A Neural Network Method for Efficient Vegetation Mapping

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.

[1]  Stephen Grossberg,et al.  ARTMAP: supervised real-time learning and classification of nonstationary data by a self-organizing neural network , 1991, [1991 Proceedings] IEEE Conference on Neural Networks for Ocean Engineering.

[2]  Gail A. Carpenter,et al.  ART neural networks for remote sensing: vegetation classification from Landsat TM and terrain data , 1996, IGARSS '96. 1996 International Geoscience and Remote Sensing Symposium.

[3]  N. Veitch,et al.  Habitat mapping from satellite imagery and wildlife survey data using a Bayesian modeling procedure in a GIS , 1993 .

[4]  Alan H. Strahler,et al.  Fuzzy Neural Network Classification of Global Land Cover from a 1° AVHRR Data Set , 1999 .

[5]  J. Franklin,et al.  Coniferous Forest Classification and Inventory Using Landsat and Digital Terrain Data , 1986, IEEE Transactions on Geoscience and Remote Sensing.

[6]  Gail A. Carpenter,et al.  ARTMAP-IC and medical diagnosis: Instance counting and inconsistent cases , 1998, Neural Networks.

[7]  John A. Richards,et al.  Remote Sensing Digital Image Analysis: An Introduction , 1999 .

[8]  Alan H. Strahler,et al.  Stratification of forest vegetation for timber inventory using Landsat and collateral data , 1980 .

[9]  Russell G. Congalton,et al.  Mapping old growth forests on National Forest and Park Lands in the Pacific Northwest from remotely sensed data , 1993 .

[10]  Stephen Grossberg,et al.  Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps , 1992, IEEE Trans. Neural Networks.

[11]  V. Judson Harward,et al.  Mapping forest vegetation using landsat TM imagery and a canopy reflectance model , 1994 .

[12]  Manfred M. Fischer,et al.  Fuzzy ARTMAP — A Neural Classifier for Multispectral Image Classification , 1997 .

[13]  Gail A. Carpenter,et al.  A Neural Network Method for Mixture Estimation for Vegetation Mapping , 1999 .

[14]  David O. Wallin,et al.  Cover Land Cover on the Western Slopes of the Central Oregon Cascade Range , 1995 .

[15]  Pol Coppin,et al.  Satellite inventory of Minnesota forest resources , 1994 .