Modelling monthly mean air temperature using artificial neural network, adaptive neuro-fuzzy inference system and support vector regression methods: A case of study for Turkey

Yakut, Emre; Süzülmüş, Seval

doi:10.1080/0954898x.2020.1759833

Cited by 20 publications

(3 citation statements)

References 98 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Bu ağı oluşturmak için beş katman kullanılır. Her katman, Şekil 1'de gösterilen birkaç düğüm yapısını içermektedir (Silarbi, Abderrahmane & Benyettou, 2014;Yakut & Süzülmüş, 2020).…”

Section: Yöntem 31 Anfis Yöntemi Ve Yapısıunclassified

Forecasting GDP in Türki̇ye Using Anfis Method

ŞENCAN¹,

Şahin²

2022

Kafkas Üniversitesi İktisadi Ve İdari Bilimler Fakültesi Dergisi

View full text Add to dashboard Cite

Gayri Safi Yurtiçi Hasıla (GSYİH), bir ülkenin makro ekonomik durumunun önemli göstergelerinden biridir. GSYİH büyümesinin büyük bir hassasiyetle tahmin edilmesi; politika yapıcılar, merkez bankaları ve diğer ekonomik aktörler için mali ve para politikalarının belirlenmesi ve planlanmasında önem taşımaktadır. Bu çalışmada, Türkiye’nin ekonomik büyümesini (GSYİH) tahmin etmek için yapay zekâ yöntemlerinden biri olan uyarlamalı ağ tabanlı bulanık mantık çıkarım sistemi (ANFIS) kullanılmıştır. İhracat, ithalat, devlet harcamaları, tüketici fiyat endeksi (TÜFE) ve enflasyon oranı girdilerine bağlı olarak ekonomik büyüme yani GSYİH tahmin edilmiştir. ANFIS modelinin güvenilirliği, çeşitli istatistiksel göstergeler kullanılarak belirlenmiştir. Ortalama mutlak yüzde hata oranı (MAPE) 1.5137 ve determinasyon katsayısı (R2) 0.9949 olarak elde edilmiştir. Bu değerlerin kabul edilebilir seviyelerde olduğu ve ekonomik büyümenin tahmin edilmesinde bu modelin başarıyla kullanılabileceği görülmüştür. Çalışmadan elde edilen sonuçlar, GSYİH büyümesini büyük bir hassasiyetle tahmin etmek, maliye ve ekonomi politikalarını belirlemek ve planlamak için kullanılabilir.

show abstract

Section: Yöntem 31 Anfis Yöntemi Ve Yapısıunclassified

Forecasting GDP in Türki̇ye Using Anfis Method

ŞENCAN¹,

Şahin²

2022

Kafkas Üniversitesi İktisadi Ve İdari Bilimler Fakültesi Dergisi

View full text Add to dashboard Cite

show abstract

“…Scholars at home and abroad have carried out a lot of research on temperature prediction 2 , Karevan et al 3 established the transformed long-short memory network model (T-LSTM) on the basis of the long-short memory network model (LSTM) to predict the weather, and the performance of the T-LSTM model is better than the LSTM model in practical applications; Karimi et al 4 constructed a monthly temperature based on the RF prediction model and used monthly temperature observations from 30 different weather stations in Iran between 1986 and 2000 as an example, and used three different performance evaluation indexes to conduct a comparative study of the traditional SVM model, and the results of the study showed that the RF model had better prediction results than the SVM model; Lee et al 5 utilized the EMD approach to the phenomenon of non-stationary oscillations in climate research and proposed a non-stationary oscillation resampling model. The results of simulation experiments showed that the model was able to provide useful forecasts of future series using the long-term oscillation patterns of the observed data 5 ; Yakut et al 6 constructed a method for forecasting monthly mean temperature based on an ANN model, an adaptive neuro-fuzzy inference system, and an SVR model, which further improved the accuracy of forecasting the monthly mean temperature in Turkey; Mohammadi et al utilized a linear regression time series model to calculate the minimum, maximum, and mean temperatures. They also created a novel hybrid model by combining AR and nonlinear time series models.…”

