In order to accurately predict noctiluca density, a new prediction model PSO-GRNN was constructed according to the relationship between noctiluca density and environmental factors. Particle swarm optimization (PSO) algorithm was used to obtain the optimal smoothing factor of generalized regression neural network (GRNN) in this model, that could reduce human subjective influence and improve the generalization ability and performance of generalized regression neural network. The dissolved oxygen, water temperature, total nitrogen, salinity, phytoplankton density and soluble inorganic phosphorus were taken as the model input, and the noctiluca density was taken as the model output. Finally, the new model and other traditional models were both tested, and the prediction results of the improved model were compared with other traditional models. The experimental results showed that the improved new model had high accuracy in the prediction of noctiluca density, and could indirectly realize the early prediction of red tide.
ZohdiEAbbaspourM. Harmful algal blooms (red tide): A review of causes, impacts and approaches to monitoring and prediction. International Journal of Environmental Science and Technology.2019; 16(3): 1789-1806.
2.
Mirza EsmaeiliFMortazaviMSArjomandiR, et al. A study on red tide risk and basic understanding of fishermen and residents in Bandar Abbas, Hormozgan Province, Iran (Persian Gulf). Iranian Journal of Fisheries Sciences.2020; 19(1): 471-487.
3.
HeXChenCLuC, et al. Spatial-temporal distribution of red tide in coastal China. IOP Conference Series: Earth and Environmental Science. IOP Publishing.2021; 783(1): 012141.
4.
GuoJHengFHuangZ, et al. Marine hazards from 2000 to 2016 in Zhejiang province of the subtropical region, South China. Journal of Physics: Conference Series. IOP Publishing.2020; 1654(1): 012124.
5.
XuLLiangYXiaoW, et al. Analysis of the inter-annual variability and southward expansion of red tides in the Zhejiang coastal waters from 1981 to 2018. Acta Oceanologica Sinica.2022; 41(1): 132-140.
6.
WangG. Marine Disaster Prediction Based on Mathematical Model. Journal of Coastal Research.2020; 107(SI): 230-233.
7.
HuangBWeiNHuY, et al. Microbial Communities in Water during Red Tides along the Coast of China-A Case Study of Prorocentrum Donghaiense Red Tide in the East China Sea. Journal of Marine Science.2021; 3(1): 29-38.
8.
DuXShaoFWuS, et al. Complex network modeling for mechanisms of red tide occurrence: A case study in Bohai Sea and North Yellow Sea of China. Ecological Modelling.2017; 361: 41-48.
9.
ZhangCHQianZSSunWX, et al. Red tide LMBP neural network combined prediction model based on IOWA operator. Journal of Tianjin University.2011; 44(2): 101-106.
10.
LiHGuSM. Red tide prediction method based on RBF neural network. Computer Engineering and Application.2012; 48(1): 228-230+248.
11.
MaYMGaoJYWangQH. Prediction model of Red Tide Based on artificial neural network. Ocean Forecast.2007; 24(1): 38-44.
12.
HuZMLiuZH. Red tide prediction model based on BSO-BP neural network. Journal of Guilin Institute of Aerospace Technology.2020; 1: 1-8.
13.
WangJ. Prediction Model of Red Tides in Fujian Sea Area Based on BP Neural Network. Journal of Physics: Conference Series. IOP Publishing.2020; 1486(2): 022001.
14.
KimSMShinJBaekS, et al. U-Net convolutional neural network model for deep red tide learning using GOCI. Journal of Coastal Research.2019; 90(SI): 302-309.
15.
SuXHJinFJYangQZ, et al. Red tide forecasting model based on BP neural network in Fujian sea area. Journal of Fisheries of China.2017; 41(11): 1744-1755.
16.
LiHTLiuTLShaoZD, et al. Application of BP neural network based on decision tree and binary segmentation algorithm in red tide level prediction. Marine Science.2019; 43(9): 34-40.
17.
AndreevPGYurkovNKAndreevaTV. Artificial neural networks of GRNN type in prediction problems. 2017 XX IEEE International Conference on Soft Computing and Measurements (SCM). In IEEE Access. 2017; pp. 458-460.
18.
SongCWangLHouJ, et al. The optimized GRNN based on the FDS-FOA under the hesitant fuzzy environment and its application in air quality index prediction. Applied Intelligence.2021; 51(11): 8365-8376.
19.
LuJQChenYZLiuYZ. The application of generalized regression neural network in spatial data clustering. Journal of Navigation and Positioning.2020; 8(2): 31-35.
20.
MariniFWalczakB. Particle swarm optimization (PSO). A tutorial. Chemometrics and Intelligent Laboratory Systems.2015; 149: 153-165.
21.
DeOMStutzleTBirattariM, et al. Frankenstein’s PSO: A composite particle swarm optimization algorithm. IEEE Transactions on Evolutionary Computation.2009; 13(5): 1120-1132.
22.
WeiJ. Simulation of chlorophyll assimilation in Taihu Lake based on ensemble Kalman filter. Nanjing: Nanjing Normal University;2018.
23.
XiYJZhaoZLSunGQ, et al. Analysis of grey incidence between density of Noctiluca scintillans and factors. 2015 International Forum on Energy, Environment Science and Materials. Atlantis Press. 2015; pp. 1141-1145.
24.
WangSWangJLuH, et al. A novel combined model for wind speed prediction – Combination of linear model, shallow neural networks, and deep learning approaches. Energy.2021; 234: 121275.
25.
ZhouYL. Real-time probabilistic forecasting of river water quality under data missing situation: Deep learning plus post-processing techniques. Journal of Hydrology.2020; 589: 125164.
26.
WangB. Study on characteristics of red tide in Bohai Bay. Marine Environmental Science; 2021.
