Samantha T Arundel, PhD
Dr. Samantha T. Arundel is a research geographer in the Center of Excellence for Geospatial Information Science at the U.S. Geological Survey. Her research focuses on automating physical feature mapping and modeling using various techniques like traditional raster modeling, GEOBIA and machine learning.
Dr. Samantha T. Arundel (Sam) received her Ph.D. in geography from Arizona State University in 2000 and was an assistant and then associate professor at Northern Arizona University where her research focused on spatial modeling and automation of plant/climate relationships. In 2009, when she joined the USGS, she first served as raster specialist in the Ortho & Elevation section and as elevation and hydrography specialist for the Applied Research and Technology Branch. During this time, she led the contour generation development team in developing algorithms for automating contour production from 10-meter elevation data for the USTopo product; and served as the program manager for the automation of the National Elevation Dataset production, in its transition from Earth Resource Observation System (EROS) to the National Geospatial Technical Operations Center (NGTOC). In 2015, Sam moved to the Center of Excellence for Geospatial Information Science, the research section of the NGTOC, where she is a Research Geographer conducting research on automated terrain mapping and modeling using various techniques like traditional raster modeling, geographic object-based image analysis and machine learning.
Science and Products
GeoNatShapes: a natural feature reference dataset for mapping and AI training
GeoAI for spatial image processing
A guide to creating an effective big data management framework
Historical maps inform landform cognition in machine learning
Geomorphometric analysis of the Summit and Ridge classes of the Geographic Names Information System
GeoImageNet: A multi-source natural feature benchmark dataset for GeoAI and supervised machine learning
GeoAI and the future of spatial analytics
Deep learning detection and recognition of spot elevations on historic topographic maps
The evolution of geospatial reasoning, analytics, and modeling
GeoAI in the US Geological Survey for topographic mapping
Spatial data reduction through element -of-interest (EOI) extraction
Improving the positional and vertical accuracy of named summits above 13,000 ft in the United States
Automated extraction of areal extents for GNIS Summit features using the eminence core method
Non-USGS Publications**
**Disclaimer: The views expressed in Non-USGS publications are those of the author and do not represent the views of the USGS, Department of the Interior, or the U.S. Government.
ADOM: A Data Orchestration Manager
Science and Products
- Data
GeoNatShapes: a natural feature reference dataset for mapping and AI training
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 digitizi - Publications
Filter Total Items: 24
GeoAI for spatial image processing
The development of digital image processing, as a subset of digital signal processing, depended upon the maturity of photography and image science, introduction of computers, discovery and advancement of digital recording devices, and the capture of digital images. In addition, government and industry applications in the Earth and medical sciences were paramount to the growth of the technology. FrAuthorsSamantha Arundel, Kevin G McKeehan, Wenwen Li, Zhining GuA guide to creating an effective big data management framework
Many agencies and organizations, such as the U.S. Geological Survey, handle massive geospatial datasets and their auxiliary data and are thus faced with challenges in storing data and ingesting it, transferring it between internal programs, and egressing it to external entities. As a result, these agencies and organizations may inadvertently devote unnecessary time and money to convey data withoutAuthorsSamantha Arundel, Kevin G McKeehan, Bryan B Campbell, Andrew N. Bulen, Philip T. ThiemHistorical maps inform landform cognition in machine learning
No abstract available.AuthorsSamantha Arundel, Sinha Gaurav, Wenwen Li, David P. Martin, Kevin G McKeehan, Philip T. ThiemGeomorphometric analysis of the Summit and Ridge classes of the Geographic Names Information System
This research aims to conduct a geosemantic comparison of landforms classified in the Summit and Ridge feature classes in the Geographic Names Information System (GNIS). The comparison is based on a 2D shape analysis of manually delineated polygons produced by USGS staff to correspond to 33,304 Summit and 8,006 Ridge features. Five shape measures were chosen for this specific geomorphometry-basedAuthorsSinha Gaurav, Samantha Arundel, Romim Somadder, David P. Martin, Kevin G McKeehanGeoImageNet: A multi-source natural feature benchmark dataset for GeoAI and supervised machine learning
The field of GeoAI or Geospatial Artificial Intelligence has undergone rapid development since 2017. It has been widely applied to address environmental and social science problems, from understanding climate change to tracking the spread of infectious disease. A foundational task in advancing GeoAI research is the creation of open, benchmark datasets to train and evaluate the performance of GeoAIAuthorsWenwen Li, Sizhe Wang, Samantha Arundel, Chia-Yu HsuGeoAI and the future of spatial analytics
This chapter discusses the challenges of traditional spatial analytical methods in their limited capacity to handle big and messy data, as well as mining unknown or latent patterns. It then introduces a new form of spatial analytics—geospatial artificial intelligence (GeoAI)—and describes the advantages of this new strategy in big data analytics and data-driven discovery. Finally, a convergent spaAuthorsWenwen Li, Samantha ArundelDeep learning detection and recognition of spot elevations on historic topographic maps
