2021
DOI: 10.53070/bbd.990966
|View full text |Cite
|
Sign up to set email alerts
|

Derin Öğrenme Yöntemleri ile Sıcaklık Tahmini: Diyarbakır İli Örneği

Abstract: Birçok uygulamada kısa vadeli sıcaklık tahminleri gereklidir. Bu tür tahminlere olan talep birçok alanla beraber özellikle enerji endüstrisinde artmıştır. Daha iyi sıcaklık tahminleri için veriye dayalı modeller giderek daha fazla popülerlik kazanmaktadır. Bu yaklaşımlar arasında derin öğrenme kavramları, yani birden çok gizli katmana sahip sinir ağları bulunmaktadır. Bu çalışmanın odak noktası, meteorolojik verilere dayalı hava sıcaklığı tahmini için derin öğrenmenin uygulanabilirliğini göstermektir. Bu kapsa… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
4
0
1

Year Published

2022
2022
2024
2024

Publication Types

Select...
4

Relationship

0
4

Authors

Journals

citations
Cited by 4 publications
(5 citation statements)
references
References 8 publications
(2 reference statements)
0
4
0
1
Order By: Relevance
“…However, it has been seen in the literature that different models are run on different data sets. Considering the LSTM accuracy rate of temperature prediction from Sevinç and Kaya deep learning methods, the RMSE values are seen as 1.859 (Sevinç and Kaya 2021). In another study, Kara found the RMSE value to be 19.39% (Kara 2019).…”
Section: Resultsmentioning
confidence: 96%
See 1 more Smart Citation
“…However, it has been seen in the literature that different models are run on different data sets. Considering the LSTM accuracy rate of temperature prediction from Sevinç and Kaya deep learning methods, the RMSE values are seen as 1.859 (Sevinç and Kaya 2021). In another study, Kara found the RMSE value to be 19.39% (Kara 2019).…”
Section: Resultsmentioning
confidence: 96%
“…There are error criterion measures, which are special formulas that provide evidence about the working type and reliability of an algorithm or model. These criteria, which are widely used in the literature; Root Mean Square Error (RMSE), Mean Square Error (MSE), R Squared Score (R2) and Mean Absolute Error (MAE) (Sevinç and Kaya, 2021). In this study, the RMSE method given in Equation 7 was used to measure the performance of the proposed model.…”
Section: Performance Calculation Criteriamentioning
confidence: 99%
“…Mean square error (MSE): MSE is the average of the squares of the error between actual values and predicted values. It measures the magnitude of errors and the closer it is to zero, the better the model works [ 21 ].…”
Section: Methodsmentioning
confidence: 99%
“…R 2 : R 2 , takes a value between 0 and 1, expressing the relationship between predicted values and actual values. The closer the result is to 1, the higher the performance and precision of the model [ 21 ].…”
Section: Methodsmentioning
confidence: 99%
“…Eksi sonsuz ile 1 arasında değer alır. Sonuç 1'e ne kadar yakınsa model o kadar hassas ve uyum iyiliği uygun demektir [18]. 2 (5)…”
Section: R Kareunclassified