Denis Krivoguz | Russian scientific research institute of Fisheries and Oceanography (original) (raw)
Papers by Denis Krivoguz
Data
This study investigates the application of various machine learning models for land use and land ... more This study investigates the application of various machine learning models for land use and land cover (LULC) classification in the Kerch Peninsula. The study utilizes archival field data, cadastral data, and published scientific literature for model training and testing, using Landsat-5 imagery from 1990 as input data. Four machine learning models (deep neural network, Random Forest, support vector machine (SVM), and AdaBoost) are employed, and their hyperparameters are tuned using random search and grid search. Model performance is evaluated through cross-validation and confusion matrices. The deep neural network achieves the highest accuracy (96.2%) and performs well in classifying water, urban lands, open soils, and high vegetation. However, it faces challenges in classifying grasslands, bare lands, and agricultural areas. The Random Forest model achieves an accuracy of 90.5% but struggles with differentiating high vegetation from agricultural lands. The SVM model achieves an ac...
Anais do XIV Colóquio Internacional "Educação e Contemporaneidade" (EDUCON), 2020
RESUMO: Neste artigo abordo uma noção de corpo que percebo ser recorrente em diversos espaços de ... more RESUMO: Neste artigo abordo uma noção de corpo que percebo ser recorrente em diversos espaços de ensino da dança, a de que somos uma tábula rasa a ser preenchida passivamente por qualquer tipo de movimento. Essa crença em uma suposta neutralidade corporal, que desconsidera todos as informações sociais, genéticas e afetivas que nos atravessam, pode acarretar certo comportamento violento de professores, que muitas vezes sem perceber, acabam gerando bloqueios no processo de aprendizagem dos seus alunos. Esta escrita, que utiliza Pinker (2004), Katz (2005) e Greiner (2006) como principais referências, narra e analisa uma das minhas experiências como aluna e componente de um dos projetos de extensão do curso de Licenciatura em Dança da Universidade Federal de Sergipe (UFS). Palavras-chave: Corpo. Ensino-aprendizagem. Dança. RESUMEN: En este artículo abordo una noción de cuerpo que percibo recurrente en varios espacios de enseñanza de la danza, que somos uma tábula rasa que se llena pasivamente por cualquier tipo de movimiento. Esta creencia en una supuesta neutralidad corporal, que desconcidera todas las informaciones sociales, genéticas y afectivas que nos cruzan, puede conducir a un cierto comportamiento violento de los profesores, que a menudo sin darse cuenta, terminan generando bloqueos en el proceso de aprendizaje de sus alumnos. Esta escrita, que utiliza a Pinker (2004), Katz (2005) y Greiner (2006) como principales referencias, narra y analiza una de mis experiencias como estudiante y miembro de uno de los proyectos de extensión del Grado en Danza de
2022 Conference of Russian Young Researchers in Electrical and Electronic Engineering (ElConRus)
Fisheries
The Black Sea sprat Sprattus sprattus phalericus (Risso) and temperature factor impact have been ... more The Black Sea sprat Sprattus sprattus phalericus (Risso) and temperature factor impact have been investigated. Statistical assessment of the long-term dynamics (1951–2019) of a relationship between the temperature factor and sprat mean weight in fishery catches used as a population quality characteristic has been performed. Pearson product-moment correlation and cross-correlation was evaluated, then data series was smoothed by the local polynomial regression and, finally, a linear model was fitted. The correlation test shows significant relationship between the temperature factor and sprat mean weight-at-age (mean weight in 3+ age group and SST in the port of Yalta resulted in r = -0.86, whereas average SST and average mean weight by age classes led to r = -0.74). The fitted linear model by smoothed data of average SST and average weight-at-age successfully passed diagnostics (R2 = 0.87, RSE = 0.34), with the equation: w = f(sst) = 22.23 - 1.263*sst. As a result, this study allows t...
