Currently, there is a growing population around the world, and this is particularly true in developing countries, where food security is becoming a major problem. Therefore, agricultural land monitoring, land use classification and analysis, and achieving high yields through efficient land use are important research topics in precision agriculture. Deep learning-based algorithms for the classification of satellite images provide more reliable and accurate results than traditional classification algorithms. In this study, we propose a transfer learning based residual UNet architecture (TL-ResUNet) model, which is a semantic segmentation deep neural network model of land cover classification and segmentation using satellite images. The proposed model combines the strengths of residual network, transfer learning, and UNet architecture. We tested the model on public datasets such as DeepGlobe, and the results showed that our proposed model outperforms the classic models initiated with random weights and pre-trained ImageNet coefficients. The TL-ResUNet model outperforms other models on several metrics commonly used as accuracy and performance measures for semantic segmentation tasks. Particularly, we obtained an IoU score of 0.81 on the validation subset of the DeepGlobe dataset for the TL-ResUNet model.

This paper tells the story of trade-off between hydropower and irrigation and its implications for groundwater use in Syrdarya basin in Central Asia. With the independence of the central Asian republics, this trade-off has become a transboundary issue. Efforts to coordinate bilateral action using integrated water resources management (IWRM) principles of basin-wide cooperation have not yet yielded the hoped for results. This paper shows that there could be a ‘second best’ option of solving at least part of this transboundary problem by ‘banking’ winter flows released for hydropower production in Kyrgyzstan in the underground aquifers of Uzbekistan's Fergana Valley and extracting it for irrigation in the summer months.

In the article it is considered the information support of the system of modeling the hydrogeological processes based on geographical information system (GIS) technology for processing spatially distributed the information to experience with creations geodatabase of underground water resources. In the research the main graphic properties of a real object are adequately reflected, which have been allowed to understand the nature of the object, to create mathematical models, to accurately determine the types of water exchange and to reduce the amount of expensive hydro-geological experiments. The aim of the research is to increase the effectiveness of methods for mathematical modeling of geofiltration processes of regional hydrogeological systems.

The paper describes an acoustic measurement and control method for remote monitoring of liquid level determination in wells and reservoirs. Before the paper, the task was to increase the depth of noncontact measurement of the liquid level in the well by measuring the time of direct propagation of ultrasound from the transmitter to the receiver, which, in contrast to the reflected sound, provides a much greater range of sound propagation and also the range of measurement and monitoring it using GSM networks. Data is returned to the main module via a USB channel or wireless radio transmitter 24 from the measurement channel. With the help of the first, ultrasound's propagation speed is determined, and the second time determines the distance from the installation site of the main module to the measuring part located on the surface of the well water in a floating position. In the main microcontroller, if the GSM network is available 16, the data is transmitted to the host server; otherwise, it is stored in the internal flash memory to wait for the availability of the GSM network, after which again, all micro-controllers of the device switch to energy-saving mode until the next measurement cycle.