U.S. Navy weather observing and forecasting operations would be greatly assisted with the immediate assessment of meteorological parameters when ground observations are not available. To this end, numerical weather prediction data and satellite data from various sensors and platforms are being used to develop automated algorithms to assist in operational weather assessment and forecasting. Supervised machine learning techniques, including decision tree, neural network, K-nearest neighbor, etc., are used to discover patterns in the data and develop associated classification and parameter estimation algorithms. These data mining methods, used in a Knowledge Discovery from Databases (KDD) procedure, are applied to cloud ceiling height and rain accumulation estimation at remote locations using appropriate geostationary and polar orbiting satellite data in conjunction with Coupled Ocean/Atmosphere Mesoscale Prediction System (COAMPS) data. A database of COAMPS output, satellite data, climatology, and ground truth observations (METARS)is being created in an attempt to accurately diagnose and potentially forecast these sensible weather elements. COAMPS is triply-nested (81, 27, and 9 km) and run twice daily (12-hour forecasts) for three areas: U.S. west coast, Adriatic Sea, and Korean peninsula. COAMPS output parameters, coincident satellite parameters (including both geostationary and polar-orbiting data) and climatological information are extracted/computed at 45 METAR observation sites. Automated data collection routines have been written and data has been collected hourly since July, 2000. Data mining techniques have been applied relevant to cloud ceiling height and rain accumulation diagnosis. Methodology details and results from the data mining work will be presented.