doi: 10.17586/2226-1494-2021-21-1-135-142


FORECASTING THE SPRING FLOOD OF RIVERS WITH MACHINE LEARNING METHODS

N. I. Kulin, E. A. Kozlov, Y. A. Zhuk


Read the full article  ';
Article in Russian

For citation:
Kulin N.I., Kozlov E.A., Zhuk Yu.A. Forecasting the spring flood of rivers with machine learning methods. Scientific and Technical Journal of Information Technologies, Mechanics and Optics, 2021, vol. 21, no. 1, pp. 135–142 (in Russian). doi: 10.17586/2226-1494-2021-21-1-135-142


Abstract
The subject of the research. The paper provides an overview of a flood forecasting problem in the Nenetsky region, Russia. The solution involves the use of the open source data on water level during the spring floods. Specifically, its collection, analysis and forecasting via machine learning models. Method. The authors describe a new forecasting approach that involves the use of the Holt-Winters model for a training sample, which is further implemented in order to train the following statistical models: XGBoost, Random Forest and Bagging. The solution is based on a sample of gauging stations’ historical indicators that provide a detailed description of weather conditions in the nearest settlements over several years. A separate sample was created for each location considered in the problem with the aim to build forecasts given a one-month or a one-year time period. Main Results. The forecast was obtained based on the results provided by individually trained models. In the future, the findings could be used when taking preventive measures during flood control. Practical relevance. Low maintenance costs of the information system along with the ability to predict the critical water level make this forecasting approach an economically viable additional measure against floods in poorer regions of Russia.

Keywords: data mining, machine learning, flood forecast, Holt-Winters model

References
1. Mosavi A., Ozturk P., Chau K.-W. Flood prediction using machine learning models: Literature review. Water, 2018, vol. 10, no. 11, pp. 1536. doi: 10.3390/w10111536
2. Huang M., Xie J., Cai Y., Wang N., Zhang Y. Application of middleware technique in Web of flood forecasting system with multiple models. Proc. International Conference on Hybrid Information Technology, ICHIT 2006, 2016, pp. 505–508. doi: 10.1109/ICHIT.2006.253534
3. Abdurrahman M., Irawan B., Latuconsina R. Flood Forecasting using Holt-Winters Exponential Smoothing Method and Geographic Information System. Proc. 3rd International Conference on Control, Electronics, Renewable Energy and Communications (ICCREC), 2017, pp. 159–163. doi: 10.1109/ICCEREC.2017.8226704
4. Adnan R., Ruslan F.A., Samad Abd M., Zain Z.Md. Flood water level modelling and prediction using artificial neural network: Case study of Sungai Batu Pahat in Johor. Proc. IEEE Control and System Graduate Research Colloquium, ICSGRC 2012, 2012, pp. 22–25. doi: 10.1109/ICSGRC.2012.6287127
5. Rahman I.I.A., Alias N.M.A. Rainfall forecasting using an artificial neural network model to prevent flash floods. Proc. 8th International Conference on High-capacity Optical Networks and Emerging Technologies, HONET , 2011, pp. 323–328. doi: 10.1109/HONET.2011.6149841
6. Linghu B., Chen F. An intelligent multi-agent approach for flood disaster forecasting utilizing case based reasoning. Proc. 5th International Conference on Intelligent Systems Design and Engineering Applications, ISDEA, 2014, pp. 182–185. doi: 10.1109/ISDEA.2014.48
7. Ranit A.B., Durge P.V. Different techniques of flood forecasting and their applications. Proc. 3rd International Conference on Research in Intelligent and Computing in Engineering, RICE, 2018, pp. 8509058. doi: 10.1109/RICE.2018.8509058
8. Zhu Y., Feng J., Yan L., Guo T., Li X. Flood prediction using rainfall- flow pattern in data-sparse watersheds. IEEE Access, 2020, vol. 8, pp. 39713–39724. doi: 10.1109/ACCESS.2020.2971264
9. Sachin D. Holt-Winters Exponential Smoothing. Towards Data Science, 2020. Available at: https://towardsdatascience.com/holt- winters-exponential-smoothing-d703072c0572 (accessed: 18.10.2020).
10. Koehrsen W. An Implementation and Explanation of the Random Forest in Python. Towards Data Science, 2018. Available at: https:// towardsdatascience.com/an-implementation-and-explanation-of-the- random-forest-in-python-77bf308a9b76 (accessed: 18.10.2020).
11. Christopher B. Time Series Analysis (TSA) in Python — Linear Models to GARCH. Blackarbs, 2016. Available at: http://www. blackarbs.com/blog/time-series-analysis-in-python-linear-models-to- garch/11/1/2016 (accessed: 18.10.2020).
12. Brownlee J. A Gentle Introduction to Exponential Smoothing for Time Series Forecasting in Python. Machine Learning Mastery, Australia, 2018. Available at: https://machinelearningmastery.com/exponential- smoothing-for-time-series-forecasting-in-python/ (accessed: 18.10.2020).
13. Rocca J. Ensemble methods: bagging, boosting and stacking. Towards Data Science, 2019. Available at: https://towardsdatascience.com/
14. Brownlee J. How to Use XGBoost for Time Series Forecasting. Machine Learning Mastery, Australia, 2018. Available at: https:// machinelearningmastery.com/xgboost-for-time-series-forecasting/ (accessed: 18.10.2020).
15. Brownlee J. Comparing Classical and Machine Learning Algorithms for Time Series Forecasting. Machine Learning Mastery, Australia, 2019. Available at: https://machinelearningmastery.com/ findings-comparing-classical-and-machine-learning-methods-for- time-series-forecasting/ (accessed: 18.10.2020).


Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
Copyright 2001-2024 ©
Scientific and Technical Journal
of Information Technologies, Mechanics and Optics.
All rights reserved.

Яндекс.Метрика