摘要
提出一种融合卷积神经网络(CNN)、双向长短期记忆网络(BiLSTM)和残差注意力(RA)机制的县域水稻产量预测模型(CNN-BiLSTM-RA),通过CNN层有效提取县域水稻气象数据中的关键空间特征,利用BiLSTM层深入分析时间序列数据的动态变化,引入RA机制强化对气象数据中关键特征的识别与捕捉,以 2015-2017 年广西 81 个县早稻历史产量和气象数据为样本,与CNN、TRANSFORMER、BiLSTM、CNN-BiLSTM、BiLSTM-RA模型进行对比,评价CNN-BiLSTM-RA模型的预测精度和有效性.结果表明,CNN-BiLSTM-RA模型的R2、MAE、RMSE和MAPE分别为0.986 1、0.121 9、0.224 8、0.864 8,模型的预测值与实际值拟合程度较高.CNN-BiLSTM-RA模型充分发挥了CNN的空间特征提取能力、BiLSTM的时间序列数据分析优势和RA机制在增强关键特征捕捉方面的特性,是一种适用于县域水稻产量高精度预测的新方法.
Abstract
A county-level rice yield prediction model(CNN-BiLSTM-RA)was proposed,which integrated convolutional neural net-work(CNN),bidirectional long short term memory network(BiLSTM),and residual attention(RA)mechanism,key spatial features were effectively extracted from county-level rice meteorological data through CNN layers,the dynamic changes of time series data were deeply analyzed using BiLSTM layers,and RA mechanism was introduced to enhance the recognition and capture of key features in meteorological data.Using historical rice yield and meteorological data from 81 counties in Guangxi from 2015 to 2017 as samples,the prediction accuracy and effectiveness of the CNN-BiLSTM-RA model were compared with CNN,TRANSFORMER,BiLSTM,CNN-BiLSTM,and BiLSTM-RA models.The results showed that the R2,MAE,RMSE,and MAPE of the CNN-BiLSTM-RA model were 0.986 1,0.121 9,0.224 8,and 0.864 8,respectively,indicating a high degree of fit between the predicted and actual values of the model.The CNN-BiLSTM-RA model fully utilized the spatial feature extraction ability of CNN,the time series data analysis ad-vantages of BiLSTM,and the RA mechanism's ability to enhance key feature capture.It was a new method suitable for high-precision prediction of rice yield in counties.
NETL
NSTL
万方数据