资源环境科技发展态势分析平台

The level of tree mortality and drought observed over the past decade in North America has been described as 'unparalleled' in our modern history, in particular in the Sierra Nevada, California. Forest managers could use early warning of where and how much tree mortality to expect in the very near future to plan and prioritize hazard tree removal, pest suppression activities, infer location of funding needs and fuels reduction treatments as well as access for firefighting. To answer these needs, we developed an empirically-based forecast model for expected tree mortality for an upcoming year based on (1) previous years' tree mortality as observed in late summer; (2) previous years' hydrologic year precipitation levels; and (3) site characteristics including amount of available host. Using this approach, initial forecasts for the next growing season can be developed by late fall for the following late summer. We demonstrated the application of this model by developing a forecast for the state of California for 2017. The explanatory variables in the California model accounted for similar to 43% of the variability in tree mortality. Overall, the model missed forecasting high levels of mortality in approximately 5% of forested or woodland locations for the state of California. Locations with more mortality than expected in 2015 & 2016 were mostly associated with new outbreaks of insects; land use changes, and margins of prescribed- or wildfires not initially attributed. The forecasts may also be useful to natural resource and land managers in locating new outbreaks that may be attributed to novel behavior or exotic insects. Published by Elsevier B.V.