No 3 (2021)
Articles
Identification of Baikal phytoplankton inferred from computer vision methods and machine learning
Abstract
This study discusses the problem of phytoplankton classification using computer vision methods and convolutional neural networks. We created a system for automatic object recognition consisting of two parts: analysis and primary processing of phytoplankton images and development of the neural network based on the obtained information about the images. We developed software that can detect particular objects in images from a light microscope. We trained a convolutional neural network in transfer learning and determined optimal parameters of this neural network and the optimal size of using dataset. To increase accuracy for these groups of classes, we created three neural networks with the same structure. The obtained accuracy in the classification of Baikal phytoplankton by these neural networks was up to 80%.
1143-1146
Optical characteristics of water at the mouth of the Ob River
Abstract
As a result of the field studies (August 25 – September 1, 2020), new data were obtained on the optical characteristics of water at the Ob River mouth near the Salemal village (Yamal region, Yamal-Nenets Autonomous Okrug) during the lowest water level and the maximum development of hydrobiocenoses. We calculated the light attenuation coefficient Ɛ(λ) in the spectral range from 400 to 800 nm, which varied from 1.5 to 21.5 m–1 during the study period, and the light absorption by yellow substance κys(λ) from 0.1 to 12.2 m–1. Concentrations of yellow substance Cys and chlorophyll а Chl were determined. For instance, chlorophyll а concentrations in water samples taken at different stations of the Ob River ranged from 12.5 to 22.7 mg∙m–3. The maximum content of chlorophyll а in our case was recorded at a depth of 14 m (station 5.3), which was 22.7 mg∙m–3. The yellow substance concentration determined optically by the calculated yellow substance light absorption coefficient at wavelength λ=450 nm ranged within 18.8 and 26.9 g∙m–3 with an average value of 22.1 g∙m–3. The average value of κys(λ) at λ=450 nm over the study period was 4.7 m–1.
1147-1151
Length-weight relationship and condition factor of endemic genus Seminemacheilus (Teloestei=Nemacheilidae) for Turkey
Abstract
This study was aimed to determine the length-weight relationships and Fulton’s condition factors of the genus Seminemacheilus that is endemic for Turkey. The specimens were collected from 2017 to 2019 using an electrofishing device (SAMUS 1000MP). The total length and the total weight of the examined specimens ranged from 3.5 to 9.1 cm and from 0.31 to 7.52 g, respectively. Based on the results, the growth coefficient values b ranged from 2.56 (S. ispartensis) to 3.48 (S. attalicus). Also, the condition factor of the studied fishesranged from 0.77 (S. dursunavsari) to 1.11 (S. attalicus). This study represents the first reports of length-weight relationship data for S. ahmeti, S. attalicus, S. dursunavşari, S. ekmekciae, and S. ispartensis from Turkish inland waters and four new maximum total lengths for the Seminemacheilus species. The results of this study provide useful information for further fisheries management, fish population dynamic studies and comparisons in future studies.
1152-1155