Finding the Optimal Machine Learning Model for Flood Prediction on the Amur River
( Pp. 11-20)

More about authors
Aleksandrov Nikita E. PhD Student
Engineering Academy of the Peoples’ Friendship University (RUDN University)
Moscow, Russian Federation Dmitry N. Ermakov Dr. Sc. (Polit.), Dr. Sc. (Econ.), Cand. Sci. (Hist.), Professor, Principal Researcher; Institute of China and Modern Asia, Russian Academy of Sciences Researcher; Russian Federation; Professor of the Department of Management
Center for World Politics and Strategic Analysis; International Academy of Business and New Technologies
Institute of China and Modern Asia, Russian Academy of Sciences Researcher, Russian Federation; Yaroslavl, Russian Federation Aziz Naofal Mohamad Hassin Aziz PhD Student
Engineering Academy of the Peoples’ Friendship University (RUDN University)
Moscow, Russian Federation Kazenkov Oleg Yu. Honorary Worker of the Sphere of Education of the Russian Federation; assistant at the Department of Nanotechnology and Microsystem Technology; researcher at the Department for Research Activities; deputy Head of the Polyus Technopark
Engineering Academy of the Peoples’ Friendship University (RUDN University); K.G. Razumovsky Moscow State University of Tehnologies and Management (the First Cossack University); Polyus Technopark of M.F. Stelmakh Research Institute Polyus JSC
Moscow, Russian Federation
Abstract:
Water-related natural disasters are among the most devastating and are responsible for 72% of the total economic damage caused by natural disasters, and due to climate change, their number will only increase. In Russia, river floods are the main such disaster. The purpose of this research work is to determine the best machine learning method for predicting floods on the Amur River, where they cause significant damage to the population and economy of the region. The study was undertaken with the aim of improving flood forecasting methods for the subsequent use of the study results in solving management problems in response to floods. The study considers the practical aspects of implementing a forecasting system, so the 3 most popular machine learning methods were studied: linear regression, neural network and gradient boosting, because these methods have a developed ecosystem of auxiliary solutions and are widely known in the professional community. The research methodology was aimed at achieving maximum comparability of results. Among the algorithms tested, gradient boosting over trees in the implementation of Catboost demonstrated the best quality. The results of the study are also applicable to other rivers, for which the amount of data is comparable to that of the Amur.
How to Cite:
Aleksandrov N.E., Dmitry N.E., Aziz N.M., Kazenkov O.Y., (2022), FINDING THE OPTIMAL MACHINE LEARNING MODEL FOR FLOOD PREDICTION ON THE AMUR RIVER. Computational Nanotechnology, 2 => 11-20.
Reference list:
Arduino G., Reggiani P., Todini E. Recent advances in flood forecasting and flood risk assessment // Hydrology and Earth Sciences. 2005. Pp. 280-284.
Aqil M., Kita I., Nishiyama S. Analysis and prediction of flow from local source in a river basin using a Neuro-fuzzy modeling tool // Journal of Environmental Management. 2007. Pp. 215-223.
Carvalho D., Pereira E., Cardoso J. Machine learning interpretability: A survey on methods and metrics // Electronics. 2019. P. 832.
Diederik P. Kingma Jimmy Ba Adam: A method for stochastic optimization // 3rd International Conference for Learning Representations. San Diego, 2015.
DiFrancesco K.N., Tullos D.D. Flexibility in water resources management: Review of concepts and development of assessment measures for flood management systems // Journal of the American Water Resources Association. Pp. 1527-1539.
Dipanjan Sarkar, Raghav Bali, Tushar Sharma. The Python machine learning ecosystem // Practical Machine Learning with Python. 2017. Pp. 67-118.
Chang F.J., Hsu K., Chang L.C. Flood forecasting using machine learning methods. 2019.
Makhinov A.N. Amur terrigene and chemical discharge formation // Proceedings of the International Kyoto Symposium. Kyoto, Japan: Research Institute for Hymanity and Nature, 2005. Pp. 61-65.
Moore R.J., Bell V.A., Jones D.A. Forecasting for flood warning // Comptes Rendus Geosciences. 2005. Pp. 203-217.
Nash J.E., Sutcliffe J.V. River flow forecasting through conceptual models. Part I: A discussion of principles // Journal of Hydrology. 1970. Pp. 282-290.
Frumkin H. Disaster preparedness. In: Environmental health: From global to local. San Francisco: Jossey-Bass Publishers, 2005.
Prokhorenkova L. et al. CatBoost: Unbiased boosting with categorical features // NIPS. 2017.
Ram rez J.A. Prediction and modeling of flood hydrology and hydraulics. In: Inland flood hazards: Human, riparian and aquatic communities. Cambridge: Cambridge University Press, 2010.
Rumelhart D.E., Hinton G.E., Williams R.J. Learning representations by back-propagating errors // Nature. 1986. No. 323. Pp. 533-536.
Sahraei S., Asadzadeh M., Unduche F. Signature-based multi-modelling and multi-objective calibration of hydrologic models: Application in flood forecasting for Canadian Prairies // Journal of Hydrology. 2020. P. 588.
Scikit-learn sklearn.linear model.LinearRegression Online . 2022. URL: https://scikit-learn.org/stable/modules/generated/sklearn.linear model.LinearRegression.html
Tullos D. Assessing environmental impact assessments: A review and analysis of documenting environmental impacts of large dams // Journal of Environmental Management. 2008. Pp. 208-223.
Vinod N., Geoffrey E. Hinton rectified linear units improve restricted Boltzmann machines // 27th International Conference on International Conference on Machine Learning s.l. . USA: Omnipress, 2010. Pp. 807-814.
Big Data Academy MADE and hh.ru compiled a portrait of a Russian specialist in the field of Data Science. Vk, hh.ru. 2020. URL: https://vk.company/ru/press/releases/10682/
Yoganath Adikari, Junichi Yoshitani. Global trends in water related disasters: An insight for policymakers. Tsukuba, Japan: International Centre for Water Hazard and Risk Management (UNESCO) (ICHARM), 2009.
Demidenko E.Z. Linear and non-linear regression. Finance and Statistics. 1981. (In Rus.)
Makhinov A.N., Kim V.I., Voronov B.A. Flooding in the Amur basin in 2013: Causes and consequences. Bulletin of the Far Eastern Branch of the Russian Academy of Sciences. 2013. (In Rus.)
Novorotsky P.V. Fluctuations in the Amur runoff over the past 110 years. Geography and Natural Resources. 2007. Pp. 86-90. (In Rus.)
Osipov Yu.S. Neural network. In: Great Russian Encyclopedia. 2017.
Sberbank NoFloodWithAI: Forecasting floods on the Amur River. 2020. URL: https://github.com/sberbank-ai/no_flood_with_ai_aij2020
Keywords:
disaster management, floods forecasting, Amur River, machine learning.