Journal of Marine Science and Engineering, 2022
Knowledge of the spatio-temporal distribution of salinity provides valuable information for under... more Knowledge of the spatio-temporal distribution of salinity provides valuable information for understanding different processes between biota and environment, especially in hypersaline lakes. Remote sensing techniques have been used for monitoring different components of the environment. Currently, one of the biggest challenges is the spatio-temporal monitoring of the salinity level in water bodies. Due to some limitations, such as the inability to be located there permanently, it is difficult to obtain these data directly. In this study, machine learning techniques were used to evaluate the salinity level in hypersaline East Sivash Bay. In total, 93 in situ data samples and 6 Sentinel-2 datasets were used, according to field measurements. Using linear regression, random forest and AdaBoost models, eight water salinity evaluation models were built (six with simple, one with random forest and one with AdaBoost). The accuracy of the best-fitted simple linear regression model was 0.8797;...
Ecology. Economy. Informatics.System analysis and mathematical modeling of ecological and economic systems, 2021
Preliminary study of impact of temperature factor to sprat quality characteristics in Russian wat... more Preliminary study of impact of temperature factor to sprat quality characteristics in Russian waters of the Black sea in period 1951–2019 was performed. In this research statistical hyphothesis about relationship between indicator sea surface temperature factor near to Chernomorskoe, Yalta, Feodosia and long-term sprat mean weight fishery statistics was done. Linear relationship hyphothesis performed by Pearson correlation test. Preliminary cross-correlation test results shows significant moderate relationship between temperature factor average and mean sprat weights (r = –0,60). After preliminary diagnostics input data was smoothed by polynomial regression to reduce interannual fluctuations and cross-correlation test to smoothed data was repeated. Correlation test by smoothed data indicate strong negative (r = –0,75) relationship between long-term sea surface temperature in all indicator points and mean sprat weights and high powerful relationship between sea surface temperature an...
Russian Journal of Earth Sciences, 2020
Russian Journal of Earth Sciences, 2020
Landslides are one of the most important problems on Kerch Peninsula. Rapidly increasing anthropo... more Landslides are one of the most important problems on Kerch Peninsula. Rapidly increasing anthropogenic pressure, which has been particularly could be seen in recent years, leads to destabilization of slopes and significant economic and social damage. Nowdays, economic activities for the further development of Kerch Peninsula, urbanization and the construction of new infrastructure facilities may lead to destabilization of slopes and activation of landslides. Application of an integrated mathematical model, helped us to reflect the current state of Kerch Peninsula in the context of solving this problem. With the help of field research, we mapped a complex of landslide areas, which made it possible to identify the main types of them occurring here-earth and earthwork slips landslides, and in the coastal zone-landfalls and caving slides, total area of which reaches 87.5 km 2 (7.4% of the research area territory). We chose an optimal method under the given conditions-the weight of evidence. The approach presented in this paper allows us to classify the territory according to the degree of its susceptibility to landslides with rather high accuracy and analyze the existing situation in this area and analyze possible scenarios for its development. We zoned the territory of the Kerch peninsula into 3 classes-stable, unstable and unsusceptible according to the degree of landslide probable occurrences. The susceptibility analysis revealed that the factors causing the activation of landslides on the Kerch Peninsula are the slope steepness from 20 to 40 degrees, the anthropogenic impact, excessive salinity of the soil cover and the lithological composition of the terrain.
Nauchno-tekhnicheskiy vestnik Bryanskogo gosudarstvennogo universiteta, 2018
Керченский государственный морской технологический университет (Керчь, Россия) Современное развит... more Керченский государственный морской технологический университет (Керчь, Россия) Современное развитие Керченского полуострова тесно связанно с масштабным техногенным воздействием, что приводит к существенным изменениям в функционировании природных комплексов. В работе продемонстрирован нейросетевой подход к изучению изменений состояния ландшафтного покрова и приняты попытки его прогнозирования. Моделирование проводилось на основании имеющихся данных о различных компонентах окружающей среды Керченского полуострова и антропогенных факторов, на них воздействующих. Анализ показал значительные изменения в ландшафтной составляющей полуострова, которые потенциально могут привести к ухудшению ситуации с проявлениями склоновых процессов.
