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

Advances in Mathematical Physics

Research Article

Jia-bin Yu¹  Ji-ping Xu¹  Li Wang¹  Xiao-yi Wang¹  Hui-yan Zhang¹  Xiao-zhe Bai¹ 

[1] School of Computer and Information Engineering, Beijing Technology and Business University, Beijing 100048, China, btbu.edu.cn

Others  :  1420190
DOI  :  10.1155/2017/9037358

 received in 2016-12-20, accepted in 2017-04-13,  发布年份 2017

【 摘 要 】

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.

【 授权许可】

CC BY   
Copyright © 2017 Xiao-zhe Bai et al. 2017

【 图 表 】

Figure 1

(a)

(b)

(c)

(d)

Figure 3

Figure 4

【 参考文献 】

• [1]B. W. Ibelings, M. Bormans, J. Fastner, P. M. Visser. et al.(2016). CYANOCOST special issue on cyanobacterial blooms: synopsis—a critical review of the management options for their prevention, control and mitigation. Aquatic Ecology.50:595-605. DOI: 10.1007/s10452-016-9596-x.
• [2]L. S. Chen. (1993). Nonlinear Biodynamic System. DOI: 10.1007/s10452-016-9596-x.
• [3]B. Q. Qin, G. J. Yang, J. R. Ma. (2016). Dynamics of variability and mechanism of harmful cyanobacteria bloom in Lake Taihu, China. Kexue Tongbao/Chinese.61(7):759-770. DOI: 10.1007/s10452-016-9596-x.
• [4]X. Y. Wang. Chaotic time series prediction method of algal bloom in urban lake and reservoir based on complex network. . DOI: 10.1007/s10452-016-9596-x.
• [5]P. R. L. Alves, L. G. S. Duarte, L. A. C. P. D. Mota. (2016). Improvement in global forecast for chaotic time series. Computer Physics Communications.207:325-340. DOI: 10.1007/s10452-016-9596-x.
• [6]Q.-F. Meng, Y.-H. Peng, J. Sun. (2007). The improved local linear prediction of chaotic time series. Chinese Physics.16(11):3220-3225. DOI: 10.1007/s10452-016-9596-x.
• [7]L. Su, C. Li. (2015). Local prediction of chaotic time series based on polynomial coefficient autoregressive model. Mathematical Problems in Engineering.2015-14. DOI: 10.1007/s10452-016-9596-x.
• [8]M. N. Islam, B. Sivakumar. (2002). Characterization and prediction of runoff dynamics: a nonlinear dynamical view. Advances in Water Resources.25(2):179-190. DOI: 10.1007/s10452-016-9596-x.
• [9]G. Heydari, M. Vali, A. A. Gharaveisi. (2016). Chaotic time series prediction via artificial neural square fuzzy inference system. Expert Systems with Applications.55:461-468. DOI: 10.1007/s10452-016-9596-x.
• [10]P. L. Gentili, H. Gotoda, M. Dolnik, I. R. Epstein. et al.(2015). Analysis and prediction of aperiodic hydrodynamic oscillatory time series by feed-forward neural networks, fuzzy logic, and a local nonlinear predictor. Chaos. An Interdisciplinary Journal of Nonlinear Science.25(1). DOI: 10.1007/s10452-016-9596-x.
• [11]H. Wang, F. Sun, Y. Cai, Z. Zhao. et al.(2010). Online chaotic time series prediction using unbiased composite kernel machine via Cholesky factorization. Soft Computing.14(9):931-944. DOI: 10.1007/s10452-016-9596-x.
• [12]H. Tongal, R. Berndtsson. (2014). Phase-space reconstruction and self-exciting threshold modeling approach to forecast lake water levels. Stochastic Environmental Research & Risk Assessment.28(4):955-971. DOI: 10.1007/s10452-016-9596-x.
• [13]S. Kermani, N. Samadzadehaghdam, M. EtehadTavakol. (2015). Automatic color segmentation of breast infrared images using a Gaussian mixture model. Optik.126(21):3288-3294. DOI: 10.1007/s10452-016-9596-x.
• [14]R. C. de Amorim, C. Hennig. (2015). Recovering the number of clusters in data sets with noise features using feature rescaling factors. Information Sciences.324:126-145. DOI: 10.1007/s10452-016-9596-x.
• [15]G. Chen, S. A. Jaradat, N. Banerjee, T. S. Tanaka. et al.(2002). Evaluation and comparison of clustering algorithms in analyzing {ES} cell gene expression data. Statistica Sinica.12(1):241-262. DOI: 10.1007/s10452-016-9596-x.
• [16]H. Guo, X. Liu, Z. Sun. (2016). Multivariate time series prediction using a hybridization of {VARMA} models and Bayesian networks. Journal of Applied Statistics.43(16):2897-2909. DOI: 10.1007/s10452-016-9596-x.
• [17]Y. Liu, X. J. Zhang, X. M. Guan, D. Delahaye. et al.(2016). Potential odor intensity grid based uav path planning algorithm with particle swarm optimization approach. Mathematical Problems in Engineering.2016(2)-16. DOI: 10.1007/s10452-016-9596-x.