Confidence Interval Approach to Weather Forecasting with Horizon Based Genetic Programming

Year 2024, Volume: 12 Issue: 1, 451 - 462, 26.01.2024

Ömer Mintemur

https://doi.org/10.29130/dubited.1188691

Abstract

Being able to forecast events has always been important for humans. Humans did forecasting by inspecting movements of material and non-material objects in ancient times. However, thanks to the technological developments and the increasing amount of data in recent years, forecasting is now done by computers, especially by machine learning methods. One of the areas where these methods are used frequently is numerical weather forecasting. In this type of forecast, short, medium and long-term weather forecasts are made using historical data. However, predictions are inherently error-prone phenomena and should be stated which error range the predictions fall. In this study, numerical weather forecasting was done by combining Genetic Programming and Inductive Conformal Prediction method. The effect of 10 and 20 days of historical data on short (1-day), medium (3-days) and long-term (5-days) weather forecasts was examined. Results suggested that Genetic Programming has a good potential to be used in this area. However, when Genetic Programming was combined with the Inductive Conformal Prediction method, it was shown that forecasts gave meaningful results only in short-term; forecasts made for medium and long-term did not produce meaningful results.

Keywords

Artificial Intelligence, Confidence Interval, Prediction, Genetic Programming

Ufuk Amaçlı Genetik Programlama ile Hava Durumu Tahminine Güven Aralıklı Yaklaşım

Abstract

Olayları önceden tahmin edebilmek insanlar için her zaman önemli olmuştur. Eski zamanlarda insanlar tahminlerini maddesel ve maddesel olmayan cisimlerin hareketlerine göre yapmışlardır. Ancak, son yıllardaki teknolojik gelişmeler ve veri miktarındaki artış sayesinde tahmin çalışmaları bilgisayarlar tarafından, özellikle de makine öğrenmesi metotları tarafından yapılmaktadır. Bu metotların kullanıldığı en önemli alanlardan bir tanesi de sayısal hava durumu tahminidir. Bu tahmin çeşidinde, tarihsel veriler kullanılarak kısa, orta ve uzun vadeli tahminler yapılmaktadır. Ancak, tahminler doğası gereği hataya açık olaylardır ve ortaya çıkan hatanın hangi aralıkta olduğu belirtilmelidir. Bu çalışmada sayısal hava durumu tahmini Genetik Programlama ve Tümevarımsal Güven Aralığı metodu birleştirilerek yapılmıştır. 10 ve 20 günlük tarihsel verinin kısa (1 gün), orta (3 gün) ve uzun (5 gün) vadede yapılan tahminlere olan etkisi incelenmiştir. Sonuçlar Genetik Programlamanın bu alanda kullanılabileceğini göstermektedir. Ancak, Genetik Programlama Tümevarımsal Güven Aralığı metodu ile birlikte kullanılınca, yapılan tahminlerin sadece kısa vadede anlamlı sonuçlar ürettiği görülmüştür. Orta ve uzun vadeli yapılan tahminlerin anlamlı sonuçlar üretmediği görülmüştür.

