Mapping species composition of forests and tree plantations in northeastern Costa Rica with an integration of hyperspectral and multitemporal landsat imagery

M E Fagan; R S DeFries; S E Sesnie; J P Arroyo-Mora; C Soto; A Singh; P A Townsend; Robin L Chazdon

doi:10.3390/rs70505660

Back

Mapping species composition of forests and tree plantations in northeastern Costa Rica with an integration of hyperspectral and multitemporal landsat imagery

Journal article

Open access

Peer reviewed

Mapping species composition of forests and tree plantations in northeastern Costa Rica with an integration of hyperspectral and multitemporal landsat imagery

M E Fagan, R S DeFries, S E Sesnie, J P Arroyo-Mora, C Soto, A Singh, P A Townsend and Robin L Chazdon

Remote Sensing, Vol.7(5), pp.5660-5696

2015

DOI: https://doi.org/10.3390/rs70505660

Files and links (2)

pdf

PDF - Published Version (Open Access)3.41 MBDownload View

Published Version PDF - Published Version (Open Access) Open Access CC BY V4.0

url

https://doi.org/10.3390/rs70505660View

Published Version

Abstract

hyperspectral fusion

Landsat

Costa Rica

reforestation

secondary forests

payments for environmental services (PES)

tree plantations

remote sensing

An efficient means to map tree plantations is needed to detect tropical land use change and evaluate reforestation projects. To analyze recent tree plantation expansion in northeastern Costa Rica, we examined the potential of combining moderate-resolution hyperspectral imagery (2005 HyMap mosaic) with multitemporal, multispectral data (Landsat) to accurately classify (1) general forest types and (2) tree plantations by species composition. Following a linear discriminant analysis to reduce data dimensionality, we compared four Random Forest classification models: hyperspectral data (HD) alone; HD plus interannual spectral metrics; HD plus a multitemporal forest regrowth classification; and all three models combined. The fourth, combined model achieved overall accuracy of 88.5%. Adding multitemporal data significantly improved classification accuracy (p < 0.0001) of all forest types, although the effect on tree plantation accuracy was modest. The hyperspectral data alone classified six species of tree plantations with 75% to 93% producer's accuracy; adding multitemporal spectral data increased accuracy only for two species with dense canopies. Non-native tree species had higher classification accuracy overall and made up the majority of tree plantations in this landscape. Our results indicate that combining occasionally acquired hyperspectral data with widely available multitemporal satellite imagery enhances mapping and monitoring of reforestation in tropical landscapes. © 2015 by the authors.

Details

Title: Mapping species composition of forests and tree plantations in northeastern Costa Rica with an integration of hyperspectral and multitemporal landsat imagery
Authors: M E Fagan (Author) - Goddard Space Flight Center
R S DeFries (Author) - Columbia University
S E Sesnie (Author) - United States Fish and Wildlife Service
J P Arroyo-Mora (Author) - McGill University
C Soto (Author) - McGill University
A Singh (Author) - University of Wisconsin–Madison
P A Townsend (Author) - University of Wisconsin–Madison
Robin L Chazdon (Author) - University of Connecticut
Publication details: Remote Sensing, Vol.7(5), pp.5660-5696
Publisher: MDPI AG
Date published: 2015
DOI: 10.3390/rs70505660
ISSN: 2072-4292
Copyright note: Copyright © 2015 by the authors; licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution license (http://creativecommons.org/licenses/by/4.0/).
Organisation Unit: Tropical Forests and People Research Centre; University of the Sunshine Coast, Queensland; Forest Research Institute
Language: English
Record Identifier: 99450602302621
Output Type: Journal article

Metrics

13 File views/ downloads

537 Record Views

61 Times Cited - Web of Science

InCites Highlights

These are selected metrics from InCites Benchmarking & Analytics tool, related to this output

Collaboration types: Domestic collaboration; International collaboration
Web Of Science research areas: Environmental Sciences; Geosciences, Multidisciplinary; Imaging Science & Photographic Technology; Remote Sensing

UN Sustainable Development Goals (SDGs)

This output has contributed to the advancement of the following goals:

Source: InCites