The Adaptive-Clustering and Error-Correction Method for Forecasting Cyanobacteria Blooms in Lakes and Reservoirs

Abstract

Globally, cyanobacteria blooms frequently occur, and effective prediction of cyanobacteria blooms in lakes and reservoirs could constitute an essential proactive strategy for water-resource protection. However, cyanobacteria blooms are very complicated because of the internal stochastic nature of the system evolution and the external uncertainty of the observation data. In this study, an adaptive-clustering algorithm is introduced to obtain some typical operating intervals. In addition, the number of nearest neighbors used for modeling was optimized by particle swarm optimization. Finally, a fuzzy linear regression method based on error-correction was used to revise the model dynamically near the operating point. We found that the combined method can characterize the evolutionary track of cyanobacteria blooms in lakes and reservoirs. The model constructed in this paper is compared to other cyanobacteria-bloom forecasting methods (e.g., phase space reconstruction and traditional-clustering linear regression), and, then, the average relative error and average absolute error are used to compare the accuracies of these models. The results suggest that the proposed model is superior. As such, the newly developed approach achieves more precise predictions, which can be used to prevent the further deterioration of the water environment.

Modelling Microcystis Cell Density in a Mediterranean Shallow Lake of Northeast Algeria (Oubeira Lake), Using Evolutionary and Classic Programming

“…However, the choice of the different parameters of the SVM has a significant impact on the reliability of the SVM classification. Nevertheless, it is very complicated to choose the most adequate SVM parameters [49] because of the complexity of the cyanobacteria bloom process [5]. This may not only explain the discrepancies observed between SVM and PSO but also between the applied techniques, which were certainly caused by several factors influencing Microcystis densities that are not included in current models.…”

“…However, the highly complex nonlinearity of water variables and their interactions make blooms difficult to model [4]. The bloom process is a complex dynamic system of multi-dimensional coordination associated with multiple factors, with a high, intrinsic non-linear dissipative structuring [5]. They are highly variable, and the parameters involved in their occurrence are unstable [6].…”

A combination prediction model based on ELM and prior information of shapelet for algal bloom

“…where α 2 is regularization parameter. Eqn ( 9) is the solution of eqn (8). FCM can reduce the number of fuzzy rules, so it can effectively improve the efficiency of the algorithm.…”

“…The data-driven model built for the time series prediction model becomes increasingly, which could effectively learn implicit laws from historical data with good generalization capabilities [8,9]. Machine learning and deep learning algorithms have been applied to successfully improve prediction accuracy of the data-driven model with time series [6,10,11].…”