• ▶ 2008-2024年被中国情报信息研究所评价中心评为“中国科技核心期刊”
  • ▶ 2019-2024年连续三届被中国科学院文献情报中心中国科学引文数据库CSCD(核心库)收录
  • ▶ 2021、2023年入编北京大学图书馆《中文核心期刊要目总览》
  • ▶ 2020-2024连续四年入选《科技期刊世界影响力指数(WJCI)报告》
郝玉莹, 赵 林, 孙 同, 乔 治.基于RF-LSTM的地表水体水质预测水资源与水工程学报[J].,2021,32(6):41-48
基于RF-LSTM的地表水体水质预测
Surface water quality prediction based on RF-LSTM
  
DOI:10.11705/j.issn.1672-643X.2021.06.06
中文关键词:  水质预测  长短时记忆神经网络  随机森林  特征选择
英文关键词:water quality prediction  long short-term memory (LSTM) neural network  random forest (RF)  feature selection
基金项目:天津市科技重大专项与工程项目(18ZXSZSF00240)
作者单位
郝玉莹1,2, 赵 林1,2, 孙 同1,2, 乔 治1,2 (1.天津大学 环境科学与环境工程学院 天津 300350 2.天津市滨海生态关键带保护与功能构建工程技术中心 天津 300350) 
摘要点击次数: 1811
全文下载次数: 389
中文摘要:
      水质预测是水污染防治的重要一环,为提高水质预测的精度,研究随机森林算法(RF)与长短时记忆神经网络(LSTM)相结合的预测方法。以桃林口水库水质监测数据为例,采用RF算法分别筛选出影响高锰酸盐指数(CODMn)、氨氮(NH3—N)、总氮(TN)和总磷(TP)浓度变化的关键特征,在此基础上构建基于RF-LSTM的水质预测模型,并与单一LSTM、RF-BPNN和RF-RNN模型的预测效果进行对比。结果表明:RF-LSTM模型的预测效果均优于其他模型,预测CODMn、NH3—N、TN和TP未来4 h浓度时的决定系数(R2)分别达到0.986、0.990、0.989和0.988,具有极高的预测精度和较强的泛化能力。研究结果为实现高精度水质预测提供了新思路。
英文摘要:
      Water quality prediction plays an important role in the prevention and control of water pollution. In order to improve the accuracy of water quality prediction, a new prediction method based on the combination of random forest (RF) algorithm and long short-term memory (LSTM) neural network was proposed. Taking the water quality monitoring data of Taolinkou Reservoir as an example, the RF algorithm was used to screen out the key characteristics that affect the changes in the concentration of permanganate index (CODMn), ammonia nitrogen (NH3—N), total nitrogen (TN) and total phosphorus (TP). On this basis, a water quality prediction model based on RF-LSTM was constructed and the prediction results were then compared with those of sole LSTM, RF-BPNN, and RF-RNN model. The results show that the prediction performance of the RF-LSTM model is better than the other models with extremely high prediction accuracy and strong generalization ability, the coefficient of determination (R2) for predicting the concentration of CODMn, NH3—N, TN and TP in the next four hours are 0.986, 0.990, 0.989 and 0.988, respectively. The research results can provide a new approach for high-precision water quality prediction.
查看全文  查看/发表评论  下载PDF阅读器
关闭