Non-forest ecosystems, dominated by shrubs, grasses and herbaceous plants, provide ecosystem services including carbon sequestration and forage for grazing, and are highly sensitive to climatic changes. Yet these ecosystems are

Precise coastal shoreline mapping is essential for monitoring changes in erosion rates, surface hydrology, and ecosystem structure and function. Monitoring water bodies in the Arctic National Wildlife Refuge (ANWR) is of high importance, especially considering the potential for oil and natural gas exploration in the region. In this work, we propose a modified variant of the Deep Neural Network based U-Net Architecture for the automated mapping of 4 Band Orthorectified NOAA Airborne Imagery using sparsely labeled training data and compare it to the performance of traditional Machine Learning (ML) based approaches—namely, random forest, xgboost—and spectral water indices—Normalized Difference Water Index (NDWI), and Normalized Difference Surface Water Index (NDSWI)—to support shoreline mapping of Arctic coastlines. We conclude that it is possible to modify the U-Net model to accept sparse labels as input and the results are comparable to other ML methods (an Intersection-over-Union (IoU) of 94.86% using U-Net vs. an IoU of 95.05% using the best performing method).

Non-forest ecosystems, dominated by shrubs, grasses and herbaceous plants, provide ecosystem services including carbon sequestration and forage for grazing, yet are highly sensitive to climatic changes. Yet these ecosystems are poorly represented in remotely-sensed biomass products and are undersampled by in-situ monitoring. Current global change threats emphasise the need for new tools to capture biomass change in non-forest ecosystems at appropriate scales. Here we assess whether canopy height inferred from drone photogrammetry allows the estimation of aboveground biomass (AGB) across low-stature plant species sampled through a global site network. We found mean canopy height is strongly predictive of AGB across species, demonstrating standardised photogrammetric approaches are generalisable across growth forms and environmental settings. Biomass per-unit-of-height was similar within, but different among, plant functional types. We find drone-based photogrammetry allows for monitoring of AGB across large spatial extents and can advance understanding of understudied and vulnerable non-forested ecosystems across the globe.

No abstract

ABSTRACT. Although much progress has been made with various Arctic Observing efforts, assessing that progress can be difficult. What data collection efforts are established or underway? Where? By whom? To help meet the strategic needs of programs such as the U.S. Study of Environmental Arctic Change (SEARCH), the Arctic Observing Network (AON), Sustaining Arctic Observing Networks (SAON), and related initiatives, an update has been released for the Arctic Observing Viewer (AOV; http://ArcticObservingViewer.org). This web mapping application and information system has begun to compile the who, what, where, and when for thousands of data collection sites (such as boreholes, ship tracks, buoys, towers, sampling stations, sensor networks, vegetation sites, stream gauges, and observatories) wherever marine, terrestrial, or atmospheric data are collected. Contributing partners for this collaborative resource include the U.S. NSF, ACADIS, ADIwg, AOOS, a 2 dc, AON, ARMAP, BAID, CAFF, IASOA, INTERACT, and others. While focusing on U.S. activities, the AOV welcomes information exchange with international groups for mutual benefit. Users can visualize, navigate, select, search, draw, print, and more. AOV is founded on principles of interoperability, with open metadata and web service standards, so that agencies and organizations can use AOV tools and services for their own purposes. In this way, AOV will reinforce and complement other distributed yet interoperable cyber-resources and will help science planners, funding agencies, researchers, data specialists, and others to assess status, identify overlap, fill gaps, optimize sampling design, refine network performance, clarify directions, access data, coordinate logistics, collaborate, and more in order to meet Arctic Observing goals.