Search

Several changes have occurred in the river environment of Nakdong river due to the construction of multifunctional weirs as part of the Four Major Rivers Project. This river currently exhibits characteristics that are similar to those of a stagnant water area in which the river depth increases and the flow velocity decreases. Consequently, blue-green algae are frequently observed. Toxic substances secreted by blue-green algae are harmful to aquatic ecosystems and the human body; therefore, ensuring the stability of the water quality of Nakdong river is of utmost importance. Various factors are associated with the occurrence of blue-green algae. Therefore, the causal relationship between these causative factors must be identified. In this study, we investigated factors influencing algal growth, such as water quality, hydraulics, and weather, and algal occurrence patterns by site were analyzed. Recent studies have used data mining and machine-learning techniques in algal management to quantitatively identify the characteristics of blue-green algae. In machine learning, the prediction results differ depending on the selection of parameters, which are an important aspect in the management of blue-green algae with complex causes. In this study, we quantitatively analyzed the conditions for the occurrence of cyanobacteria according to the influencing factors using decision trees and random forests, which are machine-learning techniques, along with an analysis of the major complex factors influencing the occurrence of blue-green algae in the Nakdong river weirs. Considering the water quality and hydraulic factors, we analyzed the characteristics of algal generation in each weir at different hydraulic volume times. In addition, we investigated the possibility of improving the accuracy of cyanobacterial prediction according to the learning factors. Through these analyses, we attempted to study the characteristics of blue-green algae in stagnant rivers.

A multifunctional weir was built on the Nakdong River. As a result, changes in the river environment occurred, such as an increase in river residence time. This causes changes in water quality, including green algae. The occurrence of green algae in the Nakdong River, which is used as a water source, also affects the purified water supply system. In particular, the mass spread of harmful algae is becoming a major problem as the frequency and intensity of occurrences increase. There are various causes of blue-green algae. We would like to examine the relationships between causal factors through a decision tree-based algorithm. Additionally, we would like to predict the occurrence of green algae based on the combination of these factors. For prediction, we studied categorical prediction based on the blue-green algae warning system used in Korea. RF, Catboost and XGBoost algorithms were used. Optimal hyperparameters were applied. We compared the prediction performance of each algorithm. In addition, the predictability of using sensor-based data was reviewed for a preemptive response to the occurrence of blue-green algae. By applying sensor-based data, the accuracy was over 80%. Prediction accuracy by category was also over 75%. It is believed that real-time prediction is possible through sensor-based factors. The optimal forecast period was analyzed to determine whether a preemptive response was possible and the possibility of improvement was examined through the segmentation of prediction categories. When there were three categories, 79% of predictions were possible by the 21st day. In seven categories, 75% prediction was possible up to 14 days. In this study, sensor-based categorical predictability was derived. In addition, real-time response and proactive response were determined. Such sensor-based algae prediction research is considered important for future blue-green algae management and river management.