Prediction and Early Warning of Air Quality based on the LSTM-ARIMA Model
Keywords:PM2.5 Calculate; AQI Calculate; The LSTM-ARIMA Combined Model; MATLAB.
At present, China's economy is transforming from a stage of high-speed growth to a stage of high-quality development. Building an ecological civilization is an important part of the realization of the Chinese dream of national rejuvenation. Air pollution will cause harm to human health, ecological environment, social and economic aspects, and its pollution level is affected by many factors, such as PM2.5, PM10, CO, temperature, wind speed, precipitation and so on. In order to implement the party's 20th spirit, strengthen the coordinated control of pollutants, basically eliminate heavy pollution weather, improve and improve the response and disposal mechanism of heavy pollution weather, a place issued an emergency plan for pollution weather, which will strengthen monitoring and early warning, energy conservation and emission reduction, and minimize the impact of pollution weather. To explore the influencing factors of PM2.5 concentration change, more accurate prediction PM2.5 concentration and AQI index, this paper for the prediction and warning of air quality, using the daily pollutants in January 2015 to April 2023, the data of analysis of PM2.5 concentration, the importance of the top three factors PM10, average temperature, CO as auxiliary variables, to construct the LSTM-ARIMA combination model. First, LSTM was used for multi-factor prediction. In order to improve the accuracy of the prediction results, the prediction error of LSTM was then linearly corrected based on the ARIMA model, the time step was adjusted to observe the previous data, and the prediction results of the model were evaluated by root mean square error (RMSE).
Liu D J, Li L. Application Study of Comprehensive Forecasting ModelBased on Entropy Weighting Method on Trend of PM2.5 Concentration inGuangzhou, China [J]. International journal of environmental research and publichealth, 2015,12(6):7085-7099. DOI: https://doi.org/10.3390/ijerph120607085
Yang Z S, Wang J. A new air quality monitoring and early warningsystem: Air quality assessment and air pollutant concentration prediction[J]. Environmental Research, 2017, 158:105-117. DOI: https://doi.org/10.1016/j.envres.2017.06.002
Ni Zhiwei, Zhu Xuhui, Cheng Meiying. .Air Quality Prediction Method Based on Fish Swarm and Fractal Dimension[J]. Pattern Recognition and Artificial Intelligence, 2016,29 (12): 1122-1131.
Yang Taofeng,Peng Yi. A hybrid ARIMA-SVM model for the study of air quality prediction based on
improved PSO[J]. Journal of Yunnan University (Natural Science Edition), 2020,42 (05): 854-862.
He K,Zhang X,Ren S,et al.Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition [C]// IEEE Transactions on Pattern Analysis & Machine Intelligence,2014: 1904-16. DOI: https://doi.org/10.1109/TPAMI.2015.2389824
Wang Xia,Chen Xiaojian. SPATIAL-TEMPORAL CHARACTERISTICS AND CONSTRAINT OF PRIMARY SCHOOL COMMUTING IN XI’AN CITY[J]. Urban Planning, 2018,42 (11): 148-158.
How to Cite
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.