Since　most　of　the　existing　air　quality　index　(AQI)　predicting　models　focused　on　prediction　of　the　time　series　data　of　a　single　target　monitoring　station,　they　failed　to　consider　the　correlation　and　mutual　influence　among　the　air　quality　monitoring　station　sites　and　the　spatio-temporal　characteristics　of　air　quality.　And　this　will　lead　to　a　certain　one-sidedness　during　air　quality　prediction　of　a　particular　site.　Aimed　at　this　problem,　a　short-term　air　quality　prediction　model　based　on　K-nearest　neighbor　(KNN)　and　Long　Short-Term　Memory　(LSTM)　was　proposed.　The　model　firstly　used　KNN　algorithm　to　select　the　time　and　space-related　monitoring　stations,　then　the　air　quality　index　sequences　of　these　stations　were　constructed　into　data　sets,　followed　by　training　and　testing　processes　in　the　LSTM　model,　and　finally　the　model　was　verified　with　real　data.　It　is　suggested　that　the　prediction　accuracy　of　the　hybrid　prediction　model　constructed　in　this　paper　is　acceptable　in　terms　of　the　space-time　correlation,　and　it　could　be　an　alternative　for　further　application　of　air　quality　prediction.　©　Published　under　licence　by　IOP　Publishing　Ltd.