摘要
PM_(2.5)浓度的预测对于大气污染治理、改善环境质量等起到重要作用。受气象条件变化与大气污染物排放等多种因素的交叉影响,PM_(2.5)预测通常易受突变事件及噪声数据干扰。因此,基于对气象条件以及大气污染物与PM_(2.5)的相关性分析,提出阶段式时序注意力网络模型(staged temporal-attention network, STAN),该方法融合多段注意力学习模块与循环神经网络,建模气象因素与大气污染物对PM_(2.5)浓度的交叉影响。统计分析北京市、上海市、广州市预测结果的绝对误差值,可知:1)对比广泛使用的单一类模型支持向量机(support vector machine, SVM)、长短期时序记忆方法 (long short-term memory, LSTM)和多层感知机(multilayer perceptron, MLP), STAN可达到10%以上的性能领先;对比最新的融合类模型U型网络(U-net),STAN领先了7%的优势。2)以北京市冬季预测结果为例进行统计分析,STAN的预测值与实测值之间的拟合系数可有95.2%的性能领先。此外,在鲁棒性分析中发现,STAN在含有10%噪声的数据上进行预测,误差上升幅度仅为9.3%。结果表明:注意力机制与时序学习模块相结合能够深度挖掘PM_(2.5)变化规律并抑制噪声数据,且STAN模型可以进行PM_(2.5)浓度的鲁棒预测。
The forecast of PM_(2.5) concentration plays an important role in air pollution control and improvement of environmental quality.Affected by multiple factors such as changes in meteorological conditions and air pollutants emissions,the PM_(2.5) forecast was usually susceptible to sudden changes and noise data.Therefore,in-depth exploration of the PM_(2.5) concentration change law and modeling robust prediction models have become key steps in this task.Based on the analysis of the correlation between meteorological conditions and atmospheric pollutants on PM_(2.5),a staged temporal-attention network(STAN)was proposed.This method combined a multi-stage attention module and a recurrent neural network(RNN)to model the cross-influence of meteorological factors and atmospheric pollutants on PM_(2.5) concentration.Statistical analysis of the absolute error values of the prediction results of Beijing,Shanghai,and Guangzhou showed the following results:1)compared with the widely used support vector machine(SVM),long short-term memory(LSTM),and multilayer perceptron(MLP),the performance of the proposed method increased more than 10%.2)compared with the latest fusion model U-net,the proposed STAN still achieved a decrease in the error of 7%.Taking Beijing’s winter forecast results as an example for statistical analysis,the fitting coefficient between the predicted value of STAN and the measured value could reach 95.2%.In the robustness analysis,it was found that the error increased by only 9.3%when the proposed method ran on data with 10%noise.The above results proved that the combination of the attention mechanism and the temporal learning module could deeply mine the change law of PM_(2.5) and suppress noise data.It also showed that the STAN could achieve the robust prediction of PM_(2.5) concentration.
作者
陆瑶
杨洁
邵智娟
朱聪聪
LU Yao;YANG Jie;SHAO Zhi-juan;ZHU Cong-cong(College of Environmental Science and Engineering,Suzhou University of Science and Technology,Suzhou 215009,China;College of Computer Engineering and Science,Shanghai University,Shanghai 200444,China)
出处
《环境工程》
CAS
CSCD
北大核心
2021年第10期93-100,共8页
Environmental Engineering
基金
国家自然科学基金面上项目(41571475)。
