Forecast of Baoding Air Quality Index Based on Long-Short Term Neural Memory
DOI:
https://doi.org/10.54097/wgn6wy78Keywords:
Air quality index, long-short-term neural memory network, recurrent neural network.Abstract
Accurate prediction of air quality in Baoding City will help residents take preventive measures against air pollution and relevant departments to understand the city’s air quality situation and implement air pollution control policies. This article uses Python to crawl a total of 3457 sets of historical data on the concentration and air quality index of 6 pollutants including , , , , and in Baoding City from 2014 to 2023, and establishes a long- and short-term neural network prediction model. Define the number of input layers, output layers and hidden nodes, and determine ReLU as the activation function. The tangible output results after applying the model are RMSE 23.6727, R2 0.8332, MAE 17.4298, and MBE 0.35743. The research results demonstrate that the model is training It shows excellent performance on both the test set and the test set. The evaluation results indicate that using the LSTM model to predict AQI in Baoding City has higher accuracy. At the same time, the model has strong robustness and can accurately forecast even in extreme situations.
Downloads
References
Cheng Hao. China's urban and rural human settlements: achievements and challenges [J]. Human Habitat, 2016 (03): 22-23.
Gao Qingxian, Liu Junrong, Li Wentao, et al. Comparative study and enlightenment of air quality index (AQI) between China and the United States [J]. Environmental Science, 2015, 36 (04): 1141-1147.
Ding Yuxian, Sun Weina, Niu Jiangang. Research on AQI characterization of Hohhot-Baotou urban agglomeration from 2014 to 2019 [J]. Inner Mongolia Science and Technology and Economy, 2020 (14): 7-8.
Shen Haoyang, Wei Anlei, Wang Xiaowen, etc. Application of BP artificial neural network in prediction of SO2 mass concentration in ambient air [J]. Environmental Engineering, 2014, 32 (06): 117-121.
Kong Y W, Sheng L F, Li Y P, et al. Improving PM2.5 forecast during haze episodes over China based on a coupled 4D-LETKF and WRF-Chem system [J]. Atmospheric Research. Volume 249, Issue. 2021. PP 105366.
Hao Yongchao, Hou Xinrui, Yu Ling, etc. Research on the construction of air quality prediction model in Xingtai City based on neural network [J]. Computers and Information Technology, 2018, 26 (04): 69-74.
Xie Yonghua, Zhang Mingmin, Yang Le, et al. Prediction of urban PM2.5 concentration based on support vector machine regression [J]. Computer Engineering and Design, 2015, 36 (11): 3106-3111.
Si Zhijuan, Sun Baosheng, Li Xiaofang. Air quality prediction based on improved gray neural network combination model [J]. Journal of Environmental Engineering, 2013, 7 (09): 3543-3547.
Shi Xiaowen, Jiang Hongxun. Research on LSTM model for air quality prediction with high accuracy and strong robustness [J]. Statistics and Decision Making, 2019, 35 (16): 49-53.
Shi Xueliang, Li Liang, Zhao Qinghua. Air quality index prediction based on improved LSTM network [J]. Statistics and Decision Making, 2021, 37 (16): 57-60.
Sun Chaoyun, Du Yaohui, Pei Lili et al. Air quality index prediction method based on inverse variance multiple model fusion [J]. Environmental Engineering, 2023, 41 (02): 197-204.
Gao Song, He Zhuojun, Liu Ziyue, et al. Application of machine learning based differential fusion analysis in air quality prediction [J]. Electronic Measurement Technology, 2021, 44 (18): 85-92.
Zhu Juxiang, Ren Mingyu, Gu Wei, et al. Air quality prediction modeling based on CEEMDAN-IGWO-CNN-LSTM [J/OL]. Computer simulation: 1-11 [2024-02-19] http://kns.cnki.net/kcms/detail/11.3724.tp.20230922.1501.004.html.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Highlights in Science, Engineering and Technology
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
