Heavy pollution sequence case base-based region heavy pollution discriminating and prediction method and device

Abstract

The present invention discloses a heavy pollution sequence case base-based region heavy pollution discriminating and prediction method and device and belongs to the atmospheric heavy pollution prediction technical field. The heavy pollution sequence case base-based region heavy pollution discriminating and prediction method includes the following steps that: a historical heavy pollution sequence case base of a target region is established according to collected pollution index data and meteorological element data monitored by each monitoring site of the target region, sequences in the case base are composed of meteorological element data; on the basis of the predicted meteorological element data of the target region in a certain future period, the sequence of the future period is obtained; and similarity comparison is performed on the sequence of the future period and the sequences in the historical heavy pollution sequence case base, so that the heavy pollution condition of the target region in the future period can be discriminated. With the heavy pollution sequence case base-based region heavy pollution discriminating and prediction method and device of the invention adopted, the accuracy of the prediction of the heavy pollution of the target region in a selected future period can be improved; and the accuracy of the prediction is high.

Description

technical field [0001] The invention relates to the technical field of heavy air pollution forecasting, in particular to a regional heavy pollution discrimination and forecasting method and device based on a heavy pollution sequence case library. Background technique [0002] In recent years, with the rapid development of social economy and the acceleration of industrialization and urbanization, the problem of complex air pollution has become increasingly prominent, seriously threatening the health and ecological safety of the people, and has become a major environmental problem that is highly concerned by all sectors of society and needs to be resolved urgently. . The air pollution in my country's cities is serious, and about one-fifth of the cities in the country have serious air pollution. Among the first batch of 74 cities to implement the new standards in 2014, only 8 cities met the air quality standards. Urban air pollution began to change from coal smoke to coal smo...

AI Technical Summary

Problems solved by technology

However, the physical and chemical mechanisms adopted by the numerical models of various institutions are different, and they have mutual strengths in the prediction of different heavy pollution processes in North China, but the prediction results fluctuate greatly, and it is difficult to achieve complementary advantages

Statistical forecasting methods use time series analysis (such as ARMA, ARIMA, SVM, ANN, etc. models) to train the evolution of pollution and weather conditions in the past, and predict future air quality. The dependence on historical data is large, and the regional heavy pollution process cannot be considered as a whole, and it lacks certain physical meaning

Expert forecasting is mainly to forecast experts’ comprehensive pollution and meteorological conditions and carry out manual identification. However, this method relies too much on the personal judgment of experts. In most cases, experts can only provide a rough judgment basis for dry stickiness, which is not very accurate.

Images