O. V. Kolgunova
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
O. V. Kolgunova has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Denis A. Solomakha
Don State Technical University
1 shared publication - I. A. Usenko
Don State Technical University
1 shared publication - M. I. Gabuyeva
North Ossetian State Medical Academy
1 shared publication - Yulia Valerievna Belova
Don State Technical University
1 shared publication Д. А. Соломаха
Донской государственный технический университет
1 shared publicationИ. А. Усенко
Донской государственный технический университет
1 shared publication
Latest Publications
- Open Access
- 1 October 2026
- Published by FSFEI HE Don State Technical University in COMPUTATIONAL MATHEMATICS AND INFORMATION TECHNOLOGIES
- Vol. 10 (3) , 41-48
Comparative Analysis of the Effectiveness of Petroleum-Product Contamination Detection in Aquatic Systems Using Pre-Trained YOLO-Family Neural Network Models and the SMDNetV4 and PSPNet Architectures
Introduction . The PSPNet, SMD-Net, and YOLO26-Seg semantic segmentation architectures are considered for the task of detecting oil spills in satellite imagery. Particular attention is paid to comparing segmentation accuracy under identical training conditions. Materials and Methods . PSPNet uses a ResNet101 backbone with a pyramid pooling module for semantic segmentation. SMD-Net is a lightweight shared-backbone architecture with two decoders and CTGM, CoordAtt, and ASPP modules. YOLO26-Seg combines a YOLO26 encoder backbone with fixed weights and a lightweight decoder. The following metrics are compared: IoU (Intersection over Union), defined as the ratio of the intersection of the predicted and ground-truth regions to their union; Dice (Dice coefficient), a measure of segment overlap based on the intersection area; accuracy, the proportion of correct predictions among all predictions; inference time, the time required by the model to process one input; and the number of trainable parameters. Results . After 50 epochs of training on the existing dataset masks without manual annotation, PSPNet significantly outperformed SMD-Net in binary oil-spill segmentation (IoU = 0.704, Dice = 0.770, Acc = 0.896 versus IoU = 0.467, Dice = 0.575, Acc = 0.671 for SMD-Net). The additionally fine-tuned YOLO26l-seg model demonstrated moderate pixellevel metrics (IoU = 0.320) at a reduced detection threshold, which limits its applicability to this task. Discussion . The choice of architecture for oil-spill segmentation is governed by a trade-off between accuracy and speed: PSPNet provides the highest segmentation quality, SMD-Net performs worse across all metrics, and YOLO26-SemSeg cannot reliably detect oil spills without task-specific training. Conclusion . PSPNet significantly outperforms SMD-Net and YOLO26-Seg in binary oil-spill segmentation under identical training conditions (IoU = 0.704 versus 0.467 for SMD-Net), confirming the effectiveness of the ResNet101 backbone combined with pyramid pooling.
- 1 October 2026
- Published by FSFEI HE Don State Technical University in COMPUTATIONAL MATHEMATICS AND INFORMATION TECHNOLOGIES
- Vol. 10 (3) , 41-48
Open AccessComparative Analysis of the Effectiveness of Petroleum-Product Contamination Detection in Aquatic Systems Using Pre-Trained YOLO-Family Neural Network Models and the SMDNetV4 and PSPNet Architectures
Introduction . The PSPNet, SMD-Net, and YOLO26-Seg semantic segmentation architectures are considered for the task of detecting oil spills in satellite imagery. Particular attention is paid to comparing segmentation accuracy under identical training conditions. Materials and Methods . PSPNet uses a ResNet101 backbone with a pyramid pooling module for semantic segmentation. SMD-Net is a lightweight shared-backbone architecture with two decoders and CTGM, CoordAtt, and ASPP modules. YOLO26-Seg combines a YOLO26 encoder backbone with fixed weights and a lightweight decoder. The following metrics are compared: IoU (Intersection over Union), defined as the ratio of the intersection of the predicted and ground-truth regions to their union; Dice (Dice coefficient), a measure of segment overlap based on the intersection area; accuracy, the proportion of correct predictions among all predictions; inference time, the time required by the model to process one input; and the number of trainable parameters. Results . After 50 epochs of training on the existing dataset masks without manual annotation, PSPNet significantly outperformed SMD-Net in binary oil-spill segmentation (IoU = 0.704, Dice = 0.770, Acc = 0.896 versus IoU = 0.467, Dice = 0.575, Acc = 0.671 for SMD-Net). The additionally fine-tuned YOLO26l-seg model demonstrated moderate pixellevel metrics (IoU = 0.320) at a reduced detection threshold, which limits its applicability to this task. Discussion . The choice of architecture for oil-spill segmentation is governed by a trade-off between accuracy and speed: PSPNet provides the highest segmentation quality, SMD-Net performs worse across all metrics, and YOLO26-SemSeg cannot reliably detect oil spills without task-specific training. Conclusion . PSPNet significantly outperforms SMD-Net and YOLO26-Seg in binary oil-spill segmentation under identical training conditions (IoU = 0.704 versus 0.467 for SMD-Net), confirming the effectiveness of the ResNet101 backbone combined with pyramid pooling.
