Fire danger predicted by the Fire Weather Index, derived from point-source weather records, is limited spatially. NOAA-AVHRR images were used to model the Duff Moisture Code and Drought Code of the Fire Weather Index in boreal forests of a 250,000 km2 portion of northern Alberta and the southern Northwest Territories, Canada. Temporal and spatial factors affecting slow changing fuel moisture codes (Duff Moisture Code and Drought Code) and spectral variables (normalized difference vegetation index, surface temperature, relative greenness and the ratio between normalized difference vegetation index and surface temperature) were identified. Models were developed on a yearly and seasonal basis. They were strongest in spring, but had a tendency to saturate. Drought Code was best modeled in the spring of 1995 when categorized spatially by broad forest cover types. Mapping Drought Code with this spectral model improved spatial resolution. Limitations and possible improvements of the study are also discussed.