Skip to main content
Advanced Search

Filters: Tags: {"scheme":"https://www.sciencebase.gov/vocab/category/WRET/CMS_Themes/CDI_CMS_Themes"} (X) > Categories: Project (X)

Folders: ROOT > ScienceBase Catalog > Community for Data Integration (CDI) > CDI Projects Fiscal Year 2018 ( Show direct descendants )

7 results (71ms)   

Location

Folder
ROOT
_ScienceBase Catalog
__Community for Data Integration (CDI)
___CDI Projects Fiscal Year 2018
View Results as: JSON ATOM CSV
thumbnail
Deep learning is a computer analysis technique inspired by the human brain’s ability to learn. It involves several layers of artificial neural networks to learn and subsequently recognize patterns in data, forming the basis of many state-of-the-art applications from self-driving cars to drug discovery and cancer detection. Deep neural networks are capable of learning many levels of abstraction, and thus outperform many other types of automated classification algorithms. This project developed software tools, resources, and two training workshops that will allow USGS scientists to apply deep learning to remotely sensed imagery and to better understand natural hazards and habitats across the Nation. The tools and...
thumbnail
The Community for Data Integration (CDI) Risk Map Project is developing modular tools and services to benefit a wide group of scientists and managers that deal with various aspects of risk research and planning. Risk is the potential that exposure to a hazard will lead to a negative consequence to an asset such as human or natural resources. This project builds upon a Department of the Interior project that is developing geospatial layers and other analytical results that visualize multi-hazard exposure to various DOI assets. The CDI Risk Map team has developed the following: a spatial database of hazards and assets, an API (application programming interface) to query the data, web services with Geoserver (an open-source...
thumbnail
Spatial data on landslide occurrence across the U.S. varies greatly in quality, accessibility, and extent. This problem of data variability is common across USGS Mission Areas; it presents an obstacle to developing national-scale products and to identifying areas with relatively good/bad data coverage. We compiled available data of known landslides into a national-scale, searchable online map, which greatly increases public access to landslide hazard information. Additionally, we held a workshop with landslide practitioners and sought broader input from the CDI community; based on recommendations we identified a limited subset of essential attributes for inclusion in our product. We also defined a quantitative metric...
thumbnail
Identifying, extracting, and mobilizing information from current and historical literature is a time-consuming part of organizing and collating synthetic data productions. This project explored the use of algorithm-based methods to identify and extract occurrence information from the GeoDeepDive (GDD) literature database to support upkeep of the Nonindigenous Aquatic Species (NAS) data. The GeoDeepDive API was extended to include query capabilities on terms from the Integrated Taxonomic Information System (ITIS). This functionality helped support identification of literature mentioning/focusing on species that are tracked by the Nonindigenous Aquatic Species Database. These methods were paired with algorithms to...
thumbnail
The Nonindigenous Aquatic Species (NAS) Database and Alert System (https://nas.er.usgs.gov/default.aspx) provides a framework for the rapid dissemination of new invasions as they are incorporated into the NAS Database. The system notifies registered users of new sightings of >1,330 non-native aquatic species as part of national-scale early detection and rapid response systems (EDRR), and in support of several federal programs: National Invasive Species Council, Aquatic Nuisance Species Task Force, and other Department of the Interior agencies. The NAS group has developed a new tool, the Alert Risk Mapper (ARM; https://nas.er.usgs.gov/AlertSystem/default.aspx), to characterize river reaches, lakes, and other waterbodies...
thumbnail
USGS will soon transition to the international metadata standards known collectively as ISO 19115. The open-ended nature of ISO benefits with much greater flexibility and vocabulary to describe research products. However, that flexibility means few constraints that can guide authors and ensure standardized, robust documentation across the bureau. This project proposed that the USGS data community develop content specifications to define standard USGS ISO metadata content requirements. These specifications would be modular in order to meet documentation needs of the diverse range of research data that USGS produces. Using the specifications, metadata authors will be guided to include appropriate metadata fields for...
thumbnail
Lower technical and financial barriers have led to a proliferation of lidar point-cloud datasets acquired to support diverse USGS projects. The objective of this effort was to implement an open-source, cloud-based solution through USGS Cloud Hosting Solutions (CHS) that would address the needs of the growing USGS lidar community. We proposed to allow users to upload point-cloud datasets to CHS-administered Amazon Web Services storage where open-source packages Entwine and Potree would provide visualization and manipulation via a local web browser. This functionality for individual datasets would mirror services currently available for USGS 3DEP data. After the software packages could not satisfy internal technical...