Oleksandr Hordiienko

Mr. Oleksandr Hordiienko


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications

6 February 2023
Verified
Book Chapter
Closed access
PDF file
YAYevheniia Anpilova
Yevheniia Anpilova
SDStanislav Dovgyi
Stanislav Dovgyi
YYYevhenii Yakovliev
Yevhenii Yakovliev
OHOleksandr Hordiienko
Oleksandr Hordiienko
MMMykyta Myrontsov
Mykyta Myrontsov
OKOleksii Karpenko
Oleksii Karpenko


28 June 2024 in Environmental safety and natural resources
Verified
Journal Article
Open access
PDF file
TPTatyana Prosiankina-Zharova
Tatyana Prosiankina-Zharova
OHOleksandr Hordiienko
Oleksandr Hordiienko
YAYevheniia S. Anpilova
Yevheniia S. Anpilova
YYYevhenii O. Yakovliev
Yevhenii O. Yakovliev
The Synthetic Aperture Radar (SAR) equipped Sentinel-1 satellites are a valuable source of Earth observation data. They provide a spatial resolution of 10 to 20 metres, depending on the imaging mode. Unlike optical sensors, SAR radars can operate day and night, in cloudy weather and in the absence of sunlight. This makes them a reliable source of data in all conditions. Google Earth Engine (GEE), in turn, includes dual-polarisation Sentinel-1 data in its large and up-to-date archive. Since GEE does not have a single lookup complex (SLC) that allows standard methods to investigate changes in terrain, the authors set out to build a model based on the Random Forest (RF) machine learning library built into GEE that would be well suited to detecting natural and anthropogenic changes in the gypsometric structure of the terrain.In this article we analyse Sentinel-1 satellite radar images and automatically obtain data on the location of significant relief changes. Our research area is the natural and anthropogenic zones covering the agglomeration of the village of Solotvyno and the fields of flooded salt mines with active development of karst forms and areas with vertical relief shifts. Maps and graphs of changes and deformations in the agglomeration of Solotvyno were prepared on the basis of satellite radar images.The authors developed a Random Forest machine learning algorithm to detect local vertical displacements of the earth's surface, which has advantages over other algorithms and is data-free (SLC). The algorithm is based on the classification of the earth's surface and identifies well the areas where relief displacements are filled with water, and allows to increase the accuracy of the assessment of hazardous areas of surface deformations (landscapes) in the area of residential, industrial, recreational facilities, important critical infrastructure.