No abstract

The resting stages of phytoplankton are usually regarded as the seed bank and source of harmful algal blooms because of the recruitment of phytoplankton from sediment to the water column under suitable environmental conditions. Information about resting stages of phytoplankton is abundant in shallow lakes and littoral sea; yet, studies on river–reservoir systems are rare. The river–reservoir continuum shows a unique structuring of longitudinal gradients of hydrological and hydrodynamic conditions. We hypothesized that the seed bank and algal blooms in reservoirs are influenced by the hydrodynamic conditions of each reservoir. We used Illumina Miseq sequencing to examine the spatio-temporal variation in the phytoplankton community in the sediment as reservoir drawdown and in surface water during algal blooms in Pengxi River, a tributary of China’s Three Gorges Reservoir. The results show that the cyanobacteria community in sediment is significantly influenced by temperature, total carbon, maximum flow velocity, and total phosphorous, the eukaryotic phytoplankton community in sediment is significantly influenced by total phosphorous, temperature, total carbon, maximum flow velocity, and total nitrogen. Additionally, the dominant species in sediment is significantly different from that in surface water during algal blooms. Our results suggest that the dominant species in surface water during algal blooms is more influenced by the environmental factors and hydrodynamic conditions in the water column than the seeds in the sediment. These findings are fundamental for further research on the influence of hydrodynamic conditions on algal blooms in artificially regulated river-reservoir systems.

No abstract

No abstract

The variations in algal diversity and populations are essential for evaluating aquatic system health. However, manual classification is time-consuming and labor-intensive. As AI has shown its capacity in face identification and would be possible for algal identification, we developed a deep convolutional neural network (CNN) algorithm for the accurate identification and classification of algae. Results showed that a fractional threshold at 0.6 ensured a good balance between precision, recall, and F1_score. Furthermore, the corresponding confusion matrix showed that the lowest probability for classifying algal species was 93.9%, indicating the high classification capacity of the CNN, which was supported by receiver operating characteristics. In contrast, conventional extensive sampling activities for establishing an algal database of publicly available algal images ensured a good training of the CNN, showing the robustness of the CNN. This study proved that the applied CNN can achieve an efficient and accurate algal classification. Therefore, our developed CNN approach is a successful pioneer for building advanced identification and classification systems with broad applications for aquatic system protection.