The use of bivalve mollusks as bioindicators in automated monitoring systems can provide real-time detection of emergency situations associated with the pollution of aquatic environments. The behavioral reactions of Unio pictorum (Linnaeus, 1758) were employed in the development of a comprehensive automated monitoring system for aquatic environments by the authors. The study used experimental data obtained by an automated system from the Chernaya River in the Sevastopol region of the Crimean Peninsula. Four traditional unsupervised machine learning techniques were implemented to detect emergency signals in the activity of bivalves: elliptic envelope, isolation forest (iForest), one-class support vector machine (SVM), and local outlier factor (LOF). The results showed that the use of the elliptic envelope, iForest, and LOF methods with proper hyperparameter tuning can detect anomalies in mollusk activity data without false alarms, with an F1 score of 1. A comparison of anomaly detection times revealed that the iForest method is the most efficient. These findings demonstrate the potential of using bivalve mollusks as bioindicators in automated monitoring systems for the early detection of pollution in aquatic environments.

Determining the solute mass amount in seawater using in situ measurements in seas and oceans is currently an unresolved problem. To solve it, it is necessary to develop both new methods and instruments for measurements. The authors of this article analyzed methods for the indirect measurement of salinity and density using parameters that can be measured in situ, including relative electrical conductivity, speed of sound, temperature, and hydrostatic pressure. The authors propose an electric conductivity sensor design that allows for the obtainment of data on solid suspensions along with measuring the impedance of electrodes under various the alternating current frequencies. The authors analyzed the joint measurement technique using the Conductivity-Temperature-Depth (CTD) and Sound Velocity Profiler (SVP) devices in a marine testing area. Based on the results of joint measurements, the authors present tests of water samples of various salt compositions for the presence of solid suspensions.

In the water environment, we are dealing with a complex mixture of pollutants. Modern monitoring systems, mainly based on the physicochemical methods of monitoring the aquatic environment, cannot quickly determine the full range of pollutants and assess the degree of danger of an agent for the ecosystem and humans. The most effective for solving these problems are bioelectronic (biosensor) systems for automated monitoring of surface waters, in which animals are directly incorporated into the electronic registration system of certain physiological, biochemical, or behavioral biomarkers. Such systems, in contrast to physico-chemical methods of monitoring, allow obtaining an integral toxicological characteristic of the aquatic environment, regardless of the origin and composition of pollutants, and in real time to assess the quality of water as the habitat of hydrobionts. The article presents the results of the development automated biological early warning system for water environment. As the main element of this system, the authors developed a device for automated monitoring of aquatic media (DAMAM) based on the behavioral reactions of bivalve mollusks and computer program kits. In addition, for the implementation of the system, the authors developed software for server and system users.

The paper presents a monitoring system based on a distributed network of autonomous surface robots for automated comprehensive monitoring of water parameters across the observed field. It proposes an intelligent decision support system for anomalies detection that enables high-awareness expert decision-making in terms of factor space of the scalar and vector fields, increase the sufficiency, accuracy, and reliability. The authors present a solution to the problem of correcting the readings from the robot control system; the solution is based on inertial MEMS sensors and nonlinear filtration. The developed hardware and software were used to carry out computational experiments to optimize the system scenarios and further optimize the controls in real time.

The method of visual analysis, which provides detection of contours and clusterization of objects of interest optimized for real-time operation is offered in this paper. The method is intended for use in oceanographic equipment to estimate the abundance and dynamics of plankton spatial distribution in seas and oceans in situ. The structural elements of the monitoring system are given and their mathematical model is described. The comparison of the recursive clusterization method and the method of K-means clustering by the criteria of correct and erroneous classification coefficients was made based on plankton video analyzer using OpenCV framework. The results of practical tests of the suggested method show significant reduction in nuisance tripping factor at the expense of insignificant increase in the processing time and the volume of memory used. These aspects meet the requirements for work in high-load Big Data processing systems, standalone image processing systems designed for long-term deployment.

Новые уравнения для расчета плотности морской воды на основе измерений скорости звука