- Open Access
- 30 December 2025
- Published by FSFEI HE Don State Technical University in COMPUTATIONAL MATHEMATICS AND INFORMATION TECHNOLOGIES
- Vol. 9 (4) , 56-67
Mathematical Modelling of Green Microalgae Invasion and Rehabilitation of the Taganrog Bay: Ecological-Hygienic and Medical Consequences
Introduction. The Taganrog Bay of the Azov Sea is one of the most eutrophic and ecologically vulnerable water areas in Russia, where massive blooms of toxic cyanobacteria (Microcystis, Aphanizomenon, Anabaena, Nodularia) regularly occur during summer. Their proliferation is accompanied by the accumulation of cyanotoxins (microcystin, anatoxin, cylindrospermopsin, saxitoxin), posing a serious threat to public health. This paper considers an approach to the biological rehabilitation of the bay based on the controlled introduction of the freshwater green microalgae Chlorella vulgaris, which competes with cyanobacteria for nutrients. The aim of the study is to develop and apply a comprehensive mathematical model describing phytoplankton kinetics and substance transport processes under conditions of increasing bay salinity, as well as to assess the ecological-hygienic and medical consequences of the proposed method. Materials and Methods. The research object is the Taganrog Bay of the Azov Sea. The modelling is based on the threedimensional hydrodynamic model “Azov3D”, previously used to calculate currents and vertical mixing under conditions of changing salinity. Water environment parameters (salinity, temperature, current velocities) were used as input data for solving the linearized hydrobiological problem. The source of bathymetric data was digitized nautical charts processed using automated depth recognition algorithms. The model grid was generated considering the actual coastline configuration and bottom topography. Calculations were performed on the computing cluster of the Southern Federal University. The numerical method is based on finite-difference schemes previously applied for hydrobiological calculations in the Azov Sea. Results. It is shown that a 30% increase in salinity leads to a shift in the cyanobacteria habitat from the Azov Sea water area to the eastern part of the Taganrog Bay, which is consistent with hydrological observations. Model calculations demonstrate an increase in the proportion of green algae with the controlled introduction of Chlorella vulgaris cultures, reflecting the potential for biomelioration. The forecast of the spatial distribution of populations shows stable dominance of green and blue-green algae, constituting 60−70% of the bay’s phytoplankton biomass, under various impact scenarios. Discussion. The results indicate that mathematical modelling is an effective tool for predicting the dynamics of phytoplankton populations under changing hydrological conditions. The model allows for assessing the influence of biological regulation and salinization scenarios, providing a basis for management decisions in the field of ecological rehabilitation of water bodies. Conclusion. The application of Chlorella vulgaris may be a promising biomelioration method but requires further verification based on field observations and controlled field experiments. The modelling results indicate the possibility of adaptive ecological management of the Taganrog Bay and minimizing the risk of toxic blooms.
- 30 December 2025
- Published by FSFEI HE Don State Technical University in COMPUTATIONAL MATHEMATICS AND INFORMATION TECHNOLOGIES
- Vol. 9 (4) , 56-67
Open AccessMathematical Modelling of Green Microalgae Invasion and Rehabilitation of the Taganrog Bay: Ecological-Hygienic and Medical Consequences
Introduction. The Taganrog Bay of the Azov Sea is one of the most eutrophic and ecologically vulnerable water areas in Russia, where massive blooms of toxic cyanobacteria (Microcystis, Aphanizomenon, Anabaena, Nodularia) regularly occur during summer. Their proliferation is accompanied by the accumulation of cyanotoxins (microcystin, anatoxin, cylindrospermopsin, saxitoxin), posing a serious threat to public health. This paper considers an approach to the biological rehabilitation of the bay based on the controlled introduction of the freshwater green microalgae Chlorella vulgaris, which competes with cyanobacteria for nutrients. The aim of the study is to develop and apply a comprehensive mathematical model describing phytoplankton kinetics and substance transport processes under conditions of increasing bay salinity, as well as to assess the ecological-hygienic and medical consequences of the proposed method. Materials and Methods. The research object is the Taganrog Bay of the Azov Sea. The modelling is based on the threedimensional hydrodynamic model “Azov3D”, previously used to calculate currents and vertical mixing under conditions of changing salinity. Water environment parameters (salinity, temperature, current velocities) were used as input data for solving the linearized hydrobiological problem. The source of bathymetric data was digitized nautical charts processed using automated depth recognition algorithms. The model grid was generated considering the actual coastline configuration and bottom topography. Calculations were performed on the computing cluster of the Southern Federal University. The numerical method is based on finite-difference schemes previously applied for hydrobiological calculations in the Azov Sea. Results. It is shown that a 30% increase in salinity leads to a shift in the cyanobacteria habitat from the Azov Sea water area to the eastern part of the Taganrog Bay, which is consistent with hydrological observations. Model calculations demonstrate an increase in the proportion of green algae with the controlled introduction of Chlorella vulgaris cultures, reflecting the potential for biomelioration. The forecast of the spatial distribution of populations shows stable dominance of green and blue-green algae, constituting 60−70% of the bay’s phytoplankton biomass, under various impact scenarios. Discussion. The results indicate that mathematical modelling is an effective tool for predicting the dynamics of phytoplankton populations under changing hydrological conditions. The model allows for assessing the influence of biological regulation and salinization scenarios, providing a basis for management decisions in the field of ecological rehabilitation of water bodies. Conclusion. The application of Chlorella vulgaris may be a promising biomelioration method but requires further verification based on field observations and controlled field experiments. The modelling results indicate the possibility of adaptive ecological management of the Taganrog Bay and minimizing the risk of toxic blooms.