基于多特征融合和牛顿-拉夫逊优化算法的LSTM日径流预测

王铮,张梦君,姜楠,王万良,屠杭垚

Daily runoff prediction using LSTM based on multi-feature fusion and Newton-Raphson-based optimizer

Zheng WANG,Mengjun ZHANG,Nan JIANG,Wanliang WANG,Hangyao TU

表 4 各模型在测试集上的1 d预见期的消融实验结果

Tab.4 Ablation experiment results of multiple models with one-day lead time on test set

站点 算法 RMSE MAE MAPE NSE 花园口 LSTM 267.388 6 131.654 0 0.110 2 0.927 5 MFF-LSTM 134.740 5 77.958 8 0.066 0 0.979 5 NRBO-LSTM 216.410 0 114.240 0 0.100 0 0.954 0 MFF-NRBO-LSTM 61.289 6 31.822 4 0.028 3 0.995 8 利津 LSTM 200.944 3 104.585 3 0.105 7 0.960 7 MFF-LSTM 116.979 6 53.791 3 0.068 8 0.985 5 NRBO-LSTM 199.833 0 105.086 6 0.108 7 0.961 2 MFF-NRBO-LSTM 55.684 4 27.875 0 0.034 2 0.996 7