Mapping Species Composition of Forests and Tree Plantations in Northeastern Costa Rica with an Integration of Hyperspectral and Multitemporal Landsat Imagery

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)

[1]  M. Cho,et al.  Classification of savanna tree species, in the Greater Kruger National Park region, by integrating hyperspectral and LiDAR data in a Random Forest data mining environment , 2012 .

[2]  H. Nagendra,et al.  Remote sensing for conservation monitoring: Assessing protected areas, habitat extent, habitat condition, species diversity, and threats , 2013 .

[3]  Helmi Zulhaidi Mohd Shafri,et al.  A review on hyperspectral remote sensing for homogeneous and heterogeneous forest biodiversity assessment , 2010 .

[4]  Olivier Chassot,et al.  CONNECTIVITY CONSERVATION OF THE GREAT GREEN MACAW'S LANDSCAPE IN COSTA RICA AND NICARAGUA (1994-2012) , 2012 .

[5]  Roberta E. Martin,et al.  Remote sensing of native and invasive species in Hawaiian forests , 2008 .

[6]  Karin Schwab,et al.  Plantation Forests And Biodiversity Oxymoron Or Opportunity , 2016 .

[7]  Moses Azong Cho,et al.  Mapping tree species composition in South African savannas using an integrated airborne spectral and LiDAR system , 2012 .

[8]  J. C. Price.  How unique are spectral signatures , 1994 .

[9]  G. Sánchez‐Azofeifa,et al.  Monitoring secondary tropical forests using space-borne data: Implications for Central America , 2003 .

[10]  W. Cohen,et al.  North American forest disturbance mapped from a decadal Landsat record , 2008 .

[11]  R. Chazdon.  Beyond Deforestation: Restoring Forests and Ecosystem Services on Degraded Lands , 2008, Science.

[12]  A. Ducharne,et al.  Comprehensive data set of global land cover change for land surface model applications , 2008 .

[13]  Götz Schroth,et al.  Conversion of secondary forest into agroforestry and monoculture plantations in Amazonia: consequences for biomass, litter and soil carbon stocks after 7 years , 2002 .

[14]  Lisa Mandle,et al.  Woody exotic plant invasions and fire: reciprocal impacts and consequences for native ecosystems , 2011, Biological Invasions.

[15]  Sophia Decker,et al.  Design And Analysis Of Ecological Experiments , 2016 .

[16]  Lenore Fahrig,et al.  Research, part of a Special Feature on Effects of Roads and Traffic on Wildlife Populations and Landscape Function Behavioral Responses of Northern Leopard Frogs (Rana pipiens) to Roads and Traffic: Implications for Population Persistence , 2009 .

[17]  Roberta E. Martin,et al.  Substrate age and precipitation effects on Hawaiian forest canopies from spaceborne imaging spectroscopy , 2005 .

[18]  Soo Chin Liew,et al.  Remotely sensed evidence of tropical peatland conversion to oil palm , 2011, Proceedings of the National Academy of Sciences.

[19]  G. Hurtt,et al.  Estimation of tropical forest height and biomass dynamics using lidar remote sensing at La Selva, Costa Rica , 2009 .

[20]  M. Herold,et al.  An assessment of deforestation and forest degradation drivers in developing countries , 2012 .

[21]  J. V. van Aardt,et al.  Spectral–age interactions in managed, even‐aged Eucalyptus plantations: application of discriminant analysis and classification and regression trees approaches to hyperspectral data , 2008 .

[22]  David Lamb,et al.  Planted Forests and Biodiversity , 2006, Journal of Forestry.

[23]  Thomas R. Loveland,et al.  A review of large area monitoring of land cover change using Landsat data , 2012 .

[24]  Dhaval Vyas,et al.  Evaluation of classifiers for processing Hyperion (EO-1) data of tropical vegetation , 2011, Int. J. Appl. Earth Obs. Geoinformation.

[25]  T. Caelli,et al.  Ecological fingerprinting of ecosystem succession: Estimating secondary tropical dry forest structure and diversity using imaging spectroscopy , 2007 .

