Extracting Topography from Historic Topographic Maps Using GIS-Based Deep Learning

Authors' Affiliations

Briar Pierce, Department of Geosciences, College of Arts and Sciences, East Tennessee State University, Johnson City, TN. Dr. Eileen Ernenwein, Department of Geosciences, College of Arts and Sciences, East Tennessee State University, Johnson City, TN.

Location

Culp Center Rm. 304

Start Date

4-25-2023 2:00 PM

End Date

4-25-2023 2:20 PM

Faculty Sponsor’s Department

Geosciences

Name of Project's Faculty Sponsor

Eileen Ernenwein

Classification of First Author

Graduate Student-Master’s

Competition Type

Competitive

Type

Oral Presentation

Project's Category

Environmental Geography

Abstract or Artist's Statement

Historical topographic maps are valuable resources for studying past landscapes, but two-dimensional cartographic features are unsuitable for geospatial analysis. They must be extracted and converted into digital formats. This has been accomplished by researchers using sophisticated image processing and pattern recognition techniques, and more recently, artificial intelligence. While these methods are sometimes successful, they require a high level of technical expertise, limiting their accessibility. This research presents a straightforward method practitioners can use to create digital representations of historical topographic data within commercially available Geographic Information Systems (GIS) software. This study uses convolutional neural networks to extract elevation contour lines from a 1940 United States Geological Survey (USGS) topographic map in Sevier County, TN, ultimately producing a Digital Elevation Model (DEM). The topographically derived DEM (TOPO-DEM) is compared to a modern LiDAR-derived DEM to analyze its quality and utility. GIS-capable historians, archaeologists, geographers, and others can use this method in their research and land management practices.

This document is currently not available here.

Share

COinS
 
Apr 25th, 2:00 PM Apr 25th, 2:20 PM

Extracting Topography from Historic Topographic Maps Using GIS-Based Deep Learning

Culp Center Rm. 304

Historical topographic maps are valuable resources for studying past landscapes, but two-dimensional cartographic features are unsuitable for geospatial analysis. They must be extracted and converted into digital formats. This has been accomplished by researchers using sophisticated image processing and pattern recognition techniques, and more recently, artificial intelligence. While these methods are sometimes successful, they require a high level of technical expertise, limiting their accessibility. This research presents a straightforward method practitioners can use to create digital representations of historical topographic data within commercially available Geographic Information Systems (GIS) software. This study uses convolutional neural networks to extract elevation contour lines from a 1940 United States Geological Survey (USGS) topographic map in Sevier County, TN, ultimately producing a Digital Elevation Model (DEM). The topographically derived DEM (TOPO-DEM) is compared to a modern LiDAR-derived DEM to analyze its quality and utility. GIS-capable historians, archaeologists, geographers, and others can use this method in their research and land management practices.