Comparative Analysis of Trend Models for Standardized Precipitation Index (SPI) Data for Çanakkale

Year 2025, Volume: 12 Issue: 3, 733 - 742, 23.07.2025

Nazlı Çiçek Söylemez , Ünal Kızıl

https://doi.org/10.30910/turkjans.1699513

Abstract

Understanding precipitation trends is critical for assessing climate change and its impacts on water resources, and disaster preparedness. In this study it was aimed to analyzes the long-term trends of the Standardized Precipitation Index (SPI) for Çanakkale. The precipitation data from a period of 1929 to 2023 was used. Three distinct models—Linear Regression, Autoregressive Integrated Moving Average (ARIMA), and Long Short-Term Memory (LSTM) networks—were employed to evaluate SPI trends. The linear regression model indicated significant short-term fluctuations in SPI values but did not reveal a clear long-term trend toward wetter or drier conditions. The ARIMA model, optimized for stationarity, also suggested relatively stable precipitation patterns, with no pronounced directional trend over the study period. The LSTM model, designed for sequential data analysis, captured complex temporal dependencies in SPI values but did not indicate a persistent long-term trend. Instead, the results highlighted substantial interannual variability in precipitation. These findings underscore the complexity of climate patterns in Çanakkale Province and emphasize the need for diverse modeling approaches to accurately assess precipitation trends. The lack of a clear directional trend suggests that short-term climate variability plays a more significant role than long-term changes in precipitation patterns in the region. This study provides a foundation for further research into advanced modeling techniques to enhance climate prediction capabilities. Future studies should explore hybrid and ensemble methods to improve accuracy, which is crucial for climate adaptation strategies and water resource management.

Keywords

ARIMA , Linear Regression , Long Short-Term Memory , Climate Variability , Precipitation Trends

References

• Ahmad, I., Tang, D., Wang, T., Wang, M., & Wagan, B. (2015). Precipitation Trends over Time Using Mann-Kendall and Spearman’s rho Tests in Swat River Basin, Pakistan. Advances in Meteorology, 2015, 1-15. https://doi.org/10.1155/2015/431860.
• Angelidis, P., Maris, F., Kotsovinos, N., & Hrissanthou, V. (2012). Computation of Drought Index SPI with Alternative Distribution Functions. Water Resources Management, 26, 2453-2473. https://doi.org/10.1007/s11269-012-0026-0.
• Blain, G., & Meschiatti, M. (2015). Inadequacy of the gamma distribution to calculate the Standardized Precipitation Index. Revista Brasileira de Engenharia Agricola e Ambiental, 19, 1129-1135. https://doi.org/10.1590/1807-1929/AGRIAMBI.V19N12P1129-1135.
• Dimri, T., Ahmad, S., & Sharif, M. (2020). Time series analysis of climate variables using seasonal ARIMA approach. Journal of Earth System Science, 129, 1-16. https://doi.org/10.1007/s12040-020-01408-x.
• Green, S., & Noles, K. (1977). A Computer Program for the Generation of ARIMA Data. Educational and Psychological Measurement, 37, 249 - 252. https://doi.org/10.1177/001316447703700132.
• Guenang, G., & Kamga, F. (2014). Computation of the Standardized Precipitation Index (SPI) and Its Use to Assess Drought Occurrences in Cameroon over Recent Decades. Journal of Applied Meteorology and Climatology, 53, 2310-2324. https://doi.org/10.1175/JAMC-D-14-0032.1.
• Kale, S. (2017). Climatic Trends in the Temperature of Çanakkale City, Turkey. Natural and Engineering Sciences, 2, 14-27. https://doi.org/10.28978/NESCIENCES.348449.
• Lausier, A., & Jain, S. (2018). Overlooked Trends in Observed Global Annual Precipitation Reveal Underestimated Risks. Scientific Reports, 8. https://doi.org/10.1038/s41598-018-34993-5.
• Merity, S., Keskar, N., & Socher, R. (2017). Regularizing and Optimizing LSTM Language Models. ArXiv, abs/1708.02182.
• Mesbahzadeh, T., Miglietta, M., Mirakbari, M., Sardoo, F., & Abdolhoseini, M. (2019). Joint Modeling of Precipitation and Temperature Using Copula Theory for Current and Future Prediction under Climate Change Scenarios in Arid Lands (Case Study, Kerman Province, Iran). Advances in Meteorology. https://doi.org/10.1155/2019/6848049.
• Morin, E. (2011). To know what we cannot know: Global mapping of minimal detectable absolute trends in annual precipitation. Water Resources Research, 47. https://doi.org/10.1029/2010WR009798.
• O'Brien, S. (2018). Spatial Patterns of Precipitation Trends in the Continental United States, 1950-2016. (Masters Thesis) Fort Hays State University, USA.
• Oruh, J., Viriri, S., & Adegun, A. (2022). Long Short-Term Memory Recurrent Neural Network for Automatic Speech Recognition. IEEE Access, 10, 30069-30079. https://doi.org/10.1109/ACCESS.2022.3159339.
• Ünsal, V. (2015). Fırst Traces Of Settlement In Canakkale And Gallıpolı Penınsula. The Journal of International Social Research, 8, 340-340. https://doi.org/10.17719/JISR.20154013909.
• Yavuz, H., & Erdogan, S. (2012). Spatial Analysis of Monthly and Annual Precipitation Trends in Turkey. Water Resources Management, 26, 609-621. https://doi.org/10.1007/s11269-011-9935-6.
• Zhang, Y., & Meng, G. (2023). Simulation of an Adaptive Model Based on AIC and BIC ARIMA Predictions. Journal of Physics: Conference Series, 2449. https://doi.org/10.1088/1742-6596/2449/1/012027.