Monitoring of dangerous shore processes of Tsimlyansk Reservoir using GIS-technologies

Abstract

In the article, the degree of displaying dangerous exogenetic geological processes (abrasion, landslide, erosion) of the Tsimlyansk Reservoir at the present stage of reforming its shores is assessed. A new original methodology for monitoring morphological and morphometrical characteristics of different shore types of the reservoir, using unmanned aerial vehicles (UAV) and Agisoft Photoscan tooling is proposed. For a number of shore sections of the Tsimlyansk reservoir, assessment of consequence for stirring up abrasion activity being expressed in stepping back the edge of shore steeps and reducing land fund is carried out. In the automated information system of water bodies state monitoring, a compulsory index is monitoring of erosion dismemberment. Methods to carry out erosion processes monitoring in water protection zones (WPZ) of water bodies using software and apparatus complex, created on the base of UAVs and GIS-technologies are developed and tested, an optimal type of digital elevation models (DEM) for assessing erosion network density is determined. Based on series of photographs carried out by UAVs by the DEMs and orthophotomaps, created using Agisoft Photoscan software, the relief erosion forms are determined. Morphometrical characteristics of the relief erosion forms are also measured, the erosion network density (K) for a number of plots in the water protection zones of the Tsimlyansk Reservoir coast is determined. In the protection zone of the Tsimlyansk Reservoir, comprehensive analysis is carried out, assessment of demographic load on the coastal area of the reservoir is conducted. Territorial zoning according to the degree of demographic load is carried out and it will allow in the future to organize planning timely measures for protecting coastal zones. The results obtained in the course of work allowed to make conclusions for the sections of the reservoir water protection zone most subject to anthropogenic activity and to propose a package of measures for its reducing.

A Deep Neural Network Method for Water Areas Extraction Using Remote Sensing Data

“…The main difference between these two calculations can be seen in areas with lakes that have a muddy environment. Due to the summer conditions, the areas of water bodies significantly decreased, which can be seen in results obtained using deep neural network [30]. Compared with the current approach, the methodology presented in previous research, based on mNDW I calculations, showed less accurate results.…”