A neural network method for efficient vegetation mapping

Gail A. Carpenter, Sucharita Gopal, Scott Macober, Siegfried Martens, Curtis E. Woodcock, Janet Franklin

Research output: Contribution to journalArticlepeer-review

95 Scopus citations

Abstract

This article describes the application of a neural network method designed to improve the efficiency of map production from remote sensing data. Specifically, the ARTMAP neural network produces vegetation maps of the Sierra National Forest, in Northern California, using Landsat Thematic Mapper (TM) data. In addition to spectral values, the data set includes terrain and location information for each pixel. The maps produced by ARTMAP are of comparable accuracy to maps produced by a currently used method, which requires expert knowledge of the area as well as extensive manual editing. In fact, once field observations of vegetation classes had been collected for selected sites, ARTMAP took only a few hours to accomplish a mapping task that had previously taken many months. The ARTMAP network features fast online learning, so that the system can be updated incrementally when new field observations arrive, without the need for retraining on the entire data set. In addition to maps that identify lifeform and Calveg species, ARTMAP produces confidence maps, which indicate where errors are most likely to occur and which can, therefore, be used to guide map editing.

Original languageEnglish (US)
Pages (from-to)326-338
Number of pages13
JournalRemote Sensing of Environment
Volume70
Issue number3
DOIs
StatePublished - Dec 1999

ASJC Scopus subject areas

  • Soil Science
  • Geology
  • Computers in Earth Sciences

Fingerprint Dive into the research topics of 'A neural network method for efficient vegetation mapping'. Together they form a unique fingerprint.

Cite this