Keywords

Yapay Zeka, Genetik Programlama, Güven Aralığı, Tahmin

References

• Ning, Y., Kazemi, H., & Tahmasebi, P. (2022). A comparative machine learning study for time series oil production forecasting: ARIMA, LSTM, and Prophet. Computers & Geosciences, 164, 105126. Doi: 10.1016/j.cageo.2022.105126
• Sean J. Taylor & Benjamin Letham (2018) Forecasting at Scale, The American Statistician, 72:1, 37-45, Doi: 10.1080/00031305.2017.1380080
• W. Kong, Z. Y. Dong, Y. Jia, D. J. Hill, Y. Xu, and Y. Zhang, “Short-Term Residential Load Forecasting Based on LSTM Recurrent Neural Network,” IEEE Transactions on Smart Grid, vol. 10, no. 1, pp. 841–851, Jan. 2019, Doi: 10.1109/TSG.2017.2753802.
• X. Xiao, H. Mo, Y. Zhang, and G. Shan, “Meta-ANN – A dynamic artificial neural network refined by meta-learning for Short-Term Load Forecasting,” Energy, vol. 246, p. 123418, May 2022, Doi: 10.1016/j.energy.2022.123418.
• S. R. Ghaffari-Razin, A. R. Moradi, and N. Hooshangi, “Modeling and forecasting of ionosphere TEC using least squares SVM in central Europe,” Advances in Space Research, Jun. 2022, Doi: 10.1016/j.asr.2022.06.020.
• Fan Li & Guang Jin (2022) Research on power energy load forecasting method based on KNN, International Journal of Ambient Energy, 43:1, 946-951, Doi: 10.1080/01430750.2019.1682041
• M. Lehna, F. Scheller, and H. Herwartz, “Forecasting day-ahead electricity prices: A comparison of time series and neural network models taking external regressors into account,” Energy Economics, vol. 106, p. 105742, Feb. 2022, Doi: 10.1016/j.eneco.2021.105742.
• A. Brusaferri, M. Matteucci, P. Portolani, and A. Vitali, “Bayesian deep learning based method for probabilistic forecast of day-ahead electricity prices,” Applied Energy, vol. 250, pp. 1158–1175, 2019, Doi: 10.1016/j.apenergy.2019.05.068
• X. Gong, W. Zhang, W. Xu, and Z. Li, “Uncertainty index and stock volatility prediction: evidence from international markets,” Financial Innovation, vol. 8, no. 1, p. 57, Jun. 2022, Doi: 10.1186/s40854-022-00361-6.
• F. Baart, M. van Ormondt, J. van T. de Vries, and M. van Koningsveld, “Morphological impact of a storm can be predicted three days ahead,” Computers & Geosciences, vol. 90, pp. 17–23, 2016, Doi: 10.1016/j.cageo.2015.11.011.
• R. Buizza, “Chaos and weather prediction January 2000,” European Centre for Medium-Range Weather Meteorological Training Course Lecture Series ECMWF, 2002.
• H. R. Biswas, M. M. Hasan, and S. K. Bala, “Chaos theory and its applications in our real life,” Barishal University Journal Part, vol. 1, no. 5, pp. 123–140, 2018.
• Ibrahim Gad & Doreswamy Hosahalli (2022) A comparative study of prediction and classification models on NCDC weather data, International Journal of Computers and Applications, 44:5, 414-425, Doi: 10.1080/1206212X.2020.1766769.
• H. Yang, J. Yan, Y. Liu, and Z. Song, “Statistical downscaling of numerical weather prediction based on convolutional neural networks,” Global Energy Interconnection, vol. 5, no. 2, pp. 217–225, 2022, Doi: 10.1016/j.gloei.2022.04.018.
• J. Frnda, M. Durica, J. Rozhon, M. Vojtekova, J. Nedoma, and R. Martinek, “ECMWF short-term prediction accuracy improvement by deep learning,” Scientific Reports, vol. 12, no. 1, pp. 1–11, 2022, Doi: 10.1038/s41598-022-11936-9.
• G. Xu, K. Lin, X. Li, and Y. Ye, “SAF-Net: A spatio-temporal deep learning method for typhoon intensity prediction,” Pattern Recognition Letters, vol. 155, pp. 121–127, 2022, Doi: 10.1016/j.patrec.2021.11.012.
• J. R. Koza and R. Poli, “Genetic Programming,” in Search Methodologies: Introductory Tutorials in Optimization and Decision Support Techniques, E. K. Burke and G. Kendall, Eds. Boston, MA: Springer US, 2005, pp. 127–164. Doi: 10.1007/0-387-28356-0_5.
• O. Claveria, E. Monte, and S. Torra, “A Genetic Programming Approach for Economic Forecasting with Survey Expectations,” Applied Sciences, vol. 12, no. 13, Art. no. 13, Jan. 2022, Doi: 10.3390/app12136661.
• E. Christodoulaki, M. Kampouridis, and P. Kanellopoulos, “Technical and Sentiment Analysis in Financial Forecasting with Genetic Programming,” in 2022 IEEE Symposium on Computational Intelligence for Financial Engineering and Economics (CIFEr), May 2022, pp. 1–8. Doi: 10.1109/CIFEr52523.2022.9776186.
• S. Cramer, M. Kampouridis, and A. A. Freitas, “Decomposition genetic programming: An extensive evaluation on rainfall prediction in the context of weather derivatives,” Applied Soft Computing, vol. 70, pp. 208–224, 2018, Doi: 10.1016/j.asoc.2018.05.016
• M. Sadat-Noori, W. Glamore, and D. Khojasteh, “Groundwater level prediction using genetic programming: the importance of precipitation data and weather station location on model accuracy,” Environmental Earth Sciences, vol. 79, no. 1, pp. 1–10, 2020, Doi: 10.1007/s12665-019-8776-0.
• J. B. Elsner and A. A. Tsonis, “Nonlinear prediction, chaos, and noise,” Bulletin of the American Meteorological Society, vol. 73, no. 1, pp. 49–60, 1992, Doi: 10.1175/1520-0477(1992)073<0049:NPCAN>2.0.CO;2
• Mnassrı, B. Weather Station Beutenberg Dataset. https://www.kaggle.com/datasets/mnassrib/jena-weather-dataset. [Accessed: 25.07.2022].
• H. Papadopoulos, "Inductive Conformal Prediction: Theory and Application to Neural Networks", in Tools in Artificial Intelligence. London, United Kingdom: IntechOpen, 2008 [Online]. Available: https://www.intechopen.com/chapters/5294 Doi: 10.5772/6078.