Safety in Technosphere, 2017
Modern approaches to the region’s landslide susceptibility assessment are considered in this pape... more Modern approaches to the region’s landslide susceptibility assessment are considered in this paper. Have been presented descriptions of the most used techniques for landslide susceptibility assessment: logistic regression, indicator validity, linear discriminant analysis and application of artificial neural networks. These techniques’ advantages and disadvantages are discussed in the paper. The most suitable techniques for various conditions of analysis have been marked. It has been concluded that the most acceptable techniques of analysis for a large number of input data related to the studied region are the method of logistic regression and indicator validity method. With these methods the most accurate results are achieved. When there is a lack of information, it is more expedient to use linear discriminant analysis and artificial neural networks that will minimize potential analysis inaccuracies.
Economies
The article presents the sectoral structure of cruise (maritime) tourism and identifies the facto... more The article presents the sectoral structure of cruise (maritime) tourism and identifies the factors influencing the level of demand and supply of cruise tourism products. The sources of the influence of the cruise industry on the economic growth of the state and the welfare of its citizens are also considered. On the basis of specific features of cruise tourism functioning and the peculiarities of creating a cruise tourism product, a model of the functioning of a cruise (maritime) tourism complex has been built. Representation of the relationship of tourist needs according to the hierarchy of needs and a species classification of cruise tourism and the industries involved in its development is also given. The model of indicators and the structural components described are built in an environment of geoinformation modeling.
Climatic changes that have occurred over the past decades, with an acceleration of urbanization o... more Climatic changes that have occurred over the past decades, with an acceleration of urbanization of territories and technological development, leads to the significant changes not only in the atmosphere, but also in the Earth’s surface. Surface water bodies are one of these components. Today there are 3 main methods of monitoring water bodies -field, remote and combined. In this paper, we show the possibility of automating remote monitoring of water bodies using QGIS, Python and Sentinel-2 data of the main and largest lakes of the Kerch Peninsula. Having analysed both the available satellite data and the features of the study area, we came to the conclusion that it is advisable to use the NDWI index instead of the mNDWI. After processing and analysing the Sentinel-2 data for 2018 using the data processing model presented in the work, we obtained time series of changes in the areas of the studied lakes of the Kerch Peninsula.
Salinity is one of the most important factors that primarily determines the level of seawater’s d... more Salinity is one of the most important factors that primarily determines the level of seawater’s density and, consequently, the movement of water masses in the World Ocean. Spatial distribution of the salinity in different layers of the Black Sea are associated with varying levels of water balance seasonal variability and, general circulation of Black Seas waters and in the surface layer has a seasonal structure. To study spatial distribution of salinity in upper layers of the Black Sea we’ve used data from Copernicus Marine Environment Monitoring Service, that were processed and aggregate by seasons and depth. We found that the most fluctuated layer is a top layer (up to 2.8 m) and the highest values Black Sea salinity reaches near the Bosporus Strait, where more saline water from the Sea of Marmara connected with fresher water of the Black Sea. Also we found that the impact of the river flows, mixing of the water, water regime of the sea decreasing with depth, so in the bottom of t...
Russian Journal of Earth Sciences
Aquatic ecosystems of the Black Sea are complex multiparametric systems with a hierarchical struc... more Aquatic ecosystems of the Black Sea are complex multiparametric systems with a hierarchical structure. Thus, the main goal of our research was to investigate possibilities of using Bayesian networks to study the structure fo the natural systems in the Black Sea. We used CMEMS Black Sea environmental dataset, which consists of 7 different variables, that, in our opinion, can describe structural relations in the Black Sea ecosystem -- sea surface temperature and salinity, concentrations of nitrates and phosphates, amount of chlorophyll-a and net primary production and also dissolved oxygen concentration. We think, that these variables can generally define interactions in water environment of the Black Sea, organisms, that live there and human activity. As a modelling result, we receive a structure of environmental variables interactions. At the top of this structure is a dissolved oxygen, as a final result of the ecosystem functioning. Further, we think it's more appropriate to us...
