GLORIA

GEOMAR Library Ocean Research Information Access

X

Your email was sent successfully. Check your inbox.

An error occurred while sending the email. Please try again.

Proceed reservation?

Export
Filter
  • MDPI AG  (2)
  • 1
    Online Resource
    Online Resource
    Arctic Vegetation Mapping Using Unsupervised Training Datasets and Convolutional Neural Networks
    MDPI AG ; 2019
    In:  Remote Sensing Vol. 11, No. 1 ( 2019-01-02), p. 69-
    Details
    In: Remote Sensing, MDPI AG, Vol. 11, No. 1 ( 2019-01-02), p. 69-
    Abstract: Land cover datasets are essential for modeling and analysis of Arctic ecosystem structure and function and for understanding land–atmosphere interactions at high spatial resolutions. However, most Arctic land cover products are generated at a coarse resolution, often limited due to cloud cover, polar darkness, and poor availability of high-resolution imagery. A multi-sensor remote sensing-based deep learning approach was developed for generating high-resolution (5 m) vegetation maps for the western Alaskan Arctic on the Seward Peninsula, Alaska. The fusion of hyperspectral, multispectral, and terrain datasets was performed using unsupervised and supervised classification techniques over a ∼343 km2 area, and a high-resolution (5 m) vegetation classification map was generated. An unsupervised technique was developed to classify high-dimensional remote sensing datasets into cohesive clusters. We employed a quantitative method to add supervision to the unlabeled clusters, producing a fully labeled vegetation map. We then developed convolutional neural networks (CNNs) using the multi-sensor fusion datasets to map vegetation distributions using the original classes and the classes produced by the unsupervised classification method. To validate the resulting CNN maps, vegetation observations were collected at 30 field plots during the summer of 2016, and the resulting vegetation products developed were evaluated against them for accuracy. Our analysis indicates the CNN models based on the labels produced by the unsupervised classification method provided the most accurate mapping of vegetation types, increasing the validation score (i.e., precision) from 0.53 to 0.83 when evaluated against field vegetation observations.
    Type of Medium: Online Resource
    ISSN: 2072-4292
    URL: Article
    DOI: 10.3390/rs11010069
    Language: English
    Publisher: MDPI AG
    Publication Date: 2019
    detail.hit.zdb_id: 2513863-7
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 2
    Online Resource
    Online Resource
    Untargeted Exometabolomics Provides a Powerful Approach to Investigate Biogeochemical Hotspots with Vegetation and Polygon Type in Arctic Tundra Soils
    MDPI AG ; 2021
    In:  Soil Systems Vol. 5, No. 1 ( 2021-02-09), p. 10-
    Details
    In: Soil Systems, MDPI AG, Vol. 5, No. 1 ( 2021-02-09), p. 10-
    Abstract: Rising temperatures in the Arctic have led to the thawing of tundra soils, which is rapidly changing terrain, hydrology, and plant and microbial communities, causing hotspots of biogeochemical activity across the landscape. Despite this, little is known about how nutrient-rich low molecular weight dissolved organic matter (LMW DOM) varies within and across tundra ecosystems. Using a high-resolution nano-liquid chromatography-mass spectrometry (LC/MS) approach, we characterized the composition and availability of LMW DOM from high-centered polygons (HCP) and low-centered polygons (LCP) with Eriophorum angustifolium or Carex aquatilis as the dominant vegetation. Over 3000 unique features (i.e., discrete mass/charge ions) were detected; 521 were identified as differentially abundant between polygonal types and 217 were putatively annotated using high mass accuracy MS data. While polygon type was a strong predictor of LMW DOM composition and availability, vegetation and soil depth were also important drivers. Extensive evidence was found for enhanced microbial processing at the LCP sites, which were dominated by Carex plant species. We detected significant differences between polygon types with varying aboveground landscape features or properties, and hotspots of biogeochemical activity, indicating LMW DOM, as quantified by untargeted exometabolomics, provides a window into the dynamic complex interactions between landscape topography, vegetation, and organic matter cycling in Arctic polygonal tundra soils.
    Type of Medium: Online Resource
    ISSN: 2571-8789
    URL: Article
    DOI: 10.3390/soilsystems5010010
    Language: English
    Publisher: MDPI AG
    Publication Date: 2021
    detail.hit.zdb_id: 2932897-4
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
Close ⊗
This website uses cookies and the analysis tool Matomo. More information can be found here...