基于敏感参数发现的区域重点污染物浓度预测
作者:

Regional Key Pollutant Concentration Prediction Based on Sensitive Parameter Discovery
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [33]
  • |
  • 相似文献 [20]
  • | | |
  • 文章评论
    摘要:

    污染物浓度变化趋势对于环境监测工作意义重大. 现今各种前馈神经网络预测模型的输出结果仅与当前输入有关, 无法研究污染物数据前后依赖关系. 且多种污染物具有相同排放源, 污染物间往往存在潜在关联关系, 一种污染物的变化可能反映另一种污染物变化, 所以在预测中需考虑其他敏感参数的影响. 针对上述两个问题, 提出一种基于敏感参数发现的区域重点污染物浓度预测方法. 应用关联规则算法及多元回归分析挖掘出各污染物的敏感参数, 构建多变量LSTM预测模型, 将待预测污染物及其敏感参数作为预测模型特征变量, 进行污染物的浓度预测. 实验结果表明本文方法可有效预测污染物浓度变化趋势, 预测效果优于未经关系发现的LSTM模型.

    Abstract:

    The variation trend in pollutant concentration is of great significance for environmental monitoring. At present, the output of various feedforward neural network prediction models is only related to the current input, so it is impossible to study the dependence of pollutant data before and after. Multiple pollutants have the same emission source, and there is a potential correlation between pollutants. The change in one pollutant may reflect that in another pollutant, so the influence of other sensitive parameters should be considered in the prediction. To solve the above two problems, this study proposes a regional key pollutant concentration prediction method based on sensitive parameter discovery. The association rule algorithm and multiple regression analysis are used to mine the sensitive parameters of each pollutant, and a multivariable LSTM prediction model is constructed. The pollutants to be predicted and their sensitive parameters are taken as the characteristic variables of the model to predict the pollutant concentration. The experimental results show that the proposed method can reliably predict the variation trend in pollutant concentration and it performs better than the LSTM model without relation discovery.