Landslides are one of the most important problems on Kerch Peninsula. Rapidly increasing anthropo... more Landslides are one of the most important problems on Kerch Peninsula. Rapidly increasing anthropogenic pressure, which has been particularly could be seen in recent years, leads to destabilization of slopes and significant economic and social damage. Nowdays, economic activities for the further development of Kerch Peninsula, urbanization and the construction of new infrastructure facilities may lead to destabilization of slopes and activation of landslides. Application of an integrated mathematical model, helped us to reflect the current state of Kerch Peninsula in the context of solving this problem. With the help of field research, we mapped a complex of landslide areas, which made it possible to identify the main types of them occurring here-earth and earthwork slips landslides, and in the coastal zone-landfalls and caving slides, total area of which reaches 87.5 km 2 (7.4% of the research area territory). We chose an optimal method under the given conditions-the weight of evidence. The approach presented in this paper allows us to classify the territory according to the degree of its susceptibility to landslides with rather high accuracy and analyze the existing situation in this area and analyze possible scenarios for its development. We zoned the territory of the Kerch peninsula into 3 classes-stable, unstable and unsusceptible according to the degree of landslide probable occurrences. The susceptibility analysis revealed that the factors causing the activation of landslides on the Kerch Peninsula are the slope steepness from 20 to 40 degrees, the anthropogenic impact, excessive salinity of the soil cover and the lithological composition of the terrain. KEYWORDS: Landslides; landslide susceptibility; GIS; spatial analysis; landslide zoning. Citation: Krivoguz, Denis and Liudmila Bespalova (2019), Landslide susceptibility analysis for the Kerch Peninsula using weights of evidence approach and GIS, Russ.
Problem of area's zoning is very important and is one of the main problems of modern geographical... more Problem of area's zoning is very important and is one of the main problems of modern geographical science. Our point is to from a modern approach, based on the machine learning methods to provide zoning of any area. Key ideas of this methodology, that any distribution of factors that form any geographical system grouped around some clusters-unique zones that represents specific nature conditions. Formed methodology based on several stages-selection of data and objects for analysis, data normalization, assessment of predisposition of data for clustering, choosing the optimal number of clusters, clustering and validation of results. As an example, we tried to zone a surface layer of the Black Sea. We find that optimal number of unique zones is 3. Also, we find that the key driver of zone forming is a location of the rivers. Thus, we can say, that applying a machine learning approach in area's zoning tasks helps us increasing the quality of nature using and decision-making processes.
Современное развитие Керченского полуострова тесно связанно с масштабным техногенным воздействием... more Современное развитие Керченского полуострова тесно связанно с масштабным техногенным воздействием, что приводит к существенным изменениям в функционировании природных комплексов. В работе продемонстри-рован нейросетевой подход к изучению изменений состояния ландшафтного покрова и приняты попытки его прогнозирования. Моделирование проводилось на основании имеющихся данных о различных компонентах окружающей среды Керченского полуострова и антропогенных факторов, на них воздействующих. Анализ по-казал значительные изменения в ландшафтной составляющей полуострова, которые потенциально могут при-вести к ухудшению ситуации с проявлениями склоновых процессов.
Ключевые слова: ландшафтный покров, нейронная сеть, моделирование, ГИС, Керченский полуостров, склоно-вые процессы.
Safety in Technosphere, 2017
Modern approaches to the region’s landslide susceptibility assessment are considered in this pape... more Modern approaches to the region’s landslide susceptibility assessment are considered in this paper. Have been presented descriptions of the most used techniques for landslide susceptibility assessment: logistic regression, indicator validity, linear discriminant analysis and application of artificial neural networks. These techniques’ advantages and disadvantages are discussed in the paper. The most suitable techniques for various conditions of analysis have been marked. It has been concluded that the most acceptable techniques of analysis for a large number of input data related to the studied region are the method of logistic regression and indicator validity method. With these methods the most accurate results are achieved. When there is a lack of information, it is more expedient to use linear discriminant analysis and artificial neural networks that will minimize potential analysis inaccuracies.
Data
This study investigates the application of various machine learning models for land use and land ... more This study investigates the application of various machine learning models for land use and land cover (LULC) classification in the Kerch Peninsula. The study utilizes archival field data, cadastral data, and published scientific literature for model training and testing, using Landsat-5 imagery from 1990 as input data. Four machine learning models (deep neural network, Random Forest, support vector machine (SVM), and AdaBoost) are employed, and their hyperparameters are tuned using random search and grid search. Model performance is evaluated through cross-validation and confusion matrices. The deep neural network achieves the highest accuracy (96.2%) and performs well in classifying water, urban lands, open soils, and high vegetation. However, it faces challenges in classifying grasslands, bare lands, and agricultural areas. The Random Forest model achieves an accuracy of 90.5% but struggles with differentiating high vegetation from agricultural lands. The SVM model achieves an ac...
