Research Article
BibTex RIS Cite

Deniz yüzey sıcaklığının ARIMA yöntemiyle modellenmesi ve gelecek tahmini: Zonguldak ve Bartın uygulaması

Year 2023, Volume: 18 Issue: 67, 67 - 79, 22.07.2023

Abstract

Deniz yüzey sıcaklığı (DYS), okyanus ve atmosferik sistemlerin dinamiklerini anlamak ve gelecekteki iklim trendlerini tahmin etmek için kritik bir parametredir. Bu çalışmada, Avrupa Uzay Ajansı İklim Değişikliği Girişimi'nden, özellikle Deniz Yüzey Sıcaklığı İklim Değişikliği Girişimi (DYS IDG) projesinden elde edilen veriler kullanılarak, Zonguldak ve Bartın illerindeki DYS’nın ARIMA (otoregresif hareketli ortalamalar) yöntemini kullanarak modelliyoruz. Veri seti (boylam 31.25 ve enlem 40.95) 1981'den 2022'ye kadar olan 40 yıllık bir dönemi kapsamakta ve DYS trendleri ile mevsimsel varyasyonların bir değerlendirmesini içermektedir. Sonuçlar, çalışma dönemi boyunca DYS’de tutarlı bir artış göstermektedir ve mse (ortalama kare hatası) 0,07'dir.
Zonguldak ve Bartın illerindeki değişen DYS trendleri, balıkçılık ve turizm de dahil olmak üzere birçok endüstri ve sektör için önemli sonuçları vardır. Bu çalışmanın sonuçları bu alanlardaki karar verme süreçlerine ve iklim değişikliği uyum ve azaltma stratejileriyle ilgili politika kararlarına yardımcı olabilir. Bulgularımız ayrıca, DYS verilerinin alındığı DYS IDG projesi ve ARIMA yönteminin DYS verilerini modelleme etkinliği ve potansiyel sınırlamaları hakkında değerli bir iç görü sağlar.

References

  • Zhang, G. P. (2003). Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing, 159-175.
  • Merchant, C. J. (2020). Adjusting for desert-dust-related biases in a climate data record of sea surface temperature. Remote Sensing, 2554.
  • Merchant, C. E. (2019). Satellite-based time-series of sea-surface temperature since 1981 for climate applications. Scientific Data.
  • Manabe, S. a. (1988). Two stable equilibria of a coupled oceanatmosphere model. Journal of Climate, 841-866.
  • Mohamed, B. &. (2022). Sea Surface Temperature Variability and Marine Heatwaves in the Black Sea. Remote Sensing, 2383.
  • Tokat, E. a. (2023). Climatology and Variability of Sea Surface Temperature in the Region of Turkish Straits System, 1982-2021. EGU General Assembly 2023, EGU23-15096.
  • Cengiz, M. &. (2020). A solution of some commonly used optimization functions by a hybrid BFGS-PSO algorithm. ournal of the Faculty of Engineering and Architecture of Gazi University, 925-938.
  • Gülhan Toğa, B. A. (2021). COVID-19 prevalence forecasting using Autoregressive Integrated Moving Average (ARIMA) and Artificial Neural Networks (ANN): Case of Turkey. ournal of Infection and Public Health, 811-816.
  • Bollapragada, R. &.-J. (2018). A Progressive Batching L-BFGS Method for Machine Learning.
  • K. Kalpakis, D. G. (2001). Distance measures for effective clustering of ARIMA time-series,” Proceedings 2001 IEEE International Conference on Data Mining. Proceedings 2001 IEEE International Conference on Data Mining, San Jose, (s. 273-280). San Jose, CA, USA.

Modeling of sea surface temperature with ARIMA method and future prediction in Zonguldak and Bartın

Year 2023, Volume: 18 Issue: 67, 67 - 79, 22.07.2023

Abstract

Sea surface temperature (SST) is a critical parameter in understanding the dynamics of oceanic and atmospheric systems and predicting future climate trends. In this study, we use data obtained from the European Space Agency Climate Change Initiative, specifically from the Sea Surface Temperature Climate Change Initiative (SST CCI) project, to model SST in the Zonguldak and Bartın provinces using the autoregressive integrated moving average (ARIMA) method. The dataset covers 40 years from 1981 to 2022 (longitude 31.25 and latitude 40.95) and includes an assessment of FMS trends and seasonal variations. The results show a slight but consistent increase in SST over the study period, with a mean squared error of 0.07.
The changing SST trends in the Zonguldak and Bartın provinces have important implications for several industries and sectors, including fisheries and tourism. The results of this study can help inform decision-making in these areas as well as policy decisions pertaining to climate change adaptation and mitigation strategies. Our findings also provide valuable insights into the effectiveness of the ARIMA method for modeling SST data and the potential limitations of the data obtained from the SST CCI project.

References

  • Zhang, G. P. (2003). Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing, 159-175.
  • Merchant, C. J. (2020). Adjusting for desert-dust-related biases in a climate data record of sea surface temperature. Remote Sensing, 2554.
  • Merchant, C. E. (2019). Satellite-based time-series of sea-surface temperature since 1981 for climate applications. Scientific Data.
  • Manabe, S. a. (1988). Two stable equilibria of a coupled oceanatmosphere model. Journal of Climate, 841-866.
  • Mohamed, B. &. (2022). Sea Surface Temperature Variability and Marine Heatwaves in the Black Sea. Remote Sensing, 2383.
  • Tokat, E. a. (2023). Climatology and Variability of Sea Surface Temperature in the Region of Turkish Straits System, 1982-2021. EGU General Assembly 2023, EGU23-15096.
  • Cengiz, M. &. (2020). A solution of some commonly used optimization functions by a hybrid BFGS-PSO algorithm. ournal of the Faculty of Engineering and Architecture of Gazi University, 925-938.
  • Gülhan Toğa, B. A. (2021). COVID-19 prevalence forecasting using Autoregressive Integrated Moving Average (ARIMA) and Artificial Neural Networks (ANN): Case of Turkey. ournal of Infection and Public Health, 811-816.
  • Bollapragada, R. &.-J. (2018). A Progressive Batching L-BFGS Method for Machine Learning.
  • K. Kalpakis, D. G. (2001). Distance measures for effective clustering of ARIMA time-series,” Proceedings 2001 IEEE International Conference on Data Mining. Proceedings 2001 IEEE International Conference on Data Mining, San Jose, (s. 273-280). San Jose, CA, USA.
There are 10 citations in total.

Details

Primary Language Turkish
Subjects Engineering
Journal Section Articles
Authors

Cemal Erdem 0009-0001-2632-0729

Zafer Aslan 0000-0001-7707-7370

Publication Date July 22, 2023
Submission Date March 6, 2023
Published in Issue Year 2023 Volume: 18 Issue: 67

Cite

APA Erdem, C., & Aslan, Z. (2023). Deniz yüzey sıcaklığının ARIMA yöntemiyle modellenmesi ve gelecek tahmini: Zonguldak ve Bartın uygulaması. Anadolu Bil Meslek Yüksekokulu Dergisi, 18(67), 67-79.


All site content, except where otherwise noted, is licensed under a Creative Common Attribution Licence. (CC-BY-NC 4.0)

by-nc.png