[26]  Deborah Lawrence,et al.  Committed carbon emissions, deforestation, and community land conversion from oil palm plantation expansion in West Kalimantan, Indonesia , 2012, Proceedings of the National Academy of Sciences.

[27]  Benoit Rivard,et al.  Dynamics in landscape structure and composition for the Chorotega region, Costa Rica from 1960 to 2000 , 2005 .

[28]  P. Gessler,et al.  The multispectral separability of Costa Rican rainforest types with support vector machines and Random Forest decision trees , 2010 .

[29]  D. Roberts,et al.  Hyperspectral discrimination of tropical rain forest tree species at leaf to crown scales , 2005 .

[30]  Soo Chin Liew,et al.  2010 land cover map of insular Southeast Asia in 250-m spatial resolution , 2012 .

[31]  Zhiqiang Yang,et al.  Detecting trends in forest disturbance and recovery using yearly Landsat time series: 1. LandTrendr — Temporal segmentation algorithms , 2010 .

[32]  Jianchu Xu,et al.  Soil Carbon Stocks Decrease following Conversion of Secondary Forests to Rubber (Hevea brasiliensis) Plantations , 2013, PloS one.

[33]  Paul E. Gessler,et al.  Integrating Landsat TM and SRTM-DEM derived variables with decision trees for habitat classification and change detection in complex neotropical environments , 2008 .

[34]  Margaret Kalacska,et al.  Assessing Recovery Following Selective Logging of Lowland Tropical Forests Based on Hyperspectral Imagery , 2008 .

[35]  Petr Keil,et al.  Comment on “High-resolution global maps of 21st-century forest cover change” , 2014, Science.

[36]  Frédéric Achard,et al.  Global Forest Monitoring from Earth Observation , 2012 .

[37]  Ruth S. DeFries,et al.  Land cover dynamics following a deforestation ban in northern Costa Rica , 2013 .

[38]  Frédéric Achard,et al.  - Long-Term Monitoring of Australian Land Cover Change Using Landsat Data: Development, Implementation, and Operation , 2016 .

[39]  F. Putz,et al.  The Importance of Defining ‘Forest’: Tropical Forest Degradation, Deforestation, Long‐term Phase Shifts, and Further Transitions , 2010 .

[40]  Selvadurai Dayanandan,et al.  Protected Areas and Conservation of Biodiversity in the Tropics , 1999 .

[41]  C. Justice,et al.  High-Resolution Global Maps of 21st-Century Forest Cover Change , 2013, Science.

[42]  Thomas A. Groen,et al.  Monitoring basin-scale land cover changes in Kagera Basin of Lake Victoria using ancillary data and remote sensing , 2013, Int. J. Appl. Earth Obs. Geoinformation.

[43]  L. P. Koh,et al.  Is oil palm agriculture really destroying tropical biodiversity? , 2008 .

[44]  Joshua B. Fisher,et al.  Evaluating the potential to monitor aboveground biomass in forest and oil palm in Sabah, Malaysia, for 2000–2008 with Landsat ETM+ and ALOS-PALSAR , 2012 .

[45]  Petri Pellikka,et al.  Landscape analysis using multi-scale segmentation and object-oriented classification , 2009 .

[46]  Ramón Díaz-Uriarte,et al.  Gene selection and classification of microarray data using random forest , 2006, BMC Bioinformatics.

[47]  Roberta E. Martin,et al.  Hyperspectral Remote Sensing of Canopy Biodiversity in Hawaiian Lowland Rainforests , 2007, Ecosystems.

[48]  Jonathan Cheung-Wai Chan,et al.  Evaluation of random forest and adaboost tree-based ensemble classification and spectral band selection for ecotope mapping using airborne hyperspectral imagery , 2008 .

[49]  Harini Nagendra,et al.  Satellite imagery as a tool for monitoring species diversity: an assessment , 1999 .

[50]  Mathew R. Schwaller,et al.  On the blending of the Landsat and MODIS surface reflectance: predicting daily Landsat surface reflectance , 2006, IEEE Transactions on Geoscience and Remote Sensing.

