Short-Term River Flood Forecasting Using Composite Models and Automated Machine Learning: The Case Study of Lena River

The paper presents a hybrid approach for short-term river flood forecasting. It is based on multi-modal data fusion from different sources (weather stations, water height sensors, remote sensing data). To improve the forecasting efficiency, the machine learning methods and the Snowmelt-Runoff physical model are combined in a composite modeling pipeline using automated machine learning techniques. The novelty of the study is based on the application of automated machine learning to identify the individual blocks of a composite pipeline without involving an expert. It makes it possible to adapt the approach to various river basins and different types of floods. Lena River basin was used as a case study since its modeling during spring high water is complicated by the high probability of ice-jam flooding events. Experimental comparison with the existing methods confirms that the proposed approach reduces the error at each analyzed level gauging station. The value of Nash–Sutcliffe model efficiency coefficient for the ten stations chosen for comparison is 0.80. The other approaches based on statistical and physical models could not surpass the threshold of 0.74. Validation for a high-water period also confirms that a composite pipeline designed using automated machine learning is much more efficient than stand-alone models. View Full-Text

Keywords: flood forecasting; automated machine learning; composite artificial intelligence

▼ Show Figures

Graphical abstract

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited

Share and Cite

MDPI and ACS Style

Sarafanov, M.; Borisova, Y.; Maslyaev, M.; Revin, I.; Maximov, G.; Nikitin, N.O. Short-Term River Flood Forecasting Using Composite Models and Automated Machine Learning: The Case Study of Lena River. Water 2021, 13, 3482. https://doi.org/10.3390/w13243482

AMA Style

Sarafanov M, Borisova Y, Maslyaev M, Revin I, Maximov G, Nikitin NO. Short-Term River Flood Forecasting Using Composite Models and Automated Machine Learning: The Case Study of Lena River. Water. 2021; 13(24):3482. https://doi.org/10.3390/w13243482

Chicago/Turabian Style

Sarafanov, Mikhail, Yulia Borisova, Mikhail Maslyaev, Ilia Revin, Gleb Maximov, and Nikolay O. Nikitin. 2021. "Short-Term River Flood Forecasting Using Composite Models and Automated Machine Learning: The Case Study of Lena River" Water 13, no. 24: 3482. https://doi.org/10.3390/w13243482

Find Other Styles

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Metrics

Abstract views Pdf views Html views

Article Access Map by Country/Region

Author Biographies

Mikhail Sarafanov

Mikhail Sarafanov is a junior researcher at National Center for Cognitive Technologies (ITMO University). He has a master's degree in Informatics and Applied Mathematics with a graduate topic on a theme about applying machine learning algorithms for remote sensing data processing. Mikhail is the developer of the open-source automatic machine learning framework FEDOT. His specialization is the methods of time series forecasting and gap-filling.

Yulia Borisova

Julia Borisova is an engineer at National Center for Cognitive Technologies (ITMO University). She gets a master’s degree in Digital Geotechnologies at ITMO University with a graduate topic on a theme about applying hybridization methods of modeling with machine learning and domain-specific models for ocean dynamics. Julia is the developer of AutoML framework FEDOT. Her specialization is time-series preprocessing and forecasting, implementation of functionality for using physical-based and custom models in the framework. The main area of interest is the modeling of environmental systems.

Ilia Revin

Ilya Revin is an engineer at the National Center for Cognitive Technologies (ITMO University). He has a Master's degree in civil engineering with a graduate topic on the application of mathematical modeling methods to calculate the thickness of oil pipelines. Ilya is the developer of the open source automatic machine learning framework FEDOT. His specialty is time series forecasting methods, matrix factorization and continuum mechanics.

Gleb Maximov

Gleb Maksimov is an engineer at National Center for Cognitive Technologies (ITMO University). He gets a master's degree at St. Petersburg State University in Applied Mathematics and Informatics. The main areas of interest are machine learning, AutoML, and software engineering. At the university, his research interest is the study of approaches to the construction of recommendation systems.

Nikolay O. Nikitin

Dr. Nikolay O. Nikitin is a senior research fellow at the National Centre for Cognitive Technologies in ITMO University. He is working in the Natural Systems Simulation Lab. Nikolay has completed his thesis devoted to the methods and technologies of local dynamic tuning for metocean models and will be defending a Ph.D. at the end of 2020. The main areas of interest include advanced AI/ML methods, automation of the data-driven modelling and generative design of digital and real objects.

Article Menu

Short-Term River Flood Forecasting Using Composite Models and Automated Machine Learning: The Case Study of Lena River

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Article Access Map by Country/Region

Author Biographies

Further Information

Guidelines

MDPI Initiatives

Follow MDPI