Anais do XIV Colóquio Internacional "Educação e Contemporaneidade" (EDUCON), 2020
RESUMO: Neste artigo abordo uma noção de corpo que percebo ser recorrente em diversos espaços de ... more RESUMO: Neste artigo abordo uma noção de corpo que percebo ser recorrente em diversos espaços de ensino da dança, a de que somos uma tábula rasa a ser preenchida passivamente por qualquer tipo de movimento. Essa crença em uma suposta neutralidade corporal, que desconsidera todos as informações sociais, genéticas e afetivas que nos atravessam, pode acarretar certo comportamento violento de professores, que muitas vezes sem perceber, acabam gerando bloqueios no processo de aprendizagem dos seus alunos. Esta escrita, que utiliza Pinker (2004), Katz (2005) e Greiner (2006) como principais referências, narra e analisa uma das minhas experiências como aluna e componente de um dos projetos de extensão do curso de Licenciatura em Dança da Universidade Federal de Sergipe (UFS). Palavras-chave: Corpo. Ensino-aprendizagem. Dança. RESUMEN: En este artículo abordo una noción de cuerpo que percibo recurrente en varios espacios de enseñanza de la danza, que somos uma tábula rasa que se llena pasivamente por cualquier tipo de movimiento. Esta creencia en una supuesta neutralidad corporal, que desconcidera todas las informaciones sociales, genéticas y afectivas que nos cruzan, puede conducir a un cierto comportamiento violento de los profesores, que a menudo sin darse cuenta, terminan generando bloqueos en el proceso de aprendizaje de sus alumnos. Esta escrita, que utiliza a Pinker (2004), Katz (2005) y Greiner (2006) como principales referencias, narra y analiza una de mis experiencias como estudiante y miembro de uno de los proyectos de extensión del Grado en Danza de
2022 Conference of Russian Young Researchers in Electrical and Electronic Engineering (ElConRus)
Fisheries
The Black Sea sprat Sprattus sprattus phalericus (Risso) and temperature factor impact have been ... more The Black Sea sprat Sprattus sprattus phalericus (Risso) and temperature factor impact have been investigated. Statistical assessment of the long-term dynamics (1951–2019) of a relationship between the temperature factor and sprat mean weight in fishery catches used as a population quality characteristic has been performed. Pearson product-moment correlation and cross-correlation was evaluated, then data series was smoothed by the local polynomial regression and, finally, a linear model was fitted. The correlation test shows significant relationship between the temperature factor and sprat mean weight-at-age (mean weight in 3+ age group and SST in the port of Yalta resulted in r = -0.86, whereas average SST and average mean weight by age classes led to r = -0.74). The fitted linear model by smoothed data of average SST and average weight-at-age successfully passed diagnostics (R2 = 0.87, RSE = 0.34), with the equation: w = f(sst) = 22.23 - 1.263*sst. As a result, this study allows t...
Journal of Marine Science and Engineering, 2022
Knowledge of the spatio-temporal distribution of salinity provides valuable information for under... more Knowledge of the spatio-temporal distribution of salinity provides valuable information for understanding different processes between biota and environment, especially in hypersaline lakes. Remote sensing techniques have been used for monitoring different components of the environment. Currently, one of the biggest challenges is the spatio-temporal monitoring of the salinity level in water bodies. Due to some limitations, such as the inability to be located there permanently, it is difficult to obtain these data directly. In this study, machine learning techniques were used to evaluate the salinity level in hypersaline East Sivash Bay. In total, 93 in situ data samples and 6 Sentinel-2 datasets were used, according to field measurements. Using linear regression, random forest and AdaBoost models, eight water salinity evaluation models were built (six with simple, one with random forest and one with AdaBoost). The accuracy of the best-fitted simple linear regression model was 0.8797;...
