Search

Currently, one of the topical areas of application of artificial intelligence methods in ensuring environmental monitoring of water resources is the analysis of Earth remote sensing images in order to control and prevent potentially dangerous changes in the environment. In the future, algorithms with elements of artificial intelligence form the basis of forecasting and decision-making systems. Systems for ensuring high-quality environmental monitoring can be improved using artificial intelligence methods, in particular, the development and application of special algorithms to prevent emergencies. The aim of the study is to develop an algorithm using artificial intelligence to detect spots of substances of various origins on the water surface. It has been established that the YOLOv4 convolutional neural network is applicable for high-quality detection of oil spots and bloom spots of phytoplankton populations. The developed algorithm was tested on real satellite images and showed an accuracy of 84-94%.

The paper covers the development of an algorithm for modeling the pollutant distribution dynamics in shallow water and its implementation on a high-performance computer system in a limited time. A mathematical model of the pollutant transport, including oil and petroleum products, in the water environment has been developed taking into account a number of determining hydrodynamic and hydrophysical factors, including destruction and deposition, affecting the nature of their flow. Methods of its numerical implementation have been developed for prediction the pollution spread in shallow waters in limited time on a high-performance computer system. The main advantage of it in predictive modeling of environment processes and phenomena is taking into account the multidisciplinary nature of real processes, the complex geometry of simulated domain, ensuring high accuracy of calculations, performing a large number of calculations in a short time. Simulation of the pollutant transport of various etiologies was performed taking into account a number of determining factors, including their structure and deposition on the bottom surface, on the basis of the developed software and algorithmic tools. It used a scenario approach that meets the basic principles of effective predictive modeling in water systems. The simulation results are the foundation for planning and conducting measures to prevent and eliminate the consequences of technogenic hazards.

The paper presents an approach to the implementation of the model of eutrophication of the Sea of Azov waters using variational methods for assimilation of data obtained during expeditionary studies. The current fields are calculated on the basis of a mathematical model of the hydrodynamics of shallow water bodies, which includes the equation of motion (the Navier-Stokes equation) and the continuity equation. The developed software package uses the materials of expeditionary work and allows you to refine the model of pollution of the aquatic environment and biota through the use of variational methods of data assimilation. Based on the developed software package, a forecast of water pollution with harmful substances is given, which in turn leads to the development of harmful diatoms and toxic blue-green algae.

The mathematical part of the algorithm for searching for objects in an image using additional classifying functions is presented. A software module has been developed in the Python programming language using the OpenCV library, designed to search for and highlight the boundaries of the coastal systems of southern Russia and build a condensing grid to the center from the boundaries. Experiments were carried out to test the performance of the software module under various weather conditions based on the Azov Sea.

The work is devoted to the construction of a model of turbulent exchange in shallow water bodies using the results of expeditionary measurements. The Kalman filter algorithm was used to filter field data. An algorithm for calculating the coefficient of vertical turbulent exchange, which decisively affects the heat and gas exchange of the coastal system, has been developed, which has made it possible to significantly reduce the effect f noise in the experimental data used. As a result of the numerical implementation of the developed algorithm, the coefficient of microturbulent exchange in the vertical direction was obtained for a three-dimensional mathematical model of hydrodynamics of coastal systems.

The purpose of this work is the development of a difference scheme for the solution of convection-diffusion problem at high Peclet numbers (Pe>2). In accordance with this purpose the following problems were solved: difference scheme for convection is built, comparison with the existing schemes is carried out; conditions for stability of the proposed difference scheme are obtained. Solutions of the convection-diffusion equation on the basis of the proposed difference scheme at various Peclet numbers are obtained.

The paper presents the results of hydrochemical observations obtained during the expedition on the scientific-research vessel “Deneb” in the Eastern part of the Azov Sea and the Taganrog Bay in July 2017. In the ecological and hydrophysical researches we have found abnormally low levels of dissolved oxygen in the bottom layer of the Azov Sea. Among the various approximations of the vertical turbulent exchange coefficient, the algebraic subgrid models are the most applicable. These models are based on the determination of turbulent flows as averaged multiplication of deviations over space or time (correlation) of the velocity components of the currents and a transferring physical quantity. The numerical experiment for determination of vertical turbulent exchange coefficient for some points of the Azov Sea was performed. Direct dependence between values of the vertical turbulent exchange coefficient and the concentration of dissolved oxygen in the bottom layer was obtained.