Numerical simulation results of the Black Sea circulation obtained by four ocean dynamics models are compared to each other and to in situ data in order to determine the features of the Black Sea deep-water circulation such as deep-water undercurrents. The year 2011 is chosen as the test period due to the availability of deep-sea observations, including ARGO profiles and ADCP current velocities. Validation of the simulation results is based on comparison with the temperature and salinity measured by the ARGO floats. Anticyclonic currents (undercurrents) under the cyclonic Rim Current are detected by the results of all numerical models near the North Caucasian coast. The main characteristics of undercurrents are consistent with in situ data on current velocity up to a depth of 1000 m obtained by the Aqualog probe at the IO RAS test site near Gelendzhik in June 2011. The analysis of the spatio-temporal variability of the modeled salinity and velocity fields reveals that the most probable origin of the undercurrents is the horizontal density gradient of seawater in the region.

This paper presents a new method for finding the optimal positions for sensors used to reconstruct geophysical fields from sparse measurements. The method is composed of two stages. In the first stage, we estimate the spatial variability of the physical field by approximating its information entropy using the Conditional Pixel CNN network. In the second stage, the entropy is used to initialize the distribution of optimal sensor locations, which is then optimized using the Concrete Autoencoder architecture with the straight-through gradient estimator for the binary mask and with adversarial loss. This allows us to simultaneously minimize the number of sensors and maximize reconstruction accuracy. We apply our method to the global ocean under-surface temperature field and demonstrate its effectiveness on fields with up to a million grid cells. Additionally, we find that the information entropy field has a clear physical interpretation related to the mixing between cold and warm currents.

The paper examines the impact of sensor placement on the accuracy of the Global ocean state forecasting. A comparison is made between various sensor placement methods, including the arrangement obtained by the Concrete Autoencoder method. To evaluate how sensor placement affects forecast accuracy, a simulation was conducted that emulates a scenario where the initial state of the global ocean significantly deviates from the ground truth. In the experiment, initial conditions for the ocean and ice model were altered, while atmospheric forcing was retained from the control experiment. Subsequently, the model was integrated with the assimilation of data about the ground truth state at the sensor locations. The results showed that the sensor placement obtained using deep learning methods is superior in forecast accuracy to other considered arrays with a comparable number of sensors.