    参考文献
    [1] 马莉娟, 付强, 姚雅伟. 我国环境监测方法标准体系的现状与发展构想. 中国环境监测, 2018, 34(5): 30–35
    [2] 詹志明, 尹文君. 环保大数据及其在环境污染防治管理创新中的应用. 环境保护, 2016, 44(6): 44–48
    [3] 徐敏, 孙海林. 从“数字环保”到“智慧环保”. 环境监测管理与技术, 2011, 23(4): 5–7, 26. [doi: 10.3969/j.issn.1006-2009.2011.04.002
    [4] 熊亚军, 徐敬, 孙兆彬, 等. 基于数据挖掘算法和数值模拟技术的大气污染减排效果评估. 环境科学学报, 2019, 39(1): 116–125
    [5] 卢晓华. 基于数值模拟的企业地下水重金属污染的环境影响预测评价. 安全与环境工程, 2014, 21(1): 93–97. [doi: 10.3969/j.issn.1671-1556.2014.01.018
    [6] Ramyar S, Kianfar F. Forecasting crude oil prices: A comparison between artificial neural networks and vector autoregressive models. Computational Economics, 2019, 53(2): 743–761. [doi: 10.1007/s10614-017-9764-7
    [7] Gao Y, Liu XD, Li XL, et al. A prediction approach on energy consumption for public buildings using mind evolutionary algorithm and BP neural network. Proceedings of 2018 IEEE 7th Data Driven Control and Learning Systems Conference. Enshi: IEEE, 2018. 385–389.
    [8] 肖文, 胡娟, 周晓峰. 基于MapReduce计算模型的并行关联规则挖掘算法研究综述. 计算机应用研究, 2018, 35(1): 13–23. [doi: 10.3969/j.issn.1001-3695.2018.01.003
    [9] 刘莉萍, 章新友, 牛晓录, 等. 基于Spark的并行关联规则挖掘算法研究综述. 计算机工程与应用, 2019, 55(9): 1–9. [doi: 10.3778/j.issn.1002-8331.1811-0425
    [10] Han XJ, Liu YL, Yang HY. A stereo matching algorithm guided by multiple linear regression. Journal of Computer-Aided Design & Computer Graphics, 2019, 31(1): 84–93
    [11] 刘畅, 马韵洁, 黄翔. 一种基于多元线性回归算法的车流量预测模型研究. 电子技术与软件工程, 2016, (21): 175
    [12] 万永权, 徐方勤, 燕彩蓉, 等. 融合气象参数及污染物浓度的空气质量预测方法. 计算机应用与软件, 2018, 35(8): 113–117. [doi: 10.3969/j.issn.1000-386x.2018.08.020
    [13] 孙宝磊, 孙暠, 张朝能, 等. 基于BP神经网络的大气污染物浓度预测. 环境科学学报, 2017, 37(5): 1864–1871
    [14] 夏杰, 吴文青, 许海洋. 基于主成分分析的BP神经网络在水华预测中的应用. 世界生态学, 2018, 7(2): 53–60
    [15] 方彦. 基于灰色RBF神经网络的空气质量预测. 中国科技信息, 2018, (22): 100–102. [doi: 10.3969/j.issn.1001-8972.2018.22.038
    [16] 郭晓君, 刘思峰, 吴利丰. 污染物减排预测的灰色Markov组合模型与算法. 计算机应用研究, 2013, 30(12): 3670–3673. [doi: 10.3969/j.issn.1001-3695.2013.12.039
    [17] 张峰, 殷秀清, 董会忠. 组合灰色预测模型应用于山东省碳排放预测. 环境工程, 2015, 33(2): 147–152
    [18] Shaban KB, Kadri A, Rezk E. Urban air pollution monitoring system with forecasting models. IEEE Sensors Journal, 2016, 16(8): 2598–2606. [doi: 10.1109/JSEN.2016.2514378
    [19] Moazami S, Noori R, Amiri BJ, et al. Reliable prediction of carbon monoxide using developed support vector machine. Atmospheric Pollution Research, 2016, 7(3): 412–418. [doi: 10.1016/j.apr.2015.10.022
    [20] 付学良, 杨洋, 李纯子. 基于混沌—支持向量机的大气污染物浓度预测模型. 电子世界, 2013, (4): 78–79
    [21] Liu GQ, Gao XD, You DY, et al. Prediction of high power laser welding status based on PCA and SVM classification of multiple sensors. Journal of Intelligent Manufacturing, 2019, 30(2): 821–832. [doi: 10.1007/s10845-016-1286-y
    [22] Byeon H. A laryngeal disorders prediction model based on cluster analysis and regression analysis. Medicine, 2019, 98(31): e16686. [doi: 10.1097/MD.0000000000016686
    [23] Punzo A, McNicholas PD. Robust clustering in regression analysis via the contaminated Gaussian cluster-weighted model. Journal of Classification, 2017, 34(2): 349–293
    [24] 沈劲, 钟流举, 何芳芳, 等. 基于聚类与多元回归的空气质量预报模型开发. 环境科学与技术, 2015, 38(2): 63–66
    [25] 付倩娆. 基于多元线性回归的雾霾预测方法研究. 计算机科学, 2016, 43(S1): 526–528
    [26] 白婷, 文继荣, 赵鑫, 等. 基于迭代回归树模型的跨平台长尾商品购买行为预测. 中文信息学报, 2017, 31(5): 185–193. [doi: 10.3969/j.issn.1003-0077.2017.05.026
    [27] 姚宏亮, 马晓琴, 王浩, 等. 基于形态特征与因果岭回归的股市态势预测算法. 计算机工程, 2016, 42(2): 175–183. [doi: 10.3969/j.issn.1000-3428.2016.02.032
    [28] 杜续, 冯景瑜, 吕少卿, 等. 基于随机森林回归分析的PM2.5浓度预测模型. 电信科学, 2017, 33(7): 66–75
    [29] 马天成, 刘大铭, 李雪洁, 等. 基于改进型PSO的模糊神经网络PM2.5浓度预测. 计算机工程与设计, 2014, 35(9): 3258–3262. [doi: 10.3969/j.issn.1000-7024.2014.09.054
    [30] Selvin S, Vinayakumar R, Gopalakrishnan EA, et al. Stock price prediction using LSTM, RNN and CNN-sliding window model. Proceedings of 2017 International Conference on Advances in Computing, Communications and Informatics. Udupi: IEEE, 2017. 1643–1647.
    [31] Liu J, Wang G, Duan LY, et al. Skeleton-based human action recognition with global context-aware attention LSTM networks. IEEE Transactions on Image Processing, 2018, 27(4): 1586–1599. [doi: 10.1109/TIP.2017.2785279
    [32] Qing X, Niu YG. Hourly day-ahead solar irradiance prediction using weather forecasts by LSTM. Energy, 2018, 148: 461–468. [doi: 10.1016/j.energy.2018.01.177
    [33] Karim F, Majumdar S, Darabi H, et al. Multivariate LSTM-FCNs for time series classification. Neural Networks, 2019, 116: 237–245. [doi: 10.1016/j.neunet.2019.04.014
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

潘欣玉,郑亮.基于敏感参数发现的区域重点污染物浓度预测.计算机系统应用,2021,30(10):202-209

复制
分享
文章指标
  • 点击次数:917
  • 下载次数: 1785
  • HTML阅读次数: 1345
  • 引用次数: 0
历史
  • 收稿日期:2020-12-26
  • 最后修改日期:2021-01-25
  • 在线发布日期: 2021-10-08
文章二维码
您是第11205190位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京海淀区中关村南四街4号 中科院软件园区 7号楼305房间,邮政编码:100190
电话:010-62661041 传真: Email:csa (a) iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号