An approach of recursive timing deep belief network for algal bloom forecasting
- 56 Downloads
The forecasting methods of water bloom in existence are hard to reflect nonlinear dynamic change in algal bloom formation mechanism, leading to poor forecasting accuracy of bloom. To solve this problem, this paper deeply analyzes the generation process of algal bloom, introduces the recursive time series algorithm into the deep belief network model and improves the model structure and training algorithm, and proposes a forecasting method based on the recursive timed deep belief network model. The model introduces the current moments and historical time values of the characterization factors and influencing factors at the input layer, and increases the connection between the input layer and the hidden layer of the deep belief network. A recursive algorithm is used to establish the relationship between the current time value of the characterization factor and the historical time value of the characterization factor, and the connection between the current time value of the hidden layer and the influencing factor is increased. By re-extracting the characteristics of the hidden layer at each moment, and then fine tuning the network parameters by the BP neural network, a recursive timing deep belief network model is finally constructed. The results show that compared with the existing forecasting methods, this method can extract the characteristics of time series data more accurately and completely to deal with the dynamic nonlinear process and can further improve the forecast accuracy of algal blooms.
KeywordsAlgal bloom Recursive time series deep belief network Forecasting Dynamic nonlinear process
This work was financially supported by National Natural Science Foundation of China (61703008), Support Project of High-level Teachers in Beijing Municipal Universities in the Period of 13th Five-year Plan (CIT&TCD201804014), and Major Project of Beijing Municipal Education Commission science and technology development plans (KZ201510011011). Those supports are gratefully acknowledged.
- 1.Jin M, Ren Z, Shi JP et al (2010) Impact of agricultural non-point source pollution in eutrophic: water body of Taihu Lake. Environ Sci Technol 33(10):106–111Google Scholar
- 3.Liu Z, Wu Q, Wang X et al (2008) Algae growth modeling based on optimization theory and application to water-bloom prediction. CIESC J 59(7):1869–1873Google Scholar
- 4.Wang L, Gao C, Wang X et al (2017) Nonlinear dynamics analysis and water bloom prediction of cyanobacteria growth time variation system. CIESC J 68(3):1065–1072Google Scholar
- 7.Wang X, Tang L, Liu Z et al (2012) Formation mechanism of cyanobacteria bloom in urban lake reservoir. CIESC J 63(5):1492–1497Google Scholar
- 9.Wei J, Liu GB (2008) Overview of intelligent algorithms in nonlinear model predictive control. J Syst Simul 20(24):6581–6586Google Scholar
- 10.Wang L, Liu Z, Wu C et al (2013) Water bloom prediction and factor analysis based on multidimensional time series analysis. CIESC J 64(12):4649–4655Google Scholar
- 15.Yao M (2013) Application of improved genetic algorithm in optimizing BP neural networks weights. Comput Eng Appl 49(24):49–54Google Scholar
- 17.Li L, Cheng P, Lin H et al (2017) Short-term output power forecasting of photovoltaic systems based on the deep belief net. Adv Mech Eng 9(9):1–13Google Scholar
- 21.Gao Y, Su C, Li H (2018) A kind of deep belief networks based on nonlinear features extraction with application to PM2.5 concentration prediction and diagnosis. Acta Autom Sin 44(02):318–329Google Scholar
- 22.Wang G, Li W, Qiao J (2017) Prediction of effluent total phosphorus using PLSR-based adaptive deep belief network. CIESC J 68(5):1987–1997Google Scholar