[51]  Gregory Asner,et al.  Hyperspectral Time Series Analysis of Native and Invasive Species in Hawaiian Rainforests , 2012, Remote. Sens..

[52]  Neil Sims,et al.  Spectral mixture analysis to monitor defoliation in mixed-aged Eucalyptus globulus Labill plantations in southern Australia using Landsat 5-TM and EO-1 Hyperion data , 2010, Int. J. Appl. Earth Obs. Geoinformation.

[53]  Christopher D. Elvidge,et al.  Comparison of relative radiometric normalization techniques , 1996 .

[54]  Eric P. Crist,et al.  A Physically-Based Transformation of Thematic Mapper Data---The TM Tasseled Cap , 1984, IEEE Transactions on Geoscience and Remote Sensing.

[55]  William F. Laurance,et al.  Cryptic destruction of India's native forests , 2010 .

[56]  Jessica L. Schedlbauer,et al.  Consequences of Environmental Service Payments for Forest Retention and Recruitment in a Costa Rican Biological Corridor , 2009 .

[57]  Gretchen C. Daily,et al.  Integrity and isolation of Costa Rica's national parks and biological reserves: examining the dynamics of land-cover change , 2003 .

[58]  Warren B. Cohen,et al.  Automated designation of tie-points for image-to-image coregistration , 2003 .

[59]  Robert C. Harriss,et al.  Deforestation in Costa Rica: A Quantitative Analysis Using Remote Sensing Imagery1 , 2001 .

[60]  Charles J. Geyer.  5601 Notes: The Subsampling Bootstrap , 2002 .

[61]  Alvaro Redondo-Brenes,et al.  Growth, carbon sequestration, and management of native tree plantations in humid regions of Costa Rica , 2007, New Forests.

[62]  Gregory Asner,et al.  Tree Species Discrimination in Tropical Forests Using Airborne Imaging Spectroscopy , 2013, IEEE Transactions on Geoscience and Remote Sensing.

[63]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[64]  W. Kurz,et al.  Monitoring carbon stocks in the tropics and the remote sensing operational limitations: from local to regional projects. , 2009, Ecological applications : a publication of the Ecological Society of America.

[65]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[66]  Curtis E. Woodcock,et al.  Monitoring large areas for forest change using Landsat: Generalization across space, time and Landsat sensors , 2001 .

[67]  Carlos Torres-Verdín,et al.  Efficient Numerical Simulation of Axisymmetric Electromagnetic Induction Measurements Using a High-Order Generalized Extended Born Approximation , 2006, IEEE Transactions on Geoscience and Remote Sensing.

[68]  John Schelhas,et al.  Post-Frontier Forest Change Adjacent to Braulio Carrillo National Park, Costa Rica , 2006 .

[69]  Gregory Asner,et al.  Mapping Savanna Tree Species at Ecosystem Scales Using Support Vector Machine Classification and BRDF Correction on Airborne Hyperspectral and LiDAR Data , 2012, Remote. Sens..

[70]  G. Sánchez‐Azofeifa,et al.  Costa Rica's Payment for Environmental Services Program: Intention, Implementation, and Impact , 2007, Conservation biology : the journal of the Society for Conservation Biology.

[71]  Adrian C. Newton,et al.  Rapid deforestation and fragmentation of Chilean Temperate Forests , 2006 .

[72]  Roberta E. Martin,et al.  Airborne spectranomics: mapping canopy chemical and taxonomic diversity in tropical forests , 2009 .

[73]  Paul F. Donald,et al.  Changes in bird communities following conversion of lowland forest to oil palm and rubber plantations in southern Thailand , 2006 .

[74]  Christopher B. Field,et al.  Integrating Stand and Soil Properties to Understand Foliar Nutrient Dynamics during Forest Succession Following Slash-and-Burn Agriculture in the Bolivian Amazon , 2014, PloS one.

[75]  J. A. Simonetti,et al.  Enhancing Avifauna in Commercial Plantations , 2010, Conservation biology : the journal of the Society for Conservation Biology.

[76]  R. DeFries,et al.  Annual multi-resolution detection of land cover conversion to oil palm in the Peruvian Amazon , 2013 .

