基于集成学习与深度学习的日供水量预测方法

周欣磊,顾海挺,刘晶,许月萍,耿芳,王冲

Daily water supply prediction method based on integrated learning and deep learning

Xin-lei ZHOU,Hai-ting GU,Jing LIU,Yue-ping XU,Fang GENG,Chong WANG

表 1 不同输入天数的LSTM神经网络方法性能对比

Tab.1 Performance comparison of LSTM neural network models with different input days

Td/d NSE MAE/(m3·d−1) RMSE/(m3·d−1) 2 0.919 1 136 1 601 3 0.917 1 146 1 616 4 0.924 1 242 1 548 5 0.918 1 154 1 607 6 0.924 1 241 1 550 7 0.927 1 104 1 520 8 0.921 1 233 1 581 9 0.921 1 168 1 581 10 0.919 1 207 1 605