Precipitation Forecast with Artificial Neural Networks Method
Events in the atmosphere from past to present – wind, precipitation, humidity, temperature – have almost always been the subject of research to create a forecast in regions. The rapid development of the technological field in terms of software and hardware brings methods and techniques to be used in research. One of them is Artificial Neural Networks. In this study, precipitation data were estimated using the Feed Forward Backpropagation method of Artificial Neural Networks method using past data of meteorological parameters, and they were compared with the data of multiple linear regression analysis. Based on these models, six different models were studied, and regression and performance evaluations were made. While the error average of multiple linear regression is 0.2413, this value is 0.076 in artificial neural networks, and the correlation average for both is 0.90. As a result of this study, the best model has a coefficient of determination of 0.95 and an error value of 0.18 in multiple linear regression, as well as a coefficient of certainty of 0.99 and an error value of 0.0438 in artificial neural networks; It has been understood that the 1st model, which has 6 data sets as the input layer, exhibits the best performance.
Anahtar Kelimeler:
Regression, Artificial neural networks, Precipitation forecast
Precipitation Forecast with Artificial Neural Networks Method
Events in the atmosphere from past to present – wind, precipitation, humidity, temperature – have almost always been the subject of research to create a forecast in regions. The rapid development of the technological field in terms of software and hardware brings methods and techniques to be used in research. One of them is Artificial Neural Networks. In this study, precipitation data were estimated using the Feed Forward Backpropagation method of Artificial Neural Networks method using past data of meteorological parameters, and they were compared with the data of multiple linear regression analysis. Based on these models, six different models were studied, and regression and performance evaluations were made. While the error average of multiple linear regression is 0.2413, this value is 0.076 in artificial neural networks, and the correlation average for both is 0.90. As a result of this study, the best model has a coefficient of determination of 0.95 and an error value of 0.18 in multiple linear regression, as well as a coefficient of certainty of 0.99 and an error value of 0.0438 in artificial neural networks; It has been understood that the 1st model, which has 6 data sets as the input layer, exhibits the best performance.
Keywords:
Regression, artificial neural networks, precipitation forecast,
___
- Yıldıran A. and Kandemir S. Y., “Estimation of rainfall amount with artificial neural networks”, BSEU Journal of Science, 5(2): 97–104, (2018).
- https://www.mgm.gov.tr/genel/meteorolojinedir.aspx
- Turhan E. and Çağatay H. Ö., “Using of Artificial Neural Network (Ann) for setting estimation model of missing flow data: Asi river-Demirköprü flow observation station (fos)”, Çukurova University Journal of the Faculty of Engineering and Architecture, 31(1): 93–106, (2016).
- Gümüş V., Başak A. and Yenigün K., “Drought Estimation of Şanlıurfa Station with Artificial Neural Network”, Gazi University Journal of Science Part C: Design and Technology, 6(3): 621–633, (2018).
- Ünes F., Taşar B., Demirci M. and Kaya Y. Z., “Forecasting of daily evaporation amounts using Artificial Neural Networks technique”, Dicle University Journal of Engineering, 9(1): 543–551, (2018).
- Tufaner F., Dabanlı İ. and Özbeyaz A., “Analysis of Drought with Artificial Neural Networks: Adıyaman Example”, 4th International Water and Environment Congress, 4(1): 25–32, (2019).
- Sezer M. S., “Long term load forecast thorugh Artificial Neural Network and different forecasting methods: Zonguldak case", Master's Thesis, Institute of Science Kütahya Dumlupınar University, (2019).
- Akbulut İ. and Özcan B., “Air pollution forecast: A comparison with Artificial Neural Networks and Regression methods”, Kocaeli Üniversitesi Science Journal. 3(1): 12–22, (2020).
- Holmstrom C., Liu D. and Vo C., “Machine learning applied to weather forecasting” Stanford University, (2016).
- Refonaa M., Lakshmi J., Abbas M., Raziullha R., “Rainfall Prediction using Regression Model” International Journal of Recent Technology and Engineering, 8(2S3): 543-546, (2019).
- Prabakara P. S. M., Kumar S. and Tarun P. N., “Rainfall prediction using modified linear regression”, ARPN Journal of Engineering and Applied Sciences, 12(12), (2017).
- Ahmed S. W. A., and Mohamed H. A. Y., “Rainfall prediction using multiple linear regressions model”, International Conference on Computer, Control, Electrical, and Electronics Engineering, 1-5, (2021).
- Srivastava L. K., Anand S., Sharma N., Dhar S. and Sinha S., “Monthly rainfall prediction using various machine learning algorithms for early warning of landslide occurrence” International Conference for Emerging Technology, 1–7, (2020).
- Parmar M., Mistree A. and Sompura K., “Machine learning techniques for rainfall prediction: A review”, International Conference on Innovations in information Embedded and Communication Systems, 3, (2017).
- Darji H. B., Dabhi M. P. and Prajapati V. K., “Rainfall forecasting using neural network: A survey”, International Conference on Advances in Computer Engineering and Applications, 706–713, (2015).
- Hatim R., Siddiqui M. and Kumar F., “Addressing Challenges and Demands of Intelligent Seasonal Rainfall Forecasting using Artificial Intelligence Approach”, International Conference on Computation, Automation and Knowledge Management, 263–267, (2020).
- Ataseven B., “Forecasting by using artificial neural networks”, Marmara University Öneri Journal, 10(39): 101-115, (2013).
- Köse B., “A new analytical approach for predicting hourly and daily wind speed and comparison with Artificial Neural Networks", 10th International Clean Energy Symposium, 928-938, (2016).
- Kaya S., “The buckling analysis of axially loaded columns with artificial neural networks”, Electronic Letters on Science & Engineering, 2(2): 36–45, (2006).
- Jacobs R. A., “Increased rates of convergence through learning rate adaptation” Neural Networks, 1(4): 295–307, (1998).
- Riedmiller M. and Braun H., “A direct adaptive method for faster backpropagation learning: the RPROP algorithm”, IEEE International Conference on Neural Networks, 1: 586-591, (1993).
- Doğru F., “Parameter estimation from residual gravity anomalies using actual optimization methods”, Bulletin of the Earth Sciences Application and Research Centre of Hacettepe University, 36(1): 31-43, (2015).
- http://kod5.org/yapay-sinir-aglari-ysa-nedir/
- Yavuz S. and Deveci M., “The effect of statistical normalization techniques on the performance of artificial neural network”, Erciyes University Journal of Faculty of Economics and Administrative Sciences, (40): 167–187, (2015).
- Özdamar K., "SPSS ile biyoistatistik", Nobel Kitabevi, 11, Ankara, (2019).
- https://avys.omu.edu.tr/storage/app/public/vceyhan
- https://acikders.ankara.edu.tr/pluginfile.php/117326/mod_resource/content/1/11-Coklu Regresyon 1.pdf
- http://www1.mgm.gov.tr/kurumsal/istasyonlarimiz.aspx?sSirala=AL&m=AYDIN
- Yeşilırmak E., “Analysis of daily precipitation concentration in büyük menderes basin”, Journal of Adnan Menderes University Agricultural Faculty, 12(2): 55–71, (2015).
- Yayın Aralığı: Yıllık
- Başlangıç: 2017
- Yayıncı: İzmir Akademi Derneği