Xiao Ming-Jun, Zhu Yi-Chun, Gao Wen-Yuan, Zeng Yu, Li Hao, Chen Shuo-Fu, Liu Ping, Huang Hong-Li
College of Environment and Ecology, Hunan Agricultural University, Changsha 410128, China.
Ecological Environment Monitoring Center of Hunan Province, Changsha 410000, China.
Huan Jing Ke Xue. 2024 Oct 8;45(10):5761-5767. doi: 10.13227/j.hjkx.202310074.
The prediction of future data using existing data is an effective tool for regional planning and watershed management. The back propagation neural network （BPNN） and convolutional neural network （CNN） were used to construct a prediction model based on the water quality index of Hengyang in Xiangjiang River Basin from April to May 2022 and the results of permanganate index prediction by different models were compared. The prediction results displayed by BPNN could predict the water quality； however, overfitting occurred during the prediction. BPNN modified by particle swarm optimization （PSO） could avoid overfitting, which improved the parameter selection method of the BPNN mode. The CNN model had a better prediction effect, which had a more complex structure and a more scientific fitting method to avoid the model falling into the local extreme value during the fitting process and improve the accuracy of the model prediction results. The evaluation parameters including root-mean-square error （RMSE）, coefficient of determination （）, and mean absolute error （MAE） were used to predict the accuracy of the network. Compared with that of the traditional BPNN model, PSO-BPNN reduced the RESM of the test set from 0.278 2 mg·L to 0.210 9 mg·L, reduced the MAE of the test set from 0.222 3 mg·L to 0.153 7 mg·L and increased the of the test set from 0.864 0 to 0.921 8, which indicated that PSO-BPNN had more stable fitting ability. RMSE, MAE, and of the test set in the CNN model were 0.122 0 mg·L, 0.092 7 mg·L, and 0.970 5, respectively, which showed that CNN had a better fitting and prediction effect than that of BPNN.
利用现有数据预测未来数据是区域规划和流域管理的有效工具。采用反向传播神经网络（BPNN）和卷积神经网络（CNN），基于2022年4月至5月湘江流域衡阳段水质指标构建预测模型，并比较不同模型对高锰酸盐指数的预测结果。BPNN显示的预测结果能够对水质进行预测，但预测过程中出现了过拟合现象。采用粒子群优化（PSO）改进的BPNN能够避免过拟合，改进了BPNN模型的参数选择方法。CNN模型具有更好的预测效果，其结构更复杂，拟合方法更科学，可避免模型在拟合过程中陷入局部极值，提高了模型预测结果的准确性。采用均方根误差（RMSE）、决定系数（）和平均绝对误差（MAE）等评估参数对网络预测精度进行评价。与传统BPNN模型相比，PSO - BPNN将测试集的RESM从0.278 2 mg·L降至0.210 9 mg·L，将测试集的MAE从0.222 3 mg·L降至0.153 7 mg·L，并将测试集的从0.864 0提高到0.921 8，表明PSO - BPNN具有更稳定的拟合能力。CNN模型测试集的RMSE、MAE和分别为0.122 0 mg·L、0.092 7 mg·L和0.970 5，表明CNN比BPNN具有更好的拟合和预测效果。
