Cargando…

Remote sensing tree classification with a multilayer perceptron

To accelerate scientific progress on remote tree classification—as well as biodiversity and ecology sampling—The National Institute of Science and Technology created a community-based competition where scientists were invited to contribute informatics methods for classifying tree species and genus u...

Descripción completa

Detalles Bibliográficos
Autores principales: Sumsion, G Rex, Bradshaw, Michael S., Hill, Kimball T., Pinto, Lucas D.G., Piccolo, Stephen R.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: PeerJ Inc. 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6397751/
https://www.ncbi.nlm.nih.gov/pubmed/30842894
http://dx.doi.org/10.7717/peerj.6101
_version_ 1783399455592022016
author Sumsion, G Rex
Bradshaw, Michael S.
Hill, Kimball T.
Pinto, Lucas D.G.
Piccolo, Stephen R.
author_facet Sumsion, G Rex
Bradshaw, Michael S.
Hill, Kimball T.
Pinto, Lucas D.G.
Piccolo, Stephen R.
author_sort Sumsion, G Rex
collection PubMed
description To accelerate scientific progress on remote tree classification—as well as biodiversity and ecology sampling—The National Institute of Science and Technology created a community-based competition where scientists were invited to contribute informatics methods for classifying tree species and genus using crown-level images of trees. We classified tree species and genus at the pixel level using hyperspectral and LiDAR observations. We compared three algorithms that have been implemented extensively across a broad range of research applications: support vector machines, random forests, and multilayer perceptron. At the pixel level, the multilayer perceptron algorithm classified species or genus with high accuracy (92.7% and 95.9%, respectively) on the training data and performed better than the other two algorithms (85.8–93.5%). This indicates promise for the use of the multilayer perceptron (MLP) algorithm for tree-species classification based on hyperspectral and LiDAR observations and coincides with a growing body of research in which neural network-based algorithms outperform other types of classification algorithm for machine vision. To aggregate patterns across the images, we used an ensemble approach that averages the pixel-level outputs of the MLP algorithm to classify species at the crown level. The average accuracy of these classifications on the test set was 68.8% for the nine species.
format Online
Article
Text
id pubmed-6397751
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher PeerJ Inc.
record_format MEDLINE/PubMed
spelling pubmed-63977512019-03-06 Remote sensing tree classification with a multilayer perceptron Sumsion, G Rex Bradshaw, Michael S. Hill, Kimball T. Pinto, Lucas D.G. Piccolo, Stephen R. PeerJ Ecology To accelerate scientific progress on remote tree classification—as well as biodiversity and ecology sampling—The National Institute of Science and Technology created a community-based competition where scientists were invited to contribute informatics methods for classifying tree species and genus using crown-level images of trees. We classified tree species and genus at the pixel level using hyperspectral and LiDAR observations. We compared three algorithms that have been implemented extensively across a broad range of research applications: support vector machines, random forests, and multilayer perceptron. At the pixel level, the multilayer perceptron algorithm classified species or genus with high accuracy (92.7% and 95.9%, respectively) on the training data and performed better than the other two algorithms (85.8–93.5%). This indicates promise for the use of the multilayer perceptron (MLP) algorithm for tree-species classification based on hyperspectral and LiDAR observations and coincides with a growing body of research in which neural network-based algorithms outperform other types of classification algorithm for machine vision. To aggregate patterns across the images, we used an ensemble approach that averages the pixel-level outputs of the MLP algorithm to classify species at the crown level. The average accuracy of these classifications on the test set was 68.8% for the nine species. PeerJ Inc. 2019-02-28 /pmc/articles/PMC6397751/ /pubmed/30842894 http://dx.doi.org/10.7717/peerj.6101 Text en ©2019 Sumsion et al. http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ) and either DOI or URL of the article must be cited.
spellingShingle Ecology
Sumsion, G Rex
Bradshaw, Michael S.
Hill, Kimball T.
Pinto, Lucas D.G.
Piccolo, Stephen R.
Remote sensing tree classification with a multilayer perceptron
title Remote sensing tree classification with a multilayer perceptron
title_full Remote sensing tree classification with a multilayer perceptron
title_fullStr Remote sensing tree classification with a multilayer perceptron
title_full_unstemmed Remote sensing tree classification with a multilayer perceptron
title_short Remote sensing tree classification with a multilayer perceptron
title_sort remote sensing tree classification with a multilayer perceptron
topic Ecology
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6397751/
https://www.ncbi.nlm.nih.gov/pubmed/30842894
http://dx.doi.org/10.7717/peerj.6101
work_keys_str_mv AT sumsiongrex remotesensingtreeclassificationwithamultilayerperceptron
AT bradshawmichaels remotesensingtreeclassificationwithamultilayerperceptron
AT hillkimballt remotesensingtreeclassificationwithamultilayerperceptron
AT pintolucasdg remotesensingtreeclassificationwithamultilayerperceptron
AT piccolostephenr remotesensingtreeclassificationwithamultilayerperceptron