Xie Zaimi, Li Zhenhua, Mo Chunmei, Wang Ji
School of Mathematics and Computer Science, Guangdong Ocean University, Zhanjiang 524088, China.
Guangdong Engineering Technology Research Center of Intelligent Ocean Sensor Network and Equipment, Zhanjiang 524088, China.
Materials (Basel). 2022 Jul 27;15(15):5200. doi: 10.3390/ma15155200.
In order to effectively solve the problem of low accuracy of seawater water quality prediction, an optimized water quality parameter prediction model is constructed in this paper. The model first screened the key factors of water quality data with the principal component analysis (PCA) algorithm, then realized the de-noising of the key factors of water quality data with an ensemble empirical mode decomposition (EEMD) algorithm, and the data were input into the two-dimensional convolutional neural network (2D-CNN) module to extract features, which were used for training and learning by attention, gated recurrent unit, and an encoder-decoder (attention-GRU-encoder-decoder, attention-GED) integrated module. The trained prediction model was used to predict the content of key parameters of water quality. In this paper, the water quality data of six typical online monitoring stations from 2017 to 2021 were used to verify the proposed model. The experimental results show that, based on short-term series prediction, the root mean square error (RMSE), mean absolute percentage error (MAPE), and decision coefficient (R) were 0.246, 0.307, and 97.80%, respectively. Based on the long-term series prediction, RMSE, MAPE, and R were 0.878, 0.594, and 92.23%, respectively, which were all better than the prediction model based on an enhanced clustering algorithm and adam with a radial basis function neural network (ECA-Adam-RBFNN), a prediction model based on a softplus extreme learning machine method with partial least squares and particle swarm optimization (PSO-SELM-PLS), and a wavelet transform-depth Bi-S-SRU (Bi-directional Stacked Simple Recurrent Unit) prediction model. The PCA-EEMD-CNN-attention-GED prediction model not only has high prediction accuracy but can also provide a decision-making basis for the water quality control and management of aquaculture in the waters around Zhanjiang Bay.
为有效解决海水水质预测精度低的问题，本文构建了一种优化的水质参数预测模型。该模型首先使用主成分分析（PCA）算法筛选水质数据的关键因素，然后采用集成经验模态分解（EEMD）算法实现水质数据关键因素的去噪，将数据输入二维卷积神经网络（2D-CNN）模块提取特征，通过注意力机制、门控循环单元和编码器-解码器（attention-GRU-encoder-decoder，attention-GED）集成模块进行训练和学习。利用训练好的预测模型对水质关键参数的含量进行预测。本文采用2017年至2021年六个典型在线监测站的水质数据对所提模型进行验证。实验结果表明，基于短期序列预测，均方根误差（RMSE）、平均绝对百分比误差（MAPE）和决定系数（R）分别为0.246、0.307和97.80%。基于长期序列预测，RMSE、MAPE和R分别为0.878、0.594和92.23%，均优于基于增强聚类算法和带有径向基函数神经网络的亚当优化算法（ECA-Adam-RBFNN）的预测模型、基于带有偏最小二乘和粒子群优化的软加极端学习机方法（PSO-SELM-PLS）的预测模型以及小波变换-深度双向堆叠简单循环单元（Bi-directional Stacked Simple Recurrent Unit）预测模型。PCA-EEMD-CNN-attention-GED预测模型不仅具有较高的预测精度，还可为湛江湾周边海域水产养殖的水质控制与管理提供决策依据。
