Development of a Data Mining System for Monitoring Dams and 576 Other Engineering Structures under the Conditions of Man-Made and Natural Impacts (BR18574144)
Modern production and life support systems consume large amounts of water.To meet these needs in Kazakhstan, located mainly in an arid zone, hundreds of hydraulic structures and complexes are designed, built and operated, including dams, dams, canals, reservoirs, etc. These objects, like other significant structures, are a source of significant danger, which increases with improper design, operation and insufficient control of their current condition. Moreover, hydraulic facilities are operated in conditions of significant natural anomalies, which can be aggravated by man-made impacts. These factors lead to serious failures, including catastrophic ones, significant destruction and loss of human lives. For example, in Kazakhstan, catastrophic floods associated with dam breaks, including from neighboring countries, led to the death of several dozen people and several tens of millions dollars material damage.
There is a need for more detailed monitoring of river flows, water conditions, dams, etc. to prevent catastrophic phenomena and improve the quality of operation of equipment and structures. At the same time, increased manual monitoring leads to significant costs. However, there are numerous examples of usage of satellite and unmanned aerial vehicle (UAV) data to assess water quality, runoff volumes, predict possible flood damage, estimate sediment volumes and possible damage from landslide dams using statistical methods. There are also examples of using machine learning methods to solve the listed problems.
Thus, there is a need and there are scientific and technical prerequisites for creating an intelligent monitoring system that combines the use of remote sensing data, images obtained from a UAV and data analysis methods to assess the condition and predict the condition of engineering structures under natural and man-made influences.
This project is aimed at creating the basic elements of such a system by assessing the boundaries and capabilities of modern methods for collecting and analyzing data and prototyping the main software and hardware components.
As a result of its implementation, the following results will be obtained: Methods have been created for remote monitoring, assessment of the condition and forecast of the stability of hydraulic facilities and water infrastructure; Digital representations and 3D models of key hydraulic facilities and water infrastructure based on interactive maps and web geoinformation service; Recommendations and digital environment to ensure the effective operation of hydraulic facilities and infrastructure, environmental and industrial safety of key water bodies on the territory of Kazakhstan; Increasing efficiency and effectiveness in the field of planning and management of the water sector of the Republic of Kazakhstan, through the use of modern monitoring tools and intelligent digital technologies, including geoinformation technologies and remote sensing data; Development of competence in the field of digitalization of Kazakhstan in the field of monitoring water and land resources using remote sensing of the earth and data mining.
The aim of the project
Creation of a monitoring system for dams and other engineering structures under conditions of man-made and natural influences using intelligent data analysis.
Program tasks
Task 1: Development of a methodology for predicting the accident rate of dams and other engineering structures based on machine learning methods and technologies.
Task 2: Development of methodology and assessment of siltation of reservoirs, canals and channels based on modern approaches of intelligent analysis and remote sensing data.
Task 3: Development of mathematical and information models based on machine learning algorithms for remote assessment of water flow and quality (virtual gauging station) and forecasting water levels in rivers.
Task 4: Development and creation of interactive maps and web geoinformation services for monitoring the current and forecast state of hydraulic facilities and water infrastructure of the Republic of Kazakhstan.
Task 5: Development of a set of scientifically based management measures and recommendations to ensure efficient and trouble-free operation of dams and other engineering structures.
Task 6: Development of a pilot project for a web geoinformation service and interactive maps based on operational remote monitoring data using archival, field research and satellite (UAV) sensing based on geoinformation technologies.
Publications
- Mukhamediev, Ravil I., Timur Merembayev, Yan Kuchin, Dmitry Malakhov, Elena Zaitseva, Vitaly Levashenko, Yelena Popova, Adilkhan Symagulov, Gulshat Sagatdinova, and Yedilkhan Amirgaliyev. Soil Salinity Estimation for South Kazakhstan Based on SAR Sentinel-1 and Landsat-8, 9 OLI Data with Machine Learning Models //Remote Sensing. – 2023. – Т. 15. – №. 17. – С. 4269. https://www.mdpi.com/2072-4292/15/17/4269; https://doi.org/10.3390/rs15174269 (Scopus: Q1, 90%, WoS: Q1, IF:5.0)
- Mukhamediev, R.; Amirgaliyev, Y.; Kuchin, Y.; Aubakirov, M.; Terekhov, A.; Merembayev, T.; Yelis, M.; Zaitceva, E.; Levashenko, V.; Popova, Y.; Symagulov, A.; Tabynbayeva, L. Operational Mapping of Salinization Areas in Agricultural Fields Using Machine Learning Models Based on Low-Altitude Multispectral Images. Drones 2023, 7, 357. https://doi.org/10.3390/drones7060357(Scopus: Q1, 75%, WoS: Q2, IF:4.8)
- Zaitseva, E., Levashenko, V., Mukhamediev, R., Brinzei, N., Kovalenko, A., & Symagulov, A. (2023). Review of Reliability Assessment Methods of Drone Swarm (Fleet) and a New Importance Evaluation Based Method of Drone Swarm Structure Analysis. Mathematics, 11(11), 2551. https://www.mdpi.com/2227-7390/11/11/2551
- Mukhamediev R. I. Yakunin, K., Aubakirov, M., Assanov, I., Kuchin, Y., Symagulov, A., Levashenko V., Zatceva E., Sokolov D., Amirgaliyev, Y. . Coverage path planning optimization of heterogeneous UAVs group for precision agriculture //IEEE Access. – 2023. – Т. 11. – №. 15. – С. 5789-5803, doi: 10.1109/ACCESS.2023.3235207, https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10011226 (Scopus Quartile: Q1, 90%, JCR Category Quartile: Q2, WoS IF=3.476)
- Zaitseva, E., Levashenko, V., Brinzei, N., Kovalenko, A., Yelis, M., Gopejenko, V., & Mukhamediev, R. (2023). Reliability Assessment of UAV Fleets. In Emerging Networking in the Digital Transformation Age: Approaches, Protocols, Platforms, Best Practices, and Energy Efficiency(pp. 335-357). Cham: Springer Nature Switzerland. https://www.researchgate.net/profile/Elena-Zaitseva-2/publication/369409989_Reliability_Assessment_of_UAV_Fleets/links/641d5db6a1b72772e42293f8/Reliability-Assessment-of-UAV-Fleets.pdf