Балл 0
Отсутствует экспертное заключение на публикацию
КБПР (методика 2025 г.) = 2.5
Количество соавторов публикации - 8
Публикация в изданиях из Белого списка уровень: 1, K=20
Публикация в изданиях из Белого списка уровень: 1, K=20
-
Шадрин Н. В.: количество аффилиаций - 1, вклад в КБПР публикации:
формула: K/(Nсоавторов*Nаффил) = 20/(8*1) = 2.5
Статья в периодическом издании
Computer Vision-Assisted Semiautomatic Analysis of Zooplankton in a Longitudinal Study of the Ecological State of Lake Baikal
WoS 3.500/Q1 SCOPUS 0.928/Q1 БС 1
| DOI | https://doi.org/10.3390/biology15090695 |
|---|---|
| Язык | Английский |
| Журнал | Biology ISSN: —; Онлайн ISSN: 2079-7737 |
| Год | 2026 |
| Выходные данные | том: 15; выпуск: 9; статья: 695; страниц (электронный ресурс): 13 |
| Авторы | |
| Даты |
Поступила в редакцию: 19.03.2026 После доработки: 20.04.2026 Принята к публикации: 27.04.2026 Опубликована: 29.04.2026 |
| Абстракт | Studying zooplankton in freshwater ecosystems is crucial for ecological research, providing insight into ecosystem health, biodiversity, and water quality. This study focuses on developing a hybrid approach for studying and analyzing zooplankton communities using machine learning and human expert analysis. The goal of the study was to automate the labor-intensive process of zooplankton analysis as part of a long-term Lake Baikal monitoring program (since 1945), while maintaining continuity with traditional methods. A software and algorithmic system were developed to automate the analysis: images were processed using a two-stage pipeline (object detection using YOLO V11, classification using metric learning and visual transformers), and complex cases and new species were sent to specialists for verification. Over 240,000 images from 811 samples were processed, and models are updated using verified data to adapt to seasonal changes. An updatable database of labeled zooplankton images suitable for statistical analysis and research has been created. A comparison of manual and machine analysis revealed no significant differences in species composition, with accurate detection in 87% of images. This approach allows for scalable monitoring and the accumulation of labeled data arrays for the development of computer vision methods and the assessment of the state of Lake Baikal’s ecosystem. Ключевые слова: Lake Baikal, zooplankton, deep neural networks, metric learning, human-in-the-loop, computer vision |
| Сведения о финансировании, указанные в публикации | This research was funded by the Yandex.Cloud company, the Russian Science Foundation (RSF grant number 24-66-00001, https://rscf.ru/project/24-66-00001/, accessed on 26 April 2026), the Ministry of Education of the Russian Federation within the project #FZZE-2026-0004 for data analysis and article writing as well as by the Foundation for Support of Applied Ecological Studies «Lake Baikal» (https://baikalfoundation.ru/project/tochka-1/, accessed on 26 April 2026) for monitoring works. |
| URL | https://www.mdpi.com/2079-7737/15/9/695 |
| Дополнительные сведения |
Запись создана: 04-05-2026 16:40
Последнее изменение: 05-05-2026 08:30
Библиографическая ссылка:
Rusanovskaya O. O., Oreshkov S. S., Demidova A. A., Rzhepka T. P., Silow E. A., Shadrin N. V., Shimaraeva S. V., Timofeyev M. A. Computer Vision-Assisted Semiautomatic Analysis of Zooplankton in a Longitudinal Study of the Ecological State of Lake Baikal // Biology. 2026. Vol. 15, iss. 9. Art. no. 695 (13 p.). https://doi.org/10.3390/biology15090695
[WoS 3.500/Q1][SCOPUS 0.928/Q1][БС 1]
Rusanovskaya O. O., Oreshkov S. S., Demidova A. A., Rzhepka T. P., Silow E. A., Shadrin N. V., Shimaraeva S. V., Timofeyev M. A. Computer Vision-Assisted Semiautomatic Analysis of Zooplankton in a Longitudinal Study of the Ecological State of Lake Baikal // Biology. 2026. Vol. 15, iss. 9. Art. no. 695 (13 p.). https://doi.org/10.3390/biology15090695
[WoS 3.500/Q1][SCOPUS 0.928/Q1][БС 1]
Экспертное заключение: –
Белый список
Индексация на момент включения в базу:- Уровень БС
- 1
Web of Science
- Статус
- Да
- Импакт-фактор/Квартиль(год)
- 3.500/Q1 (2024)
- Идентификатор
- –
- Статус
- Да
- Импакт-фактор/Квартиль(год)
- 0.928/Q1 (2025)
- Идентификатор
- –
- Статус
- Нет
- ID
- –
- EDN
- –