[77]  S. Goward,et al.  An automated approach for reconstructing recent forest disturbance history using dense Landsat time series stacks , 2010 .

[78]  Stephen V. Stehman,et al.  Design and Analysis for Thematic Map Accuracy Assessment: Fundamental Principles , 1998 .

[79]  K. Shadan,et al.  Available online: , 2012 .

[80]  Lorenzo Bruzzone,et al.  On the role of spectral resolution and classifier complexity in the analysis of hyperspectral images of forest areas , 2007, SPIE Remote Sensing.

[81]  Corina da Costa Freitas,et al.  The study of ERS-1 SAR and Landsat TM synergism for land use classification , 2000 .

[82]  D. Roy,et al.  Web-enabled Landsat Data (WELD): Landsat ETM+ composited mosaics of the conterminous United States , 2010 .

[83]  Sandra M. Guzman,et al.  Documenting Land Cover History of a Humid Tropical Environment in Northeastern Costa Rica Using Time-Series Remotely Sensed Data , 2001 .

[84]  K. Moffett,et al.  Remote Sens , 2015 .

[85]  Florencia Montagnini,et al.  The role of native species plantations in recovery of understory woody diversity in degraded pasturelands of Costa Rica. , 2004 .

[86]  Arias,et al.  Costa Rica - Forest strategy and the evolution of land use , 2000 .

[87]  Michael A. Lefsky,et al.  Biomass accumulation rates of Amazonian secondary forest and biomass of old-growth forests from Landsat time series and the Geoscience Laser Altimeter System , 2009 .

[88]  Dengsheng Lu,et al.  Classification of successional forest stages in the Brazilian Amazon basin , 2003 .

[89]  Stephen V. Stehman,et al.  A Critical Evaluation of the Normalized Error Matrix in Map Accuracy Assessment , 2004 .

[90]  D. Roberts,et al.  Estimation of tropical rain forest aboveground biomass with small-footprint lidar and hyperspectral sensors , 2011 .

[91]  Thomas A. Hennig,et al.  The Shuttle Radar Topography Mission , 2001, Digital Earth Moving.

[92]  Onisimo Mutanga,et al.  Commercial tree species discrimination using airborne AISA Eagle hyperspectral imagery and partial least squares discriminant analysis (PLS-DA) in KwaZulu-Natal, South Africa , 2013 .

[93]  S. Ollinger,et al.  DIRECT ESTIMATION OF ABOVEGROUND FOREST PRODUCTIVITY THROUGH HYPERSPECTRAL REMOTE SENSING OF CANOPY NITROGEN , 2002 .

[94]  Benoit Rivard,et al.  Intra- and inter-class spectral variability of tropical tree species at La Selva, Costa Rica: Implications for species identification using HYDICE imagery , 2006 .

[95]  Nicholas C. Coops,et al.  Towards the Operational Use of Satellite Hyperspectral Image Data for Mapping Nutrient Status and Fertilizer Requirements in Australian Plantation Forests , 2013, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[96]  R. Nelson.  Detecting forest canopy change due to insect activity using Landsat MSS , 1983 .

[97]  Alex Mesquita,et al.  Towards an ecologically-sustainable forestry in the Atlantic Forest , 2009 .

[98]  Amy E. Daniels,et al.  Forest Expansion in Northwest Costa Rica: Conjuncture of the Global Market, Land-Use Intensification, and Forest Protection , 2009 .

[99]  Joydeep Ghosh,et al.  Investigation of the random forest framework for classification of hyperspectral data , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[100]  Kamaljit S. Bawa,et al.  La Selva: ecology and natural history of a neotropical rain forest. , 1995 .

[101]  Florencia Montagnini,et al.  Tropical Forest Ecology: The Basis for Conservation and Management , 2005 .

[102]  Eric F. Lambin,et al.  Trade-offs between tree cover, carbon storage and floristic biodiversity in reforesting landscapes , 2012, Landscape Ecology.