Section: Introductionmentioning

confidence: 99%

A monthly temperature prediction based on the CEEMDAN–BO–BiLSTM coupled model

Zhang,

Ren,

Liu

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Temperature as an important indicator of climate change, accurate temperature prediction has important guidance and application value for agricultural production, energy management and disaster warning. Based on the advantages of CEEMDAN model in effectively extracting the time–frequency characteristics of nonlinear and nonsmooth signals, BO algorithm in optimizing the objective function within a limited number of iterations, and BiLSTM model in revealing the connection between the current data, the previous data and the future data, a monthly average temperature prediction model based on CEEMDAN–BO–BiLSTM is established. A CEEMDAN–BO–BiLSTM-based monthly average temperature prediction model is developed and applied to the prediction of monthly average temperature in Jinan City, Shandong Province. The results show that the constructed monthly mean temperature prediction model based on CEEMDAN–BO–BiLSTM is feasible; the constructed CEEMDAN–BO–BiLSTM model has an average absolute error of 1.17, a root mean square error of 1.43, an average absolute percentage error of 0.31%, which is better than CEEMDAN–BiLSTM, EMD–BiLSTM, and BiLSTM models in terms of prediction accuracy and shows better adaptability; the constructed CEEMDAN–BO–BiLSTM model illustrates that the model is not over-modeled and adds complexity using Friedman’s test and performance comparisons between model run speeds. The model provides insights for effective forecasting of monthly mean temperatures.

show abstract

“…Due to the unique advantages, the SVM has been widely applied to various hydrometeorological forecasting problems (Paniagua‐Tineo et al ., 2011; Raghavendra and Deka, 2014; Mehdizadeh, 2018; Aghelpour et al ., 2019; Cifuentes et al ., 2020; Yakut and Suzulmus, 2020). Especially, the SVM has been developed and compared with other ML methods for temperature forecasting at different time scales.…”

Section: Introductionmentioning

confidence: 99%

Annual forecasting of high‐temperature days in China through grey wolf optimization‐based support vector machine ensemble

Ren

Shi

Sun

2023

Intl Journal of Climatology

View full text Add to dashboard Cite

With the intensification of anthropogenic warming and urbanization, high‐temperature weather poses an enormous threat to socio‐economic and human healthy. However, the studies on annual high‐temperature days forecasting based on machine learning are relatively deficient. This study proposes a support vector machine (SVM) ensemble model based on grey wolf optimization (GWO) to predict annual high‐temperature days in Guangzhou, Shanghai and Beijing of China. Atmospheric circulation indices during 1959–2013 were utilized as inputs to train and validate models. The fivefold cross validation was used to expand the sample data and evaluate the performance of the member and ensemble models. The optimal ensemble model for Guangzhou has the highest average R (0.8939) and the lowest average root mean square error (RMSE; 3.3771), followed by the optimal ensemble models for Beijing (0.8871 and 3.6059) and Shanghai (0.7578 and 3.9968). Furthermore, compared with the typical SVM and optimal member models, the average validation RMSE of the optimal ensemble model was improved by 32.6 and 10.0% for Guangzhou, by 29.8 and 9.1% for Shanghai, and by 41.3 and 15.1% for Beijing, respectively. This study demonstrates that the GWO‐based SVM ensemble model can be a promising tool for annual high‐temperature days forecasting due to the nonlinear fitting power of the SVM, the hyperparameters tuning capability of the GWO algorithm, and the integration ability of ensemble learning.

show abstract

Modelling monthly mean air temperature using artificial neural network, adaptive neuro-fuzzy inference system and support vector regression methods: A case of study for Turkey

Cited by 20 publications

References 98 publications

Forecasting GDP in Türki̇ye Using Anfis Method

Forecasting GDP in Türki̇ye Using Anfis Method

A monthly temperature prediction based on the CEEMDAN–BO–BiLSTM coupled model

Annual forecasting of high‐temperature days in China through grey wolf optimization‐based support vector machine ensemble

Contact Info

Product

Resources

About