|
|
空气质量预报二次建模
|
Abstract:
建立空气质量预报模型提前获知可能发生的大气污染状况，并采取相应控制措施是减少大气污染危害的有效方法之一。本文针对WRF-CMAQ等模型预报结果不理想的问题，提出了基于一次预报数据和实测数据的二次预报模型，提高了一次预报模型的准确性，分析了气象条件对污染物浓度的影响程度，提出了时间序列预测模型和基于粒子群优化的BP神经网络模型，大大地提高了预测的精度。
One of the effective ways to reduce the harm of air pollution is to establish an air quality forecast model to know the possible air pollution situation in advance and take corresponding control measures. Aiming at the problem that WRF-CMAQ and other models have unsatisfactory forecast results, this paper puts forward a secondary forecast model based on primary forecast data and measured data, which improves the accuracy of the primary forecast model, analyzes the influence of meteorological conditions on pollutant concentration, and puts forward a time series forecast model and a BP neural network model based on particle swarm optimization, which greatly improves the forecast accuracy.
| [1] | 陈啸龙. 浅析环境监测在大气污染治理中的作用[N]. 江苏经济报, 2021-10-14(B03). |
| [2] | 陈道新, 李江敏, 张瑞哲, 欧阳雨婷. 防治大气污染 保卫蓝天白云[N]. 南昌日报, 2021-10-14(006). |
| [3] | 忽建永, 钱雪莹, 殷文涛, 黄奕. 近3年西双版纳州勐腊县大气污染基本特征及污染原因分析[J]. 环境科学学报, 2021(11): 4388-4395. |
| [4] | 江思力, 李文学, 步犁, 吕嘉韵, 冯文如, 杨轶戩. 广州市2020年PM2.5的污染特征与居民循环系统疾病的相关性[J]. 中国热带医学, 2021(12): 1144-1149. |
| [5] | Zhang, H., Ji, Y.Y., Wu, Z.H., Peng, L., Bao, J.M., Peng, Z.J. and Li, H. (2022) Atmospheric Volatile Halogenated Hydrocarbons in Air Pollution Episodes in an Urban Area of Beijing: Characterization, Health Risk Assessment and Sources Apportionment. Science of the Total Environment, 806, Article No. 150283.
https://doi.org/10.1016/j.scitotenv.2021.150283 |
| [6] | Ullah, S., Ullah, N., Rajper, S.A., Ahmad, I. and Li, Z.Q. (2021) Air Pollution and Associated Self-Reported Effects on the Exposed Students at Malakand Division, Pakistan. En-vironmental Monitoring and Assessment, 193, Article No. 708. https://doi.org/10.1007/s10661-021-09484-2 |
| [7] | Liu, B., Jin, Y. and Li, C. (2021) Analysis and Prediction of Air Quality in Nanjing from Autumn 2018 to Summer 2019 Using PCR-SVR-ARMA Combined Model. Scientific Reports, 11, Article No. 348.
https://doi.org/10.1038/s41598-020-79462-0 |
| [8] | Zamani, M. (2019) PM2.5 Prediction Based on Random Forest, XGBoost, and Deep Learning Using Multisource Remote Sensing Data. Atmosphere, 10, Article No. 373. https://doi.org/10.3390/atmos10070373 |
| [9] | Bhat, M.A., Romshoo, S.A. and Beig, G. (2021) Measurement and Modelling of Particulate Pollution over Kashmir Himalaya, India. Water, Air, & Soil Pollution, 232, Article No. 120. https://doi.org/10.1007/s11270-021-05062-x |
| [10] | Ma, J., Cheng, J.C.P., et al. (2020) Identification of the Most In-fluential Areas for Air Pollution Control Using XGBoost and Grid Importance Rank. Journal of Cleaner Production, 274, Article No. 122835.
https://doi.org/10.1016/j.jclepro.2020.122835 |
| [11] | 闫艳. 完善观测方法提高预报预警能力[N]. 中国环境报, 2013-09-02(002). |
