基于优化算法的CNN-BiLSTM-attention的月径流量预测  

Monthly runoff forecast based on CNN-BiLSTM-attention-FA-SSA

作　　者：朱豪 胡圆昭 尹明财 贾慧 张济世[1] ZHU Hao;HU Yuanzhao;YIN Mingcai;JIA Hui;ZHANG Jishi(School of Environmental and Municipal Engineering,Lanzhou Jiaotong University,Lanzhou 730070,China;Xinjiang Construction Engineering Group First Construction Engineering Co.,Ltd.,Urumqi 830000,China)

机构地区：[1]兰州交通大学环境与市政工程学院,甘肃兰州730070 [2]中建新疆建工集团第一建筑工程有限公司,新疆乌鲁木齐830000

出　　处：《人民长江》2023年第12期96-104,共9页Yangtze River

基　　金：国家自然科学基金重大项目(41690141);国家自然科学基金面上项目(41671029)。

摘　　要：为有效提取径流时间序列的信息特征,提高径流预测模型的高维非线性拟合能力和预测性能的稳定性,将卷积神经网络(CNN)、双向长短期记忆网络(BiLSTM)和注意力机制(attention)相结合,构建了CNN-BiLSTM-attention的径流组合模型。以长江流域中游汉口站径流量数据进行模拟验证,对比分析BiLSTM,CNN,BiLSTM-attention,CNN-BiLSTM和CNN-BiLSTM-attention 5种径流预测模型模拟月径流的误差特征,利用FA-SSA,GWO和BAO 3种优化算法分别对CNN-BiLSTM-attention组合模型的卷积核个数、BiLSTM隐藏层神经元个数、全连接隐藏层神经元个数、dropout层、批量大小和学习速率6个超参数优化,探究3种优化算法对CNN-BiLSTM-attention月径流预测性能的影响。结果表明:BiLSTM-attention预测误差最大,BiLSTM次之,CNN-BiLSTM-attention组合模型整体预测精度最高;CNN-BiLSTM-attention径流组合模型能有效捕获关键信息和掌握径流时序变化规律,预测径流值与实际值能够较好吻合;FA-SSA优化算法优于GWO和BAO,更能优化CNN-BILSTM-attention的超参数值,并进一步提高该模型的预测精度。In order to effectively extract the information features of runoff time series and improve the stability of the high-dimensional nonlinear fitting ability and prediction performance of the runoff prediction model,the convolutional neural network(CNN),BiLSTM and attention mechanism were combined to construct a runoff combination model of CNN-BiLSTM-attention.The runoff of Hankou station in the middle reaches of the Changjiang River Basin was simulated and verified by this model.The error characteristics of monthly runoff simulated by five runoff prediction models,namely BiLSTM,CNN,BiLSTM+attention,CNN-BiLSTM and CNN-BiLSTM-attention were analyzed.FA-SSA,GWO,BAO were used to optimize the hyperparameters of the novel model,including the number of convolutional nuclei,number of BiLSTM hidden layer neurons,number of fully connected hidden layer neurons,dropout layer,batch size,and learning rate,respectively,to explore the effects of the three optimization algorithms on the monthly runoff prediction performance of the novel model.The results show that the prediction error of BiLSTM-attention is the largest,followed by BiLSTM,and the overall prediction accuracy of CNN-BiLSTM-attention is the highest.The novel model can more effectively and accurately capture key information and further master the rule of runoff timing changes,and the predicted runoff value is in good agreement with the actual value.FA-SSA optimization algorithm is superior to GWO and BAO algorithms,which is conducive in optimizing the hyperparameter values of the novel model and further improving the prediction accuracy of the model.

关 键 词：径流量时间序列 卷积神经网络 双向长短期记忆网络 注意力机制 萤火虫改进的麻雀搜索算法 

分 类 号：P333[天文地球—水文科学]