GeoNat v1.0: A dataset for natural feature mapping with artificial intelligence and supervised learning

Samantha T. Arundel, Wenwen Li, Sizhe Wang

Research output: Contribution to journalArticlepeer-review

12 Scopus citations


Machine learning allows “the machine” to deduce the complex and sometimes unrecognized rules governing spatial systems, particularly topographic mapping, by exposing it to the end product. Often, the obstacle to this approach is the acquisition of many good and labeled training examples of the desired result. Such is the case with most types of natural features. To address such limitations, this research introduces GeoNat v1.0, a natural feature dataset, used to support artificial intelligence-based mapping and automated detection of natural features under a supervised learning paradigm. The dataset was created by randomly selecting points from the U.S. Geological Survey’s Geographic Names Information System and includes approximately 200 examples each of 10 classes of natural features. Resulting data were tested in an object-detection problem using a region-based convolutional neural network. The object-detection tests resulted in a 62% mean average precision as baseline results. Major challenges in developing training data in the geospatial domain, such as scale and geographical representativeness, are addressed in this article. We hope that the resulting dataset will be useful for a variety of applications and shed light on training data collection and labeling in the geospatial artificial intelligence domain.

Original languageEnglish (US)
Pages (from-to)556-572
Number of pages17
JournalTransactions in GIS
Issue number3
StatePublished - Jun 1 2020

ASJC Scopus subject areas

  • General Earth and Planetary Sciences


Dive into the research topics of 'GeoNat v1.0: A dataset for natural feature mapping with artificial intelligence and supervised learning'. Together they form a unique fingerprint.

Cite this