Non Technical Summary
This project will enable forest monitoring at previously inaccessible scales by combining daily, high resolution satellite imagery with deep learning algorithms and extensive field observations. The innovation in this proposal is not in developing any one of the approaches; high resolution imagery has previously been used to map tree mortality, and deep learning has been used for object detection in high resolution remote sensing data. The innovation is in applying these approaches to noisy, high frequency, and high resolution satellite imagery to consistently and accurately detect fine-scale ecological patterns to monitor change over time. These analyses can be usedto inform land use planning and forest management. These tree mortality maps will improve the coordination of forest management activities through precisely identifying areas facing the greatest fire risk, optimizing timber harvest strategies, and forecasting future risks.
Animal Health Component
Research Effort Categories
Goals / Objectives
California's forest ecosystems are experiencing severe stress from drought, heat, fires, and pest outbreaks. Forest dieback, driven by high rates of tree mortality, is widespread across the state and is expected to increase as these stresses shift in geographic range and in intensity. Higher fire frequency and intensity, resulting from increasing rates of tree mortality, are expected to increase economic burdens on a wide range of institutions, including natural resource managers, firefighters, state and federal agencies, and homeowners. Furthermore, they are expected to bear a high cost on human health and wellbeing. A preventative, targeted approach to fire management is expected to reduce the economic, health, and environmental costs related to forest dieback, and developing tools to monitor and predict the risks posed by tree mortality across the state will be necessary to adopt a preventative management system. Our project proposes to use high resolution, high frequency satellite imagery and deep learning algorithms to develop a novel tree mortality mapping methodology to: a) identify dead trees at high spatial resolution; b) identify the approximate time of death at high temporal resolution, and; c) forecast future mortality risk at moderate spatial resolution through integration with climate and land cover data. We plan to commercialize the products developed in this proposal through sales of data and analyses to large landowners across California. We believe that, once mature, this approach can scale beyond California and be applied in other states with large forests and high tree mortality rates.
We propose to develop a prototype mapping methodology to identifyindividual- and stand-level tree mortality across California at high resolution, high frequency, and low cost. Meetingthe above requirements will require a big data-style approach to analysis and operations. We plan to achieve this bycombiningdaily, high resolution nanosatellite imagery with deepneural networkalgorithms and an extensive series of field observations of tree mortality.First, we plan to sample field sites and imagery using a stratified geographic sampling of California's ecosystems.We will use spatially-explicitobservations of live and dead trees to extract image data for model training.We plan to utilize novel methods for training neurtal networkstopredict tree mortality from image data extracted fromfield collections.The goal of our proposal is topredict fire risk, target individual trees for removal, andmap temporal trends in tree mortality using high resolution,regularly updated maps of tree mortality.