Ecology. Economy. Informatics.System analysis and mathematical modeling of ecological and economic systems, 2021
Preliminary study of impact of temperature factor to sprat quality characteristics in Russian wat... more Preliminary study of impact of temperature factor to sprat quality characteristics in Russian waters of the Black sea in period 1951–2019 was performed. In this research statistical hyphothesis about relationship between indicator sea surface temperature factor near to Chernomorskoe, Yalta, Feodosia and long-term sprat mean weight fishery statistics was done. Linear relationship hyphothesis performed by Pearson correlation test. Preliminary cross-correlation test results shows significant moderate relationship between temperature factor average and mean sprat weights (r = –0,60). After preliminary diagnostics input data was smoothed by polynomial regression to reduce interannual fluctuations and cross-correlation test to smoothed data was repeated. Correlation test by smoothed data indicate strong negative (r = –0,75) relationship between long-term sea surface temperature in all indicator points and mean sprat weights and high powerful relationship between sea surface temperature an...
Russian Journal of Earth Sciences, 2020
Russian Journal of Earth Sciences, 2020
Landslides are one of the most important problems on Kerch Peninsula. Rapidly increasing anthropo... more Landslides are one of the most important problems on Kerch Peninsula. Rapidly increasing anthropogenic pressure, which has been particularly could be seen in recent years, leads to destabilization of slopes and significant economic and social damage. Nowdays, economic activities for the further development of Kerch Peninsula, urbanization and the construction of new infrastructure facilities may lead to destabilization of slopes and activation of landslides. Application of an integrated mathematical model, helped us to reflect the current state of Kerch Peninsula in the context of solving this problem. With the help of field research, we mapped a complex of landslide areas, which made it possible to identify the main types of them occurring here-earth and earthwork slips landslides, and in the coastal zone-landfalls and caving slides, total area of which reaches 87.5 km 2 (7.4% of the research area territory). We chose an optimal method under the given conditions-the weight of evidence. The approach presented in this paper allows us to classify the territory according to the degree of its susceptibility to landslides with rather high accuracy and analyze the existing situation in this area and analyze possible scenarios for its development. We zoned the territory of the Kerch peninsula into 3 classes-stable, unstable and unsusceptible according to the degree of landslide probable occurrences. The susceptibility analysis revealed that the factors causing the activation of landslides on the Kerch Peninsula are the slope steepness from 20 to 40 degrees, the anthropogenic impact, excessive salinity of the soil cover and the lithological composition of the terrain.
Nauchno-tekhnicheskiy vestnik Bryanskogo gosudarstvennogo universiteta, 2018
Керченский государственный морской технологический университет (Керчь, Россия) Современное развит... more Керченский государственный морской технологический университет (Керчь, Россия) Современное развитие Керченского полуострова тесно связанно с масштабным техногенным воздействием, что приводит к существенным изменениям в функционировании природных комплексов. В работе продемонстрирован нейросетевой подход к изучению изменений состояния ландшафтного покрова и приняты попытки его прогнозирования. Моделирование проводилось на основании имеющихся данных о различных компонентах окружающей среды Керченского полуострова и антропогенных факторов, на них воздействующих. Анализ показал значительные изменения в ландшафтной составляющей полуострова, которые потенциально могут привести к ухудшению ситуации с проявлениями склоновых процессов.
Safety in Technosphere, 2017
Modern approaches to the region’s landslide susceptibility assessment are considered in this pape... more Modern approaches to the region’s landslide susceptibility assessment are considered in this paper. Have been presented descriptions of the most used techniques for landslide susceptibility assessment: logistic regression, indicator validity, linear discriminant analysis and application of artificial neural networks. These techniques’ advantages and disadvantages are discussed in the paper. The most suitable techniques for various conditions of analysis have been marked. It has been concluded that the most acceptable techniques of analysis for a large number of input data related to the studied region are the method of logistic regression and indicator validity method. With these methods the most accurate results are achieved. When there is a lack of information, it is more expedient to use linear discriminant analysis and artificial neural networks that will minimize potential analysis inaccuracies.
