Author:
Nafikova Elvira,Aleksandrov Dmitriy,Shaniyazova Alsu,Bondar Christina
Abstract
Artificial neural networks and genetic algorithms have been tested for the restoration of missed hydroecological indicators (hydrological water quality parameters and bottom sediment quality parameters). Algorithms have been developed for recovering missing hydroecological data in the presence and absence of observation data from points upstream and downstream. Neural network models for the restoration of water quality indicators and bottom sediments were tested on the example of the catchment basin of the Bayda and Kidysh rivers in the territory of the Republic of Bashkortostan.
Reference13 articles.
1. Longobardi A., Fattoruso G., Guarnieri G., Di Pietro A., La Porta L., Tofani A., Pollino M., Water distribution network perspective in RAFAEL Project, a system for critical infrastructure risk analysis and forecast, in Computational Science and Its Applications–ICCSA 2021: 21st International Conference, 13–16 September, Cagliari, Italy (2021)
2. Chen Y. et al, Aerosol lidar intercomparison in the framework of the MEMO project. 1. Lidar self calibration and 1st comparison observation calibration based on statistical analysis method, in International Conf. on Meteorology Observations (ICMO), pp. 1-5 (2019)
3. Mincong H., Jiancang X., Yang C., Ni W., Yongjin Z., Application of middleware technique in Web of flood forecasting system with multiple models, in 2006 International Conference on Hybrid Information Technology, pp. 505-508 (2006)