MRMR-SA-EGA-ELM的叶绿素a浓度预测模型研究OA北大核心CSTPCD
CHLOROPHYLL A CONCENTRATION PREDICTION MODEL WITH MRMR-SA-EGA-ELM
为提高叶绿素a浓度的预测精度,以南太湖区域-湖州市新塘港2020年5月至11月份的水质监测数据为原始样本数据,使用最大相关最小冗余算法(MRMR)从原始样本数据中选取效果更优的特征值,作为预测模型的输入数据,将精英遗传算法(EGA)与模拟退火算法(SA)组合优化极限学习机(ELM)网络的初始参数,最终构建MRMR-SA-EGA-ELM叶绿素a浓度预测模型.实验结果表明,MRMR-SA-EGA-ELM模型预测叶绿素a浓度的平均绝对误差(MAE)、均方误差(MSE)、决定系数(R2)分别为1.009、1.607、0.903,而ELM模型预测结果的MAE、MSE、R2分别为2.078、8.249、0.562,MRMR-SA-EGA-ELM模型的效果得到显著提升,可实现对叶绿素a浓度的准确预测.
To improve the prediction accuracy of chlorophyll a concentration,taking the water quality monitoring data of the South Taihu Lake area-Xintang harbour of Huzhou City from May to November 2020 as the original sample data,the maximum relevance minimum redundancy algorithm was used to select better feature values from the original sample data as the input data for the prediction model.The combination of elite genetic algorithm and simulated annealing algorithm was used to optimize the initial parameters in the extreme learning machine network.The prediction model of chlorophyll a concentration with MRMR-SA-EGA-ELM was constructed.The experimental results show that the mean absolute error,mean square error and determination coefficient of the MRMR-SA-EGA-ELM model predicting chlorophyll a concentration are 1.009,1.607,0.903 respectively,while the MAE,MSE and R2 of the ELM model are 2.078,8.249,and 0.562 respectively.The effect of the MRMR-SA-EGA-ELM model is significantly improved,and the accurate prediction of chlorophyll a concentration can be achieved.
陈优良;陶剑辉;黄劲松;肖钢
江西理工大学土木与测绘工程学院 江西赣州 341000||中南大学地球科学与信息物理学院 湖南长沙 410000江西理工大学土木与测绘工程学院 江西赣州 341000浙江智谱工程技术有限公司 浙江湖州 313000赣州市城乡规划设计研究院 江西赣州 341000
计算机与自动化
叶绿素a浓度最大相关最小冗余精英遗传算法模拟退火算法极限学习机
Chlorophyll a concentrationMaximum relevance minimum redundancyElitist genetic algorithmSimulated annealing algorithmExtreme learning machine
《计算机应用与软件》 2024 (004)
60-66 / 7
国家自然科学基金项目(41261093);江西省教育厅科技项目(GJJ170522).
评论