GeoNatShapes: a natural feature reference dataset for mapping and AI training
Data for journal article: GeoNat v1.0: A dataset for natural feature mapping with artificial intelligence and supervised learning
Dates
Publication Date
2020-06-22
Time Period
2020
Citation
Arundel, S.T., Li, W., Wang, S., Chan, A., Ariani, N., and Mohamed, M.S., 2020, GeoNat Shapes: a natural feature reference dataset for mapping and AI training: U.S. Geological Survey data release, https://doi.org/10.5066/P9X5BN1L.
Summary
These data were compiled for the use of training natural feature machine learning (GeoAI) detection and delineation. The natural feature classes include the Geographic Names Information System (GNIS) feature types Basins, Bays, Bends, Craters, Gaps, Guts, Islands, Lakes, Ridges and Valleys, and are an areal representation of those GNIS point features. Features were produced using heads-up digitizing from 2018 to 2019 by Dr. Sam Arundel's team at the U.S. Geological Survey, Center of Excellence for Geospatial Information Science, Rolla, Missouri, USA, and Dr. Wenwen Li's team in the School of Geographical Sciences at Arizona State University, Tempe, Arizona, USA. Figure 1 shows the areal boundary (cyan) of Bachelor Canyon, a GNIS valley [...]
Summary
These data were compiled for the use of training natural feature machine learning (GeoAI) detection and delineation. The natural feature classes include the Geographic Names Information System (GNIS) feature types Basins, Bays, Bends, Craters, Gaps, Guts, Islands, Lakes, Ridges and Valleys, and are an areal representation of those GNIS point features. Features were produced using heads-up digitizing from 2018 to 2019 by Dr. Sam Arundel's team at the U.S. Geological Survey, Center of Excellence for Geospatial Information Science, Rolla, Missouri, USA, and Dr. Wenwen Li's team in the School of Geographical Sciences at Arizona State University, Tempe, Arizona, USA.
Figure 1 shows the areal boundary (cyan) of Bachelor Canyon, a GNIS valley feature, and a bounding box for machine learning training (black) relative to the data sources used in its delineation: A) the historical topographic map, B) respective NAIP imagery and C) 3DEP elevation data stretched and shaded.
Click on title to download individual files attached to this item.
GeoNatShapes_v1.0_Metadata.xml Original FGDC Metadata
View
77.4 KB
application/fgdc+xml
Data_Metadata_v1.0.zip
394.8 KB
application/zip
Figure1.jpg “Figure 1”
498.9 KB
image/jpeg
Related External Resources
Type: Related Primary Publication
Arundel, ST, Li, W, Wang, S. GeoNat v1.0: A dataset for natural feature mapping with artificial intelligence and supervised learning. Transactions in GIS. 2020; 24: 556– 572. https://doi.org/10.1111/tgis.12633
The data were created to allow a machine to train its learning process in the recognition and circumscription of natural features using various data sources. Hence, their purpose is to support the creation of more such data from sources such as satellite imagery, elevation data and topographic maps. Natural feature training datasets did not exist before the creation of this one. The objectives of the research resulting in these data sets were to aid the automated mapping of natural features, particularly for spatial queries on the Semantic Web. By presenting the data in digital form, they can assist the easy creation of training images using various data sources.
Rights
The author(s) of these data request that data users contact them regarding intended use and to assist with understanding limitations and interpretation. Unless otherwise stated, all data, metadata and related materials are considered to satisfy the quality standards relative to the purpose for which the data were collected. Although these data and associated metadata have been reviewed for accuracy and completeness and approved for release by the U.S. Geological Survey (USGS), no warranty expressed or implied is made regarding the display or utility of the data for other purposes, nor on all computer systems, nor shall the act of distribution constitute any such warranty.