BP　neural　network　which　was　trained　using　Bayesian　Regularization　method　based　on　mass　monitoring　data　and　meteorological　variable　was　used　to　forecast　the　hourly　average　concentration　of　O(3)　Sample　data　classification　according　to　seasons　was　used　to　improve　the　predictions.　The　results　show　that　data　mining　based　on　Neural　Networks　has　good　prediction　precision.