摘要
准确预测PM_(10)浓度是控制干散货港口人群PM_(10)暴露水平,降低健康和经济风险的关键.然而,港口气象环境因素的特殊性,为准确预测PM_(10)浓度的时序非线性变化特征带来了挑战.为此,构建了一个级联卷积神经网络(CNN)、长短期记忆(LSTM)和注意力机制(AM)的深度学习组合模型(CLAF),预测干散货港口PM_(10)的小时浓度.首先,基于随机森林特征重要性算法,从5个气象因素中筛选出重要特征气象因素,与PM_(10)浓度一起构建预测模型的输入变量.其次,利用CNN层提取输入变量中高维时变特征,通过LSTM层捕捉顺序特征以及长期依赖性,并在AM层为LSTM层的输出特征分配不同的权重,强化重要信息的影响.最后,应用3个评价指标将CLAF模型分别与3个基本模型和3个常用预测模型的性能进行对比分析.基于实例数据的分析结果表明,考虑特征气象因素可以提高港口PM_(10)浓度的预测精度和拟合性能,CLAF模型可以将平均绝对误差降低13.92%~56.9%,将均方误差降低45.99%~81.02%,将拟合优度提高3.2%~15.5%.将特征气象因素作为输入变量,可以提高模型的预测性能.
Accurate prediction of PM_(10)concentration is important for effectively managing PM_(10)exposure and mitigating health and economic risks posed to humans in dry bulk ports.However,accurately capturing the time-series nonlinear variation characteristics of PM_(10)concentration is challenging owing to the specific intensity of port operation activities and the influence of meteorological factors.To address such challenges,a novel combined deep learning model(CLAF)was proposed,merging cascaded convolutional neural networks(CNN),long short-term memory(LSTM),and an attention mechanism(AM).This integrated model aimed to forecast hourly PM_(10)concentration in dry bulk ports.First,using the random forest characteristic importance algorithm,the distinct meteorological factors were identified among the selected five meteorological factors.These selected factors were incorporated into the prediction model along with the PM_(10)concentration.Subsequently,the CNN layer was employed to extract high-dimensional time-varying features from the input variables,while the LSTM layer captured sequential features and long-term dependencies.In the AM layer,different weights were assigned to the output components of the LSTM layer to amplify the effects of important information.Finally,three evaluation metrics were applied to compare the performance of the CLAF model with three basic models and three commonly used prediction models.Real-case data was collected and used in this study.Comparison results demonstrated that considering the meteorological factors could improve the prediction accuracy and fitting performance of PM_(10)concentration in ports.The CLAF model reduced the mean absolute error statistic by 13.92%-56.9%,decreased the mean square error statistic by 45.99%-81.02%,and improved the goodness-of-fit statistic by 3.2%-15.5%.
作者
沈金星
刘沁鑫
封学军
SHEN Jin-xing;LIU Qin-xin;FENG Xue-jun(College of Civil and Transportation Engineering,Hohai University,Nanjing 210098,China;College of Harbor,Coastal and Offshore Engineering,Hohai University,Nanjing 210098,China)
出处
《环境科学》
EI
CAS
CSCD
北大核心
2024年第9期5179-5187,共9页
Environmental Science
基金
国家重点研发计划项目(2021YFB2600200)。
关键词
PM_(10)
干散货港口
浓度预测
气象因素
深度学习
组合模型
PM_(10)
dry bulk ports
concentration prediction
meteorological factors
deep learning
combinatorial models
