A neural network method for efficient vegetation mapping

Author(s): Carpenter, G.A. | Franklin, J. | Gopal, S. | Macomber, S. | Martens, S. | Woodcock, C.E. |

Year: 1999

Citation: Remote Sensing of Environment, 70, 326-338.

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.

Topics: Image Analysis, Machine Learning, Applications: Remote Sensing, Models: ARTMAP,

PDF download

Cross References