摘要
溶解氧是评价水质健康的指标之一,其对畜牧业的养殖和水污染的评价都有着重要作用。本文通过收集维多利亚港的水质数据影响因素进行预处理,然后建立门控循环神经网络模型对其进行预测,最后把GRU模型和LSTM模型进行对比。其结果表明GRU神经网络模型的预测精度要高于LSTM模型,具有可靠性和适应性。
Dissolved oxygen is one of the indexes to evaluate the health of water quality.It plays an important role in the evaluation of animal husbandry and water pollution.In this paper,the influencing factors of Victoria Harbour*s water quality data were collected for preprocessing.Then a gated circulation neural network model was established to predict it.Finally,the GRU model was compared w ith the LSTM model.The results show that the prediction accuracy of the GRU neural network model is higher than the LSTM model.And it has reliability and adaptability.
出处
《中国新通信》
2020年第22期123-124,共2页
China New Telecommunications
关键词
GRU
水质
溶解氧
时序预测
GRU
Water quality
Dissolved oxygen
The sequential predict
