This project addresses the need to develop prototype methodologies for global monitoring of forest cover with coarse resolution data in the context of the Global Observations of Forest Cover activities. The project builds on previous research to improve methodologies for characterizing forest cover and changes in forest cover independent of the often varying thresholds of canopy cover considered to be "forest." By developing a training and validation data set based on in situ measurements as well as high resolution Landsat data, we are developing a prototype product for the conterminous United States using 250m and 500m MODIS data. The methodology for combining in situ, high resolution, and coarse resolution data serves as a prototype that can be extended to other parts of the world. We are also examining the ability of the methodology to identify changes in forest cover by applying it to individual years and assessing the extent to which differences represent actual change. This aspect of the project necessarily relies on AVHRR data as a time series of MODIS data has not yet been acquired. We are also addressing the need within GOFC for methodologies that are automated and repeatable. A number of techniques such as automated noise reduction for training data, feature selection, and enhancements to decision tree classifiers are being assessed for their potential to automate the procedures.