Comparison of Neural Networks and Statistical Methods in Classification of Ecological Habitats Using FIA Data
Two artificial neural networks (ANN) and three traditional statistical classification methods are used to classify Forest Inventory and Analysis (FIA) plots into six ecological habitats in the U.S. Northeast. Four variables (overstory and understory species composition, hardwood basal area percentage, and current FIA forest type) are identified from a list of available stand variables as the most important discriminating variables for habitat classification. The error matrix and accuracy indices are used to assess the classification accuracy of the models and to test the differences between the five classifiers. The ANN models (MLP and RBF) are superior to the traditional statistical methods such as linear discriminant analysis and minimum-distance classification. The classification accuracy of the ANN models is 90% or higher for overall classification, and exceeds 92% in five of the six habitat categories. The K-Nearest Neighbor (KNN) method classifies the six ecological habitats as accurately as the two neural network models. This study shows that the ANN models and KNN method have a great potential for the classification of ecological habitats using FIA data, due to their flexibility of modeling algorithms and robustness to the problems in FIA data such as non-Gaussian distributions, nonlinear relationships, outliers and noise in the data. For. Sci. 49(4):619–631.
Keywords: K-nearest neighbor classification; Multi-Layer Perceptron (MLP); Radial Basis Function (RBF); accuracy assessment; environmental management; forest; forest management; forest resources; forestry; forestry research; forestry science; linear discriminant analysis; minimum-distance classification; natural resource management; natural resources
Document Type: Miscellaneous
Affiliations: 1: Research Assistant Faculty of Forest and Natural Resources Management, State University of New York, College of Environmental Science and Forestry, One Forestry Drive, Syracuse, NY, 13210, Phone: (315) 446-0980 firstname.lastname@example.org 2: Associate Professor Faculty of Forest and Natural Resources Management, State University of New York, College of Environmental Science and Forestry, One Forestry Drive, Syracuse, NY, 13210, Phone: (315) 470-6558; Fax: (315) 470-6535 email@example.com 3: Professor Faculty of Forest and Natural Resources Management, State University of New York, College of Environmental Science and Forestry, One Forestry Drive, Syracuse, NY, 13210, Phone: (315) 470-6569 firstname.lastname@example.org 4: Deceased Research Forester USDA Forest Service Northeastern Research Station, Durham, NH, 03824, 5: Professor College of Natural Resources, Forestry and Agriculture, University of Maine, Orono, ME, 04469, Phone (207) 581-2836 email@example.com 6: Forest Consultant L.E. Caldwell Co., P.O. Box 563 Turner, ME, 04282, Phone (207) 225-3955 firstname.lastname@example.org
Publication date: 2003-08-01
- Forest Science is a peer-reviewed journal publishing fundamental and applied research that explores all aspects of natural and social sciences as they apply to the function and management of the forested ecosystems of the world. Topics include silviculture, forest management, biometrics, economics, entomology & pathology, fire & fuels management, forest ecology, genetics & tree improvement, geospatial technologies, harvesting & utilization, landscape ecology, operations research, forest policy, physiology, recreation, social sciences, soils & hydrology, and wildlife management.
Forest Science is published bimonthly in February, April, June, August, October, and December.
2015 Impact Factor: 1.702
Ranking: 16 of 66 in forestry
Average time from submission to first decision: 62.5 days*
June 1, 2016 to Feb. 28, 2017
Also published by SAF:
Journal of Forestry
Other SAF Publications
- Submit a Paper
- Membership Information
- Author Guidelines
- Ingenta Connect is not responsible for the content or availability of external websites