Economies
The article presents the sectoral structure of cruise (maritime) tourism and identifies the facto... more The article presents the sectoral structure of cruise (maritime) tourism and identifies the factors influencing the level of demand and supply of cruise tourism products. The sources of the influence of the cruise industry on the economic growth of the state and the welfare of its citizens are also considered. On the basis of specific features of cruise tourism functioning and the peculiarities of creating a cruise tourism product, a model of the functioning of a cruise (maritime) tourism complex has been built. Representation of the relationship of tourist needs according to the hierarchy of needs and a species classification of cruise tourism and the industries involved in its development is also given. The model of indicators and the structural components described are built in an environment of geoinformation modeling.
Climatic changes that have occurred over the past decades, with an acceleration of urbanization o... more Climatic changes that have occurred over the past decades, with an acceleration of urbanization of territories and technological development, leads to the significant changes not only in the atmosphere, but also in the Earth’s surface. Surface water bodies are one of these components. Today there are 3 main methods of monitoring water bodies -field, remote and combined. In this paper, we show the possibility of automating remote monitoring of water bodies using QGIS, Python and Sentinel-2 data of the main and largest lakes of the Kerch Peninsula. Having analysed both the available satellite data and the features of the study area, we came to the conclusion that it is advisable to use the NDWI index instead of the mNDWI. After processing and analysing the Sentinel-2 data for 2018 using the data processing model presented in the work, we obtained time series of changes in the areas of the studied lakes of the Kerch Peninsula.
Salinity is one of the most important factors that primarily determines the level of seawater’s d... more Salinity is one of the most important factors that primarily determines the level of seawater’s density and, consequently, the movement of water masses in the World Ocean. Spatial distribution of the salinity in different layers of the Black Sea are associated with varying levels of water balance seasonal variability and, general circulation of Black Seas waters and in the surface layer has a seasonal structure. To study spatial distribution of salinity in upper layers of the Black Sea we’ve used data from Copernicus Marine Environment Monitoring Service, that were processed and aggregate by seasons and depth. We found that the most fluctuated layer is a top layer (up to 2.8 m) and the highest values Black Sea salinity reaches near the Bosporus Strait, where more saline water from the Sea of Marmara connected with fresher water of the Black Sea. Also we found that the impact of the river flows, mixing of the water, water regime of the sea decreasing with depth, so in the bottom of t...
Russian Journal of Earth Sciences
Aquatic ecosystems of the Black Sea are complex multiparametric systems with a hierarchical struc... more Aquatic ecosystems of the Black Sea are complex multiparametric systems with a hierarchical structure. Thus, the main goal of our research was to investigate possibilities of using Bayesian networks to study the structure fo the natural systems in the Black Sea. We used CMEMS Black Sea environmental dataset, which consists of 7 different variables, that, in our opinion, can describe structural relations in the Black Sea ecosystem -- sea surface temperature and salinity, concentrations of nitrates and phosphates, amount of chlorophyll-a and net primary production and also dissolved oxygen concentration. We think, that these variables can generally define interactions in water environment of the Black Sea, organisms, that live there and human activity. As a modelling result, we receive a structure of environmental variables interactions. At the top of this structure is a dissolved oxygen, as a final result of the ecosystem functioning. Further, we think it's more appropriate to us...
Landslides are one of the most important problems on Kerch Peninsula. Rapidly increasing anthropo... more Landslides are one of the most important problems on Kerch Peninsula. Rapidly increasing anthropogenic pressure, which has been particularly could be seen in recent years, leads to destabilization of slopes and significant economic and social damage. Nowdays, economic activities for the further development of Kerch Peninsula, urbanization and the construction of new infrastructure facilities may lead to destabilization of slopes and activation of landslides. Application of an integrated mathematical model, helped us to reflect the current state of Kerch Peninsula in the context of solving this problem. With the help of field research, we mapped a complex of landslide areas, which made it possible to identify the main types of them occurring here-earth and earthwork slips landslides, and in the coastal zone-landfalls and caving slides, total area of which reaches 87.5 km 2 (7.4% of the research area territory). We chose an optimal method under the given conditions-the weight of evidence. The approach presented in this paper allows us to classify the territory according to the degree of its susceptibility to landslides with rather high accuracy and analyze the existing situation in this area and analyze possible scenarios for its development. We zoned the territory of the Kerch peninsula into 3 classes-stable, unstable and unsusceptible according to the degree of landslide probable occurrences. The susceptibility analysis revealed that the factors causing the activation of landslides on the Kerch Peninsula are the slope steepness from 20 to 40 degrees, the anthropogenic impact, excessive salinity of the soil cover and the lithological composition of the terrain. KEYWORDS: Landslides; landslide susceptibility; GIS; spatial analysis; landslide zoning. Citation: Krivoguz, Denis and Liudmila Bespalova (2019), Landslide susceptibility analysis for the Kerch Peninsula using weights of evidence approach and GIS, Russ.
