计算机应用 ›› 2018, Vol. 38 ›› Issue (7): 2119-2123.DOI: 10.11772/j.issn.1001-9081.2017122959

• 应用前言、交叉与综合 • 上一篇    下一篇

基于遗传算法改进的一阶滞后滤波和长短期记忆网络的蓝藻水华预测方法

于家斌1, 尚方方1, 王小艺1, 许继平1, 王立1, 张慧妍1, 郑蕾2   

  1. 1. 北京工商大学 计算机与信息工程学院, 北京 100048;
    2. 北京师范大学 水科学研究院, 北京 100875
  • 收稿日期:2017-12-18 修回日期:2018-02-05 出版日期:2018-07-10 发布日期:2018-07-12
  • 通讯作者: 王小艺
  • 作者简介:于家斌(1984-),男,山东烟台人,副教授,博士,主要研究方向:智能控制、控制理论;尚方方(1992-),女,河南许昌人,硕士研究生,主要研究方向:深度学习、智能水环境数据分析、信号处理;王小艺(1975-),男,山西运城人,教授,博士,主要研究方向:复杂系统的预测和决策;许继平(1979-),湖南岳阳人,副教授,博士,主要研究方向:数据采集、专家意见集成;王立(1983-),女,北京人,副教授,博士,主要研究方向:故障监测、时序预测;张慧妍(1973-),女,黑龙江齐齐哈尔人,副教授,博士,主要研究方向:水质监测、数据建模分类与预测;郑蕾(1980-),女,河北隆尧人,副教授,博士,主要研究方向:水环境污染和治理。
  • 基金资助:
    国家自然科学基金青年项目(61703008);北京市教委科技计划重点项目(KZ201510011011)。

Cyanobacterial bloom forecast method based on genetic algorithm-first order lag filter and long short-term memory network

YU Jiabin1, SHANG Fangfang1, WANG Xiaoyi1, XU Jiping1, WANG Li1, ZHANG Huiyan1, ZHENG Lei2   

  1. 1. School of Computer and Information Engineering, Beijing Technology and Business University, Beijing 100048, China;
    2. College of Water Sciences, Beijing Normal University, Beijing 100875, China
  • Received:2017-12-18 Revised:2018-02-05 Online:2018-07-10 Published:2018-07-12
  • Supported by:
    This work is partially supported by the Youth Project of National Natural Science Foundation of China (61703008), the Key Project of Science and Technology Plan of Beijing Municipal Education Commission (KZ201510011011).

摘要: 河湖藻类水华形成过程中所具有的突发性和不确定性,导致对藻类水华爆发预测准确性不高。为解决此问题,以叶绿素a的浓度值作为蓝藻水华演化过程表征指标,提出基于长短期记忆(LSTM)循环神经网络(RNN)蓝藻水华预测模型。首先,用遗传算法改进的一阶滞后滤波(GF)优化算法对数据进行平滑滤波处理;然后,搭建GF-LSTM网络的蓝藻水华预测模型,实现对水华发生的精准预测;最后,以太湖水域梅梁湖区域的采样数据为样本,对预测模型进行检验,并与传统的RNN和LSTM网络进行对比。仿真结果表明,提出的GF-LSTM网络模型平均相对误差控制在16%~18%,而RNN模型的预测平均相对误差为28%~32%,LSTM网络模型的平均相对误差为19%~22%,对采用数据的平滑性处理效果较好,预测精度更高,对样本具有更好的适应性,克服了传统RNN模型在长期训练时出现的梯度消失与梯度爆炸缺点。

关键词: 蓝藻水华, 长短期记忆, 滤波算法, 循环神经网络, 预测模型

Abstract: The process of algal bloom evolution in rivers or lakes has characteristics of suddenness and uncertainty, which leads to low prediction accuracy of algal bloom. To solve this problem, chlorophyll a concentration was used as the surface index of cyanobacteria bloom evolution process, and a cyanobacterial bloom forecast model based on Long Short-Term Memory (LSTM) and Recurrent Neural Network (RNN) was proposed. Firstly, the improved Genetic algorithm-First order lag filter (GF) optimization algorithm was taken as data smoothing filter. Secondly, a GF-LSTM network model was built to accurately predict the cyanobacterial bloom. Finally, the data sampled from Meiliang Lake in Taihu area were used to test the forecast model, and then the model was compared with the traditional RNN and LSTM network. The experimental results show that, the mean relative error of the proposed GF-LSTM network model is 16%-18%, lower than those of RNN model (28%-32%) and LSTM network model (19%-22%). The proposed model has good effect on data smoothing filtering, higher prediction accuracy and better adaptability to samples. It also avoids two widely known issues of gradient vanishing and gradient exploding when using traditional RNN model during long term training.

Key words: cyanobacterial bloom, Long Short-Term Memory (LSTM), filter algorithm, Recurrent Neural Network (RNN), forecast model

中图分类号: