Remote sensing liana infestation in an aseasonal tropical forest: addressing mismatch in spatial units of analyses
Abstract The ability to accurately assess liana (woody vine) infestation at the landscape level is essential to quantify their impact on carbon dynamics and help inform targeted forest management and conservation action. Remote sensing techniques provide potential solutions for assessing liana infes...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2021-09-01
|
Series: | Remote Sensing in Ecology and Conservation |
Subjects: | |
Online Access: | https://doi.org/10.1002/rse2.197 |
id |
doaj-83875b43278b46d59968f8ac30f34174 |
---|---|
record_format |
Article |
spelling |
doaj-83875b43278b46d59968f8ac30f341742021-09-23T06:41:06ZengWileyRemote Sensing in Ecology and Conservation2056-34852021-09-017339741010.1002/rse2.197Remote sensing liana infestation in an aseasonal tropical forest: addressing mismatch in spatial units of analysesChris J. Chandler0Geertje M. F. van der Heijden1Doreen S. Boyd2Mark E. J. Cutler3Hugo Costa4Reuben Nilus5Giles M. Foody6School of Geography University of Nottingham University Park Nottingham United KingdomSchool of Geography University of Nottingham University Park Nottingham United KingdomSchool of Geography University of Nottingham University Park Nottingham United KingdomSchool of Social Sciences University of Dundee Dundee United KingdomDireção‐Geral do Território Lisbon 1099‐052 PortugalForestry Department Forest Research Center Sandakan MalaysiaSchool of Geography University of Nottingham University Park Nottingham United KingdomAbstract The ability to accurately assess liana (woody vine) infestation at the landscape level is essential to quantify their impact on carbon dynamics and help inform targeted forest management and conservation action. Remote sensing techniques provide potential solutions for assessing liana infestation at broader spatial scales. However, their use so far has been limited to seasonal forests, where there is a high spectral contrast between lianas and trees. Additionally, the ability to align the spatial units of remotely sensed data with canopy observations of liana infestation requires further attention. We combined airborne hyperspectral and LiDAR data with a neural network machine learning classification to assess the distribution of liana infestation at the landscape‐level across an aseasonal primary forest in Sabah, Malaysia. We tested whether an object‐based classification was more effective at predicting liana infestation when compared to a pixel‐based classification. We found a stronger relationship between predicted and observed liana infestation when using a pixel‐based approach (RMSD = 27.0% ± 0.80) in comparison to an object‐based approach (RMSD = 32.6% ± 4.84). However, there was no significant difference in accuracy for object‐ versus pixel‐based classifications when liana infestation was grouped into three classes; Low [0–30%], Medium [31–69%] and High [70–100%] (McNemar’s χ2 = 0.211, P = 0.65). We demonstrate, for the first time, that remote sensing approaches are effective in accurately assessing liana infestation at a landscape scale in an aseasonal tropical forest. Our results indicate potential limitations in object‐based approaches which require refinement in order to accurately segment imagery across contiguous closed‐canopy forests. We conclude that the decision on whether to use a pixel‐ or object‐based approach may depend on the structure of the forest and the ultimate application of the resulting output. Both approaches will provide a valuable tool to inform effective conservation and forest management.https://doi.org/10.1002/rse2.197Hyperspectral imagingliana infestationLiDARneural networkpixel‐based soft classificationsegmentation |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Chris J. Chandler Geertje M. F. van der Heijden Doreen S. Boyd Mark E. J. Cutler Hugo Costa Reuben Nilus Giles M. Foody |
spellingShingle |
Chris J. Chandler Geertje M. F. van der Heijden Doreen S. Boyd Mark E. J. Cutler Hugo Costa Reuben Nilus Giles M. Foody Remote sensing liana infestation in an aseasonal tropical forest: addressing mismatch in spatial units of analyses Remote Sensing in Ecology and Conservation Hyperspectral imaging liana infestation LiDAR neural network pixel‐based soft classification segmentation |
author_facet |
Chris J. Chandler Geertje M. F. van der Heijden Doreen S. Boyd Mark E. J. Cutler Hugo Costa Reuben Nilus Giles M. Foody |
author_sort |
Chris J. Chandler |
title |
Remote sensing liana infestation in an aseasonal tropical forest: addressing mismatch in spatial units of analyses |
title_short |
Remote sensing liana infestation in an aseasonal tropical forest: addressing mismatch in spatial units of analyses |
title_full |
Remote sensing liana infestation in an aseasonal tropical forest: addressing mismatch in spatial units of analyses |
title_fullStr |
Remote sensing liana infestation in an aseasonal tropical forest: addressing mismatch in spatial units of analyses |
title_full_unstemmed |
Remote sensing liana infestation in an aseasonal tropical forest: addressing mismatch in spatial units of analyses |
title_sort |
remote sensing liana infestation in an aseasonal tropical forest: addressing mismatch in spatial units of analyses |
publisher |
Wiley |
series |
Remote Sensing in Ecology and Conservation |
issn |
2056-3485 |
publishDate |
2021-09-01 |
description |
Abstract The ability to accurately assess liana (woody vine) infestation at the landscape level is essential to quantify their impact on carbon dynamics and help inform targeted forest management and conservation action. Remote sensing techniques provide potential solutions for assessing liana infestation at broader spatial scales. However, their use so far has been limited to seasonal forests, where there is a high spectral contrast between lianas and trees. Additionally, the ability to align the spatial units of remotely sensed data with canopy observations of liana infestation requires further attention. We combined airborne hyperspectral and LiDAR data with a neural network machine learning classification to assess the distribution of liana infestation at the landscape‐level across an aseasonal primary forest in Sabah, Malaysia. We tested whether an object‐based classification was more effective at predicting liana infestation when compared to a pixel‐based classification. We found a stronger relationship between predicted and observed liana infestation when using a pixel‐based approach (RMSD = 27.0% ± 0.80) in comparison to an object‐based approach (RMSD = 32.6% ± 4.84). However, there was no significant difference in accuracy for object‐ versus pixel‐based classifications when liana infestation was grouped into three classes; Low [0–30%], Medium [31–69%] and High [70–100%] (McNemar’s χ2 = 0.211, P = 0.65). We demonstrate, for the first time, that remote sensing approaches are effective in accurately assessing liana infestation at a landscape scale in an aseasonal tropical forest. Our results indicate potential limitations in object‐based approaches which require refinement in order to accurately segment imagery across contiguous closed‐canopy forests. We conclude that the decision on whether to use a pixel‐ or object‐based approach may depend on the structure of the forest and the ultimate application of the resulting output. Both approaches will provide a valuable tool to inform effective conservation and forest management. |
topic |
Hyperspectral imaging liana infestation LiDAR neural network pixel‐based soft classification segmentation |
url |
https://doi.org/10.1002/rse2.197 |
work_keys_str_mv |
AT chrisjchandler remotesensinglianainfestationinanaseasonaltropicalforestaddressingmismatchinspatialunitsofanalyses AT geertjemfvanderheijden remotesensinglianainfestationinanaseasonaltropicalforestaddressingmismatchinspatialunitsofanalyses AT doreensboyd remotesensinglianainfestationinanaseasonaltropicalforestaddressingmismatchinspatialunitsofanalyses AT markejcutler remotesensinglianainfestationinanaseasonaltropicalforestaddressingmismatchinspatialunitsofanalyses AT hugocosta remotesensinglianainfestationinanaseasonaltropicalforestaddressingmismatchinspatialunitsofanalyses AT reubennilus remotesensinglianainfestationinanaseasonaltropicalforestaddressingmismatchinspatialunitsofanalyses AT gilesmfoody remotesensinglianainfestationinanaseasonaltropicalforestaddressingmismatchinspatialunitsofanalyses |
_version_ |
1717370535328874496 |