Search

Today, air temperature (AT) is the most critical climatic indicator. This indicator accurately defines global warming and climate change, despite the fact that it has effects on different things, including the environment, hydrology, agriculture, and irrigation. Accurate and timely AT forecasting is crucial since it supplies more significant details that can create credibility for future planning. This study proposes innovative hybrid models that integrate a convolutional neural network (CNN) with a long short-term memory (LSTM) neural network and a gated recurrent unit (GRU) to perform one-day ahead AT predictions. For this purpose, the daily AT data obtained from 2012 to 2019 at the Adana and Ankara meteorological stations over Türkiye under Continental and Mediterranean climate conditions are used. The hybrid GRU-CNN and LSTM-CNN models are compared with various traditional statistical and machine-learning models such as feed-forward neural network, adaptive neuro-fuzzy inference system, autoregressive moving average, GRU, CNN, and LSTM. The success of the prediction models is evaluated utilizing various statistical criteria (MAE, RMSE, NSE, and R2) and visual comparisons. The results show that the proposed hybrid GRU-CNN and LSTM-CNN models in one day-ahead AT predictions yield the best results among all models with high accuracy. [ABSTRACT FROM AUTHOR]

Cooling Degree Days (CDD) is a convenient technique obtained by summing the cumulative air temperature differences that show how much deviation from the temperature is required for human comfort in a summer season. It is a basic and relatively simple measure for predicting the cooling energy requirements of the buildings. Accurate estimation of the seasonal trend of the CDD values is a crucial policy tool in determining the energy request for cooling the buildings and is critical to better energy management by decision-makers in the country. In this regard, planners or users need to develop appropriate and precise methods that allow them to forecast their future values based on their CDD historical time series data. For this reason, in this study, Seasonal Autoregressive Integrated Moving Average (SARIMA) model is utilized to forecast the CDD values in some regions with high cooling demand in Türkiye. To accomplish this, monthly CDD data from January 1991 to December 2022 are obtained from the provinces of Adana, Adyaman, Antalya, Siirt, and Şanlurfa. First, the CDD values are modeled using the SARIMA time series approach, and then the models are employed to predict the future trends of the CDD values from 2022 to 2031. Obtained results show that with the continuation of global warming at the current rate, CDD values in all selected provinces will increase slightly by 2031, which will cause a change in building energy consumption policies. [ABSTRACT FROM AUTHOR]

The main objective of the present study is to apply the nonlinear regression (NLR) model in order to forecast water demand in Adana city of Turkey. The average monthly water bill, total subscribership, atmospheric temperature, relative humidity, rainfall, global solar radiation, sunshine duration, wind speed and atmospheric pressure are selected as independent variables. Meteorological parameters were taken from Adana meteorological station, and the other parameters such as water consumption, total subscribership and water bill values were supplied from Adana Water and Sewerage Administration during the periods of 2000-2009. In order to get a successful simulation, first, all independent variables were added to the 'enter' regression model. Then, the method of stepwise multiple regression was applied for the selection of the 'best' regression equation (model). Thus, the best independent variables were selected for the NLR model. Consequently, while water consumption in Adana city is 3.84 million m at the end of 2009, it will increase up to 4.99 million m by the year 2020. [ABSTRACT FROM AUTHOR]

This paper investigates the modeling of the daily total global solar radiation in Adana city of Turkey using multi-linear regression (MLR), multi-nonlinear regression (MNLR) and feed-forward artificial neural network (ANN) methods. Several daily meteorological data, i.e., measured sunshine duration, air temperature and wind speed and date of the year, i.e., monthly and daily, were used as independent variables to the MLR, MNLR and ANN models. In order to determine the relationship between the total global solar radiation and other meteorological data, and also to obtain the best independent variables, the MLR and MNLR analyses were performed with the 'Stepwise' method in the Statistical Packages for the Social Sciences (SPSS) program. Thus, various models consisting of the combination of the independent variables were constructed and the best input structure was investigated. The performances of all models in the training and testing data sets were compared with the measured daily global solar radiation values. The obtained results indicated that the ANN method was better than the other methods in modeling daily total global solar radiation. For the ANN model, mean absolute error (MAE), mean absolute percentage error (MAPE), correlation coefficient ( R) and coefficient of determination ( R) for the training/testing data set were found to be 0.89/1.00 MJ/m day, 7.88/9.23%, 0.9824/0.9751, and 0.9651/0.9508, respectively. [ABSTRACT FROM AUTHOR]

In this study, monthly soil temperature was modeled by linear regression (LR), nonlinear regression (NLR) and artificial neural network (ANN) methods. The soil temperature and other meteorological parameters, which have been taken from Adana meteorological station, were observed between the years of 2000 and 2007 by the Turkish State Meteorological Service (TSMS). The soil temperatures were measured at depths of 5, 10, 20, 50 and 100 cm below the ground level. A three-layer feed-forward ANN structure was constructed and a back-propagation algorithm was used for the training of ANNs. In order to get a successful simulation, the correlation coefficients between all of the meteorological variables (soil temperature, atmospheric temperature, atmospheric pressure, relative humidity, wind speed, rainfall, global solar radiation and sunshine duration) were calculated taking them two by two. First, all independent variables were split into two time periods such as cold and warm seasons. They were added to the enter regression model. Then, the method of stepwise multiple regression was applied for the selection of the 'best' regression equation (model). Thus, the best independent variables were selected for the LR and NLR models and they were also used in the input layer of the ANN method. Results of these methods were compared to each other. Finally, the ANN method was found to provide better performance than the LR and NLR methods. [ABSTRACT FROM AUTHOR]