Search for: All records

Abstract. Studies in recent decades have shown strong evidence of physical and biological changes in the Arctic tundra, largely in response to rapid rates of warming. Given the important implications of these changes for ecosystem services, hydrology, surface energy balance, carbon budgets, and climate feedbacks, research on the trends and patterns of these changes is becoming increasingly important and can help better constrain estimates of local, regional, and global impacts as well as inform mitigation and adaptation strategies. Despite this great need, scientific understanding of tundra ecology and change remains limited, largely due to the inaccessibility of this region and less intensive studies compared to other terrestrial biomes. A synthesis of existing datasets from past field studies can make field data more accessible and open up possibilities for collaborative research as well as for investigating and informing future studies. Here, we synthesize field datasets of vegetation and active-layer properties from the Alaskan tundra, one of the most well-studied tundra regions. Given the potentially increasing intensive fire regimes in the tundra, fire history and severity attributes have been added to data points where available. The resulting database is a resource that future investigators can employ to analyze spatial and temporal patterns in soil, vegetation, and fire disturbance-related environmental variables across the Alaskan tundra. This database, titled the Synthesized Alaskan Tundra Field Database (SATFiD), can be accessed at the Oak Ridge National Laboratory Distributed Active Archive Center (ORNL DAAC) for Biogeochemical Dynamics (Chen et al., 2023: https://doi.org/10.3334/ORNLDAAC/2177). 

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).