidity, and wind speed), a multiple regression model was developed, and average daily
temperature for the years 2018-2020 was predicted again. For validation of the model statistical errors, Root Mean Square Error (RMSE), Mean Absolute Error (MABE), Mean Absolute Percent Error (MAPE), and coefficient of determination are calculated. The statistical errors show that multiple regression models and neural network models provide a good prediction of temperature distribution. However, the results of the neural network are better than the regression model. |
| first_indexed | 2024-12-22T17:05:32Z |
| format | Article |
| id | doaj.art-24b1086faf6d47f6924da2bde631a373 |
| institution | Directory Open Access Journal |
| issn | 2223-957X |
| language | English |
| last_indexed | 2024-12-22T17:05:32Z |
| publishDate | 2021-07-01 |
| publisher | Society of Economic Geologists and Mineral Technologists |
| record_format | Article |
| series | International Journal of Economic and Environment Geology |
| spelling | doaj.art-24b1086faf6d47f6924da2bde631a3732022-12-21T18:19:13ZengSociety of Economic Geologists and Mineral TechnologistsInternational Journal of Economic and Environment Geology2223-957X2021-07-0112028791https://doi.org/10.46660/ijeeg.Vol12.Iss2.2021.592 Neural Network and Regression Methods for Estimation of the Average Daily Temperature of Hyderabad for the Years 2018-2020 Adeel Tahir0 Mamnoon Akhtar 1 Zaheer Ud Din 2 Muhammad Sarim 3 Department of Physics, University of Karachi, Pakistan Department of Applied Physics, University of Karachi, Pakistan Department of Physics, University of Karachi, Pakistan Department of Computer Science, Federal Urdu University of Arts S&T, Karachi, Pakistan A qualitative study on temperature distribution has been executed in Hyderabad by several researchers. This study, however, is the first attempt to study temperature distribution quantitatively. Two different methods, i.e., Artificial Neural Network (ANN) and Regression Analysis (RA), have been used to determine the average daily temperature distribution for Hyderabad, a city in Pakistan. Both the methods are used to predict the average daily temperature of the years; 2018, 2019, and 2020. In Neural Network (NN) analysis, the network was trained and validated for three years with temperature recorded from 2015-2017. With the help of training and validation parameters of the hidden layer, the average daily temperature was predicted for 2018-2020. Based on input parameters (dew point, relative humidity, and wind speed), a multiple regression model was developed, and average daily temperature for the years 2018-2020 was predicted again. For validation of the model statistical errors, Root Mean Square Error (RMSE), Mean Absolute Error (MABE), Mean Absolute Percent Error (MAPE), and coefficient of determination are calculated. The statistical errors show that multiple regression models and neural network models provide a good prediction of temperature distribution. However, the results of the neural network are better than the regression model.https://www.econ-environ-geol.org/index.php/ojs/article/view/592regression analysisaverage daily temperatueartificial neural network (ann)hyderabad city |
| spellingShingle | Adeel Tahir Mamnoon Akhtar Zaheer Ud Din Muhammad Sarim Neural Network and Regression Methods for Estimation of the Average Daily Temperature of Hyderabad for the Years 2018-2020 International Journal of Economic and Environment Geology regression analysis average daily temperatue artificial neural network (ann) hyderabad city |
| title | Neural Network and Regression Methods for Estimation of the Average Daily Temperature of Hyderabad for the Years 2018-2020 |
| title_full | Neural Network and Regression Methods for Estimation of the Average Daily Temperature of Hyderabad for the Years 2018-2020 |
| title_fullStr | Neural Network and Regression Methods for Estimation of the Average Daily Temperature of Hyderabad for the Years 2018-2020 |
| title_full_unstemmed | Neural Network and Regression Methods for Estimation of the Average Daily Temperature of Hyderabad for the Years 2018-2020 |
| title_short | Neural Network and Regression Methods for Estimation of the Average Daily Temperature of Hyderabad for the Years 2018-2020 |
| title_sort | neural network and regression methods for estimation of the average daily temperature of hyderabad for the years 2018 2020 |
| topic | regression analysis average daily temperatue artificial neural network (ann) hyderabad city |
| url | https://www.econ-environ-geol.org/index.php/ojs/article/view/592 |
| work_keys_str_mv | AT adeeltahir neuralnetworkandregressionmethodsforestimationoftheaveragedailytemperatureofhyderabadfortheyears20182020 AT mamnoonakhtar neuralnetworkandregressionmethodsforestimationoftheaveragedailytemperatureofhyderabadfortheyears20182020 AT zaheeruddin neuralnetworkandregressionmethodsforestimationoftheaveragedailytemperatureofhyderabadfortheyears20182020 AT muhammadsarim neuralnetworkandregressionmethodsforestimationoftheaveragedailytemperatureofhyderabadfortheyears20182020 |