An air heavy pollution case judging method based on weather classification and meteorological element clustering comprises the following steps: classifying main weather systems and meteorological elements affecting PM2.5 concentration distribution from a meteorological point of view of factors influencing air pollution diffusion based on historical data of meteorological elements and monitored PM2.5 hourly data, and innovatively establishing a weather classification and pollutant source analysis algorithm based on a backward track pattern; and on the basis of the numerical WRF simulation result, looking for cases similar to typical weather situations of pollution weather in the same season in the history to serve for air quality forecast. A weather classification method and a numerical calculation simulation method are combined, which improves the accuracy of forecast results and reasonably avoids abnormality in numerical calculation results; an automatic classification similarity forecast method is built, which makes air quality forecast more business-oriented; and the cause and source of heavy pollution can be analyzed, and the applicability of the algorithm is improved greatly.