TY - JOUR
T1 - Remote sensing liana infestation in an aseasonal tropical forest
T2 - addressing mismatch in spatial units of analyses
AU - Chandler, Chris J.
AU - van der Heijden, Geertje M. F.
AU - Boyd, Doreen S.
AU - Cutler, Mark E. J.
AU - Costa, Hugo
AU - Nilus, Reuben
AU - Foody, Giles
N1 - The authors thank all the research assistants and staff at Danum Valley as well as supporting agencies Sabah Biodiversity Center, Danum Valley Management Committee, Sabah Forestry Department and the Chief Minister’s Department Office of Internal Affairs & Research for providing logistical support. The authors also thank Sebastian Böck for providing R code used for segmentation accuracy assessment and Liam Clark for the pre-processing of hyperspectral imagery.
The authors also thank the Natural Environment Research Council [NE/P004806/1 to MEJC, DSB, GMF, GMFvdH; NE/I528477/1 (ARSF MA14/11) to MEJC, DSB, GMF and NE/L002604/1 to CJC, GMF, GMFvdH]. The FCT (Fundação para a Ciência e a Tecnologia) under the project UIDB/04152/2020 – Centro de Investigação em Gestão de Informação (MagIC) to HC. The authors also thank the University of Nottingham for an Anne McLaren Research Fellowship to GMFvdH which funded the collection of the ground data.
Publisher Copyright:
© 2021 The Authors. Remote Sensing in Ecology and Conservation published by John Wiley & Sons Ltd on behalf of Zoological Society of London.
PY - 2021/9
Y1 - 2021/9
N2 - 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.
AB - 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.
KW - Hyperspectral imaging
KW - LiDAR
KW - liana infestation
KW - neural network
KW - pixel-based soft classification
KW - segmentation
UR - http://www.scopus.com/inward/record.url?scp=85100837647&partnerID=8YFLogxK
U2 - 10.1002/rse2.197
DO - 10.1002/rse2.197
M3 - Article
SN - 2056-3485
VL - 7
SP - 397
EP - 410
JO - Remote Sensing in Ecology and Conservation
JF - Remote Sensing in Ecology and Conservation
IS - 3
ER -