Related Articles

Artificial intelligence and machine learning Pages: 19-31 DOI: 10.33693/2313-223X-2022-9-3-19-31 Issue №21873
Identification Algorithm Faces and Criminal Actions
Kaggle machine learning deep convolutional neural network Kaggle landmarks
Show more
Mathematical and Software of Computеrs, Complexes and Computer Networks Pages: 26-35 DOI: 10.33693/2313-223X-2023-10-2-26-35 Issue №23034
Analysis of the Algorithms of the Constituent Parts of the Compiler and its Optimization
compiler program code optimization algorithm analysis
Show more
Artificial intelligence and machine learning Pages: 35-44 DOI: 10.33693/2313-223X-2022-9-2-35-44 Issue №21224
Elements of artificial intelligence in solving problems of text analysis
sentiment analysis artificial neural networks machine learning recurrent neural networks long short-term memory
Show more
Mathematical and Software of Computеrs, Complexes and Computer Networks Pages: 83-91 DOI: 10.33693/2313-223X-2023-10-3-83-91 Issue №23683
Determination of Parameters of Hidden Threats of Early Detection in Information Systems for Machine Learning Tasks
Anylogic machine learning corporate information systems (CIS) simulation modeling data analysis
Show more
5.2.2. MATHEMATICAL, STATISTICAL AND INSTRUMENTAL METHODS OF ECONOMICS Pages: 75-79 Issue №21250
Modern Directions of Research in the Field of Recommender Systems
recommender system collaborative filtering content-based filtering cold start machine learning
Show more
4. MATHEMATICAL AND INSTRUMENTAL METHODS OF ECONOMICS 08.00.13 Pages: 65-72 Issue №19146
FORECASTING FINANCIAL MARKETS USING CONVENTIONAL NEURAL NETWORK
financial market forecasting machine learning convolutional neural network mathematical model algorithm
Show more
4. MATHEMATICAL AND INSTRUMENTAL METHODS OF ECONOMICS 08.00.13 Pages: 132-138 Issue №17852
Strategy for finding an effective machine learning method based on the example of credit scoring
credit scoring machine learning feature selection random forest ensemble of models
Show more
MATHEMATICAL, STATISTICAL AND INSTRUMENTAL METHODS OF ECONOMICS Pages: 129-140 DOI: 10.33693/2541-8025-2024-20-1-129-140 Issue №72283
Development of a Binary Classification Model Based on Small Data Using Machine Learning Methods
machine learning small data classification tasks medical data sampling
Show more
MATHEMATICAL, STATISTICAL AND INSTRUMENTAL METHODS OF ECONOMICS Pages: 167-178 Issue №24067
Café’s Performance Modeling with Spatial Data
Python. spatial data economic indicators machine learning Python.
Show more
4. MATHEMATICAL AND INSTRUMENTAL METHODS OF ECONOMICS 08.00.13 Pages: 176-186 Issue №18758
The dynamics of accounting reports as an indicator of the deterioration in bank’s financial standing
forecasting financial condition machine learning credit institutions bank ratings
Show more