Spatio-Temporal data mining on MCS over Tibetan Plateau using satellite meteorological datasets

This paper presents an automatic meteorological data mining approach based on analyzing and mining heterogeneous remote sensed image datasets. The cloud structures are firstly identified and tracked in satellite remote sensed images, after which heterogeneous cloud features and properties are extracted and integrated to form a unified dataset. The C4.5 decision tree algorithm and dependency network analysis are then employed to discover useful knowledge for weather forecasting, by which a group of derivation rules and a conceptual model for metrological environment factors are generated. Experimental results have shown that the system reduces the heavy workload of manual weather forecasting and provides meaningful interpretations to the forecasted results.