Some information contained in historical topographic maps has yet to be captured digitally, which limits the ability to automatically query such data. For example, U.S. Geological Survey’s historical topographic map collection (HTMC) displays millions of spot elevations at locations that were carefully chosen to best represent the terrain at the time. Although research has attempted to reproduce tAuthorsSamantha Arundel, Trenton P. Morgan, Philip T. ThiemThe evolution of geospatial reasoning, analytics, and modeling
The field of geospatial analytics and modeling has a long history coinciding with the physical and cultural evolution of humans. This history is analyzed relative to the four scientific paradigms: (1) empirical analysis through description, (2) theoretical explorations using models and generalizations, (3) simulating complex phenomena and (4) data exploration. Correlations among developments in geAuthorsSamantha Arundel, Wenwen LiGeoAI in the US Geological Survey for topographic mapping
Geospatial artificial intelligence (GeoAI) can be defined broadly as the application of artificial intelligence methods and techniques to geospatial data, processes, models, and applications. The application of these methods to topographic data and phenomena is a focus of research in the US Geological Survey (USGS). Specifically, the USGS has researched and developed applications in terrain featurAuthorsE. Lynn Usery, Samantha Arundel, Ethan J. Shavers, Larry Stanislawski, Philip T. Thiem, Dalia E. VarankaSpatial data reduction through element -of-interest (EOI) extraction
Any large, multifaceted data collection that is challenging to handle with traditional management practices can be branded ‘Big Data.’ Any big data containing geo-referenced attributes can be considered big geospatial data. The increased proliferation of big geospatial data is currently reforming the geospatial industry into a data-driven enterprise. Challenges in the big spatial data domain can bAuthorsSamantha Arundel, E. Lynn UseryImproving the positional and vertical accuracy of named summits above 13,000 ft in the United States
The National Map (TNM) portal provides public access to U.S. Geological Survey (USGS) high-resolution topographic datasets, and maps from the Historical Topographic Map Collection (HTMC). Elevation values shown on HTMC maps were obtained from ground spot elevation measurements, as compared to today’s elevation measurements derived from more efficient methods, such as lidar, radar, or sonar. TheseAuthorsSamantha Arundel, Gaurav Sinha, Arthur ChanAutomated extraction of areal extents for GNIS Summit features using the eminence core method
An important objective of the U.S. Geological Survey (USGS) is to enhance the Geographic Names Information System (GNIS) by automatically associating boundaries with terrain features that are currently spatially represented as two-dimensional points. In this paper, the discussion focuses on experiments for mapping GNIS Summit features using the eminence core region-growing method, which maps the aAuthorsGaurav Sinha, Samantha ArundelNon-USGS Publications**
"Cole, K. L., Cannella, J., Coats, L., Arundel, S.T., Mead, J. and Fisher, J. 2008. “The biogeographic histories of Pinus monophylla and Pinus edulis over the last 50,000 years.” Journal of Biogeography 35:257-269.Cole, K.L. and Arundel, S.T. 2007. “Modeling the climatic requirements for Southwestern plant species.” Proceedings of the Twenty-First Annual Pacific Climate Workshop, Technical Report 79 (ed. by S.W. Starratt, P. Cornelius and J.G. Joelson Jr.), pp. 31-39. Interagency Ecological Program for the San Francisco Estuary, State of California, Sacramento, California.Cole, K.L., Ironside, K., Arundel, S.T., Duffy, P. and Shaw, J. 2007. “Modeling future plant distributions on the Colorado Plateau: an example using Pinus edulis.” The Colorado Plateau III: integrating research and resources management for effective conservation (ed. by C. van Riper III and M. Sogge), pp. 319-330. University of Arizona Press, Tucson.Cole, K.L., Ironside, K., Arundel, S.T., Duffy, P. and Shaw, J. 2007. “Projecting the Future Distribution of Pinyon Pine.” White Paper for the Arizona Governor.Cole, K.L. and Arundel, S.T. 2007.” Modeling the climatic requirements for Southwestern plant species.” Proceedings of the Twenty-First Annual Pacific Climate Workshop, Technical Report 79 (ed. by S.W. Starratt, P. Cornelius and J.G. Joelson Jr.), pp. 31-39. Interagency Ecological Program for the San Francisco Estuary, State of California, Sacramento, California.Arundel, S. T. 2005. “Using Spatial Models to Establish Climatic Limiters of Plant Species’ Distributions.” Ecological Modelling 162:159-181.Arundel, S.T. and Cole, K.L. 2004. “The Need for More Precise, Accurate, and Complete Plant Distribution Data, and Its Importance in Reconstructing Past Climates,” Annual Meeting of the American Geophysical Union Proceedings, San Francisco, December.Cole, K.L., Ferguson, G., Cannella, J., Spellenburg, R., Saunders, A., Arundel, S.T. & Riser, J. 2003. “Digital rangemaps for North American one and two-needled pinyon pines (Pinus monophylla, P. edulis, and fallax and californiarum-types).”Arundel, S.T. 2002. “Modeling Plant Species’ Climatic Limiters to Analyze Macrofossils in Sonoran Desert Packrat Middens.” Quaternary Research, 58(2):112-121."**Disclaimer: The views expressed in Non-USGS publications are those of the author and do not represent the views of the USGS, Department of the Interior, or the U.S. Government.
- Software
ADOM: A Data Orchestration Manager
A Data Orchestration Manager (ADOM) is a user interface designed to enforce data management goals by entwining and extending the open-source file management tool rclone. The rclone tool provides data movement and management functionality in and between supported end-user-defined endpoints, also known as remotes. ADOM takes rclone a step further by wrapping rclone functionality into USGS-specific f