Skip to main content
U.S. flag

An official website of the United States government

Comparative analysis of spectral unmixing and neural networks for estimating small diameter tree above-ground biomass in the State of Mississippi

Formally Refereed

Abstract

The accumulation of small diameter trees (SDTs) is becoming a nationwide concern. Forest management practices such as fire suppression and selective cutting of high grade timber have contributed to an overabundance of SDTs in many areas. Alternative value-added utilization of SDTs (for composite wood products and biofuels) has prompted the need to estimate their spatial availability. Spectral unmixing, a subpixel classification approach, and artificial neural networks (ANN) are being utilized to classify SDT biomass in Mississippi. The Mississippi Institute for Forest Inventory (MIFI) data base biomass (volume per acre) estimates will be used to check the accuracy and compare the two classification procedures. A suitable and accurate classification approach will be vital to understanding the spatial distribution as well as availability of SDTs and would benefit both forest industries and forest managers in proper utilization and forest health restoration.

Keywords

Minimum noise fraction, supervised classification, spectral angle mapping.

Citation

Tiruveedhula, Moham P.; Fan, Joseph; Sadasivuni, Ravi R.; Durbha, Surya S.; Evans, David L. 2010. Comparative analysis of spectral unmixing and neural networks for estimating small diameter tree above-ground biomass in the State of Mississippi. In: Merry, K.; Bettinger, P.; Fan, J.; Kushla, J.; Litts, T.; Siry, J.; Hepinstall-Cymerman, J.; Song, B. eds. Proceedings of the 7th Southern Forestry and Natural Resources GIS Conference, December 7-9, 2009. Warnell School of Forestry and Natural Resources: University of Georgia, Athens, GA. p. 76-85.
https://www.fs.usda.gov/research/treesearch/36498