IN THE PROPOSED WORK WE WILL UNMIX LANDSAT DATA COMPILE DATA ON DISTURBANCE AND INTEGRATE THESE DATA UNDER A BAYESIAN FRAMEWORK TO ADDRESS HOW DISTURBANCE DYNAMICS ALTER RECOVERY TRAJECTORIES. TO UNMIX LANDSAT SPECIES-SPECIFIC HYPERSPECTRAL PROFILES WILL BE AGGREGATED TO THE LEVEL OF PLANT FUNCTIONAL GROUP AND USED TO DEVELOP ENDMEMBERS RESULTING IN MAPS OF THE PERCENT OF EACH LANDSAT PIXEL OCCUPIED BY THE FOLLOWING LAND COVER CLASSES: CONIFEROUS FOREST DECIDUOUS FOREST SHRUB HERBACEOUS COVER AND BARE GROUND 1984-2017 AT AN ANNUAL TIMESTEP AND VALIDATED WITH UNMANNED AIRCRAFT SYSTEMS (UASS) COLLECTS. TO COMPILE DISTURBANCE DATA WE WILL USE A SUITE OF SATELLITE PRODUCTS AERIAL SURVEYS CENSUS AND HOUSING DATA AND GOVERNMENT RECORDS. USING A BAYESIAN FRAMEWORK WE MODEL THE CHANGE IN THE MIXING PROPORTION OF EACH VEGETATION CLASS FOR EACH PIXEL AS WELL AS PROJECT CHANGES IN VEGETATION STATES OVER TIME UNDER DIFFERENT CONDITIONS. OUR METHODOLOGICAL APPROACH AND MODELING FRAMEWORK ALLOW ESTIMATING ERROR FROM VARIOUS SOURCES AND TRACKING THAT ERROR AS IT PROPAGATES THROUGHOUT THE MODEL.