Advances in weather prediction have occurred on numerous fronts,from sophisticated physics packages in the latest mesoscale models to multi-model ensembles of medium range predictions. Thus, the skill of numerical weather forecasts continues to increase. Statistical techniques have further increased the utility of these predictions. The availability of large atmospheric data sets and faster processors in computers has made pattern recognition of major weather events a feasible means of statistically enhancing the value of numerical forecasts. This presentation examines the utility of pattern recognition in assisting the prediction of severe and major weather in the Middle Atlantic region. A new technique is described that employs an artificial intelligence clustering algorithm to objectively identify the patterns or fingerprints associated with past events. The potential refinement and applicability of this method as an operational forecasting tool by comparing numerical weather prediction forecasts to fingerprints already identified for major weather events is also discussed.