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...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2019-02-01
|
| Series: | PeerJ |
| Subjects: | |
| Online Access: | https://peerj.com/articles/6101.pdf |
| _version_ | 1797417689368494080 |
|---|---|
| author | G Rex Sumsion Michael S. Bradshaw Kimball T. Hill Lucas D.G. Pinto Stephen R. Piccolo |
| author_facet | G Rex Sumsion Michael S. Bradshaw Kimball T. Hill Lucas D.G. Pinto Stephen R. Piccolo |
| author_sort | G Rex Sumsion |
| collection | DOAJ |
| 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. |
| first_indexed | 2024-03-09T06:22:15Z |
| format | Article |
| id | doaj.art-dc54f484346e41d6916e3c278da64801 |
| institution | Directory Open Access Journal |
| issn | 2167-8359 |
| language | English |
| last_indexed | 2024-03-09T06:22:15Z |
| publishDate | 2019-02-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ |
| spelling | doaj.art-dc54f484346e41d6916e3c278da648012023-12-03T11:34:37ZengPeerJ Inc.PeerJ2167-83592019-02-017e610110.7717/peerj.6101Remote sensing tree classification with a multilayer perceptronG Rex Sumsion0Michael S. Bradshaw1Kimball T. Hill2Lucas D.G. Pinto3Stephen R. Piccolo4Department of Biology, Brigham Young University, Provo, UT, United States of AmericaDepartment of Biology, Brigham Young University, Provo, UT, United States of AmericaDepartment of Biology, Brigham Young University, Provo, UT, United States of AmericaDepartment of Biology, Brigham Young University, Provo, UT, United States of AmericaDepartment of Biology, Brigham Young University, Provo, UT, United States of AmericaTo 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.https://peerj.com/articles/6101.pdfAirborne remote sensingData alignmentSpecies classificationCrown segmentationNational ecological observatory networkCrown delineation |
| spellingShingle | G Rex Sumsion Michael S. Bradshaw Kimball T. Hill Lucas D.G. Pinto Stephen R. Piccolo Remote sensing tree classification with a multilayer perceptron PeerJ Airborne remote sensing Data alignment Species classification Crown segmentation National ecological observatory network Crown delineation |
| 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 | Airborne remote sensing Data alignment Species classification Crown segmentation National ecological observatory network Crown delineation |
| url | https://peerj.com/articles/6101.pdf |
| work_keys_str_mv | AT grexsumsion remotesensingtreeclassificationwithamultilayerperceptron AT michaelsbradshaw remotesensingtreeclassificationwithamultilayerperceptron AT kimballthill remotesensingtreeclassificationwithamultilayerperceptron AT lucasdgpinto remotesensingtreeclassificationwithamultilayerperceptron AT stephenrpiccolo remotesensingtreeclassificationwithamultilayerperceptron |