基于LSTM-RF模型的拉萨市空气质量预测分析

打开文本图片集

中图分类号：TP391.4；X87 文献标识码：A 文章编号：2096-4706（2025）19-0152-05

Abstract： With the accelerationof industrializationand urbanization， China's economic level has significantly improved， andairqualityisues have increasinglybecomeafocusof publicconcern.BasedonAirQuality Index （AQI）dataand the concentrations of six major pollutants （PM2.5 PM10. SO2 NO2 CO，and O3⋅ ）inLhasa from January1，2015 to December31， 2021，the Random Forest （RF）algorithm is used to identify the pollutant characteristic （ PM10 concentration） highly correlated with AQI. On this basis，the prediction results of the Long Short-Term Memory （LSTM） model and the PM10 concentration are usedasiput features tofurtherconstructtheRFmodeltoimprove thepredictionperformanceand stabilityTheexperimental results showthat thepredictionperformanceofthesingleLSTMmodelisslightlyworsethanthatofthesingleRFmodel，while the prediction abilityof theLSTM-RFcombined model issignificantlyimproved.Thecombined model provides ffective methodologicalsupport forairqualityprediction，andalsolaysasolidsientificfoundationforaccuratepolutionpreventionand control， environmental governance and policy formulation.

Keywords：AQI; LSTMmodel; RFmodel; LSTM-RF model

0 引言

我国经济与科技的迅速发展显著提升了居民生活水平，但环境问题亦日益凸显，逐渐成为制约可持续发展的重要因素。（剩余6898字）