Problem of area's zoning is very important and is one of the main problems of modern geographical... more Problem of area's zoning is very important and is one of the main problems of modern geographical science. Our point is to from a modern approach, based on the machine learning methods to provide zoning of any area. Key ideas of this methodology, that any distribution of factors that form any geographical system grouped around some clusters-unique zones that represents specific nature conditions. Formed methodology based on several stages-selection of data and objects for analysis, data normalization, assessment of predisposition of data for clustering, choosing the optimal number of clusters, clustering and validation of results. As an example, we tried to zone a surface layer of the Black Sea. We find that optimal number of unique zones is 3. Also, we find that the key driver of zone forming is a location of the rivers. Thus, we can say, that applying a machine learning approach in area's zoning tasks helps us increasing the quality of nature using and decision-making processes.
Современное развитие Керченского полуострова тесно связанно с масштабным техногенным воздействием... more Современное развитие Керченского полуострова тесно связанно с масштабным техногенным воздействием, что приводит к существенным изменениям в функционировании природных комплексов. В работе продемонстри-рован нейросетевой подход к изучению изменений состояния ландшафтного покрова и приняты попытки его прогнозирования. Моделирование проводилось на основании имеющихся данных о различных компонентах окружающей среды Керченского полуострова и антропогенных факторов, на них воздействующих. Анализ по-казал значительные изменения в ландшафтной составляющей полуострова, которые потенциально могут при-вести к ухудшению ситуации с проявлениями склоновых процессов.
Ключевые слова: ландшафтный покров, нейронная сеть, моделирование, ГИС, Керченский полуостров, склоно-вые процессы.
Safety in Technosphere, 2017
Modern approaches to the region’s landslide susceptibility assessment are considered in this pape... more Modern approaches to the region’s landslide susceptibility assessment are considered in this paper. Have been presented descriptions of the most used techniques for landslide susceptibility assessment: logistic regression, indicator validity, linear discriminant analysis and application of artificial neural networks. These techniques’ advantages and disadvantages are discussed in the paper. The most suitable techniques for various conditions of analysis have been marked. It has been concluded that the most acceptable techniques of analysis for a large number of input data related to the studied region are the method of logistic regression and indicator validity method. With these methods the most accurate results are achieved. When there is a lack of information, it is more expedient to use linear discriminant analysis and artificial neural networks that will minimize potential analysis inaccuracies.
CURRENT VIEW ON IMPACT OF SEISMICITY ON LANDSLIDES OF THE KERCH PENINSULA
This article discusses the modern view on seismic activity on the Kerch peninsula. Author shows t... more This article discusses the modern view on seismic activity on the Kerch peninsula. Author shows the short historical brief with most destructive events linked with seismic activity. Also article analyze modern researches to show the level of impact of seismicity on different geological processes, especially landslides, in this region.
This article aims to study the impact of human activities on the stability of the population and ... more This article aims to study the impact of human activities on the stability of the population and its property. Since the lower reaches of the Dniester is largely regulated it has a significant impact on existing species there. As used in this article is a method to evaluate the viability of the population, based on the statistical Monte-Carlo methods, allowing you to fully evaluate and predict the reaction of the population to the human factors. The analysis was conducted based on three possible scenarios of development of the situation, due to the receipt of environmental flows in the delta of the Dniester. As a result, we can see that the stable functioning of population Abramis brama L. possible only in full compliance with environmental requirements for the users of natural resources, carrying out its activities in the area.