Live fuel moisture content, or the ratio of water to dry mass in plants, has been linked to the speed and intensity at which fires burn. More moisture reduces the amount of energy given off during a fire, and slows fire growth. Less moisture indicates the landscape is prone for fast burning, intense fires. As a result, this information is highly relevant to support pre-fire fuels management and fire risk mapping. In the images here, we apply a machine learning model trained on data from the National Fuel Moisture Database and forced with relevant hydrologic data (e.g. evapotranspiration, reference evapotranspiration, precipitation) through the OpenET application programming interface to model live fuel moisture content at scales and frequencies relevant for pre-fire fuel reductions, prescribed burns, and informing fire response strategies. 

For hyperwall presenter use only. Please do not link to this page from public websites.