[103]  Robert C. Harriss,et al.  Deforestation in Costa Rica: A Quantitative Analysis Using Remote Sensing Imagery 1 , 2001 .

[104]  Luc Lens,et al.  Airborne remote sensing of spatiotemporal change (1955-2004) in indigenous and exotic forest cover in the Taita Hills, Kenya , 2009, Int. J. Appl. Earth Obs. Geoinformation.

[105]  C. Woodcock,et al.  Continuous monitoring of forest disturbance using all available Landsat imagery , 2012 .

[106]  M. Ashton,et al.  Hyperion, IKONOS, ALI, and ETM+ sensors in the study of African rainforests , 2004 .

[107]  Dirk Pflugmacher,et al.  Mapping Rubber Plantations and Natural Forests in Xishuangbanna (Southwest China) Using Multi-Spectral Phenological Metrics from MODIS Time Series , 2013, Remote. Sens..

[108]  L. Muñoz-Villers,et al.  Land use/cover changes using Landsat TM/ETM images in a tropical and biodiverse mountainous area of central‐eastern Mexico , 2008 .

[109]  C. Justice,et al.  Quantifying forest cover loss in Democratic Republic of the Congo, 2000–2010, with Landsat ETM + data , 2012 .

[110]  C. Tucker.  Red and photographic infrared linear combinations for monitoring vegetation , 1979 .

[111]  Serwan M. J. Baban,et al.  Mapping land use/cover distribution on a mountainous tropical island using remote sensing and GIS , 2001 .

[112]  Stephen V. Stehman,et al.  Impact of sample size allocation when using stratified random sampling to estimate accuracy and area of land-cover change , 2012 .

[113]  Gregory P. Asner,et al.  Observing Changing Ecological Diversity in the Anthropocene , 2013 .

[114]  João Roberto dos Santos,et al.  Possibilities of discriminating tropical secondary succession in Amazônia using hyperspectral and multiangular CHRIS/PROBA data , 2009, Int. J. Appl. Earth Obs. Geoinformation.

[115]  Moses Azong Cho,et al.  Evaluating variations of physiology-based hyperspectral features along a soil water gradient in a Eucalyptus grandis plantation , 2010 .

[116]  Andrew Jarvis,et al.  Hole-filled SRTM for the globe Version 4 , 2008 .

[117]  Kevin P. Price,et al.  Mapping coffee plantations with Landsat imagery: an example from El Salvador , 2012 .

[118]  A. Grainger.  Difficulties in tracking the long-term global trend in tropical forest area , 2008, Proceedings of the National Academy of Sciences.

[119]  Martin Herold,et al.  A global land-cover validation data set, II: augmenting a stratified sampling design to estimate accuracy by region and land-cover class , 2012 .

[120]  V. K. Prasad,et al.  Recent Advances in Remote Sensing and Geoinformation Processing for Land Degradation Assessment , 2012 .

[121]  A. Daniels,et al.  Understanding the impacts of Costa Rica's PES: Are we asking the right questions? , 2010 .

[122]  A. Peterson,et al.  Using hyperspectral satellite imagery for regional inventories: a test with tropical emergent trees in the Amazon Basin , 2010 .

[123]  R. N. Jadhav,et al.  Delineation of social forestry plantations under various afforestation programmes using satellite digital data , 1994 .

[124]  J. Barlow,et al.  Quantifying the biodiversity value of tropical primary, secondary, and plantation forests , 2007, Proceedings of the National Academy of Sciences.

[125]  Markku Kanninen,et al.  Performance of forest plantations in small and medium-sized farms in the Atlantic lowlands of Costa Rica , 2003 .

[126]  Yang Dam Eo,et al.  Automatic Pseudo-invariant Feature Extraction for the Relative Radiometric Normalization of Hyperion Hyperspectral Images , 2012 .

[127]  Chaichoke Vaiphasa,et al.  Discrimination of Tropical Mangroves at the Species Level with EO-1 Hyperion Data , 2013, Remote. Sens..

[128]  J. Robalino,et al.  Ecopayments and Deforestation in Costa Rica: A Nationwide Analysis of PSA’s Initial Years , 2013, Land Economics.