Mapping plant functional types in Northwest Himalayan foothills of India using random forest algorithm in Google Earth Engine

ABSTRACT Plant functional types (PFTs) have been widely used to represent the vegetation characteristics and their interlinkage with the surrounding environment in various earth system models. The present study aims to generate a PFT map for the Northwest Himalayan (NWH) foothills of India using seasonality parameters, topographic conditions, and climatic information from various satellite data and products using Random Forest (RF) algorithm in Google Earth Engine (GEE) platform. The seasonality information was extracted by carrying out a harmonic analysis of Normalized Difference Vegetation Index (NDVI) time-series (2008 to 2018) from Moderate Resolution Imaging Spectroradiometer (MODIS) Terra surface reflectance 8 day 500 m data (MOD09A1). For topographic information, Shuttle Radar Topography Mission (SRTM) digital elevation model (DEM) derived aspect and Multi-Scale Topographic Position Index (MTPI) were used, whereas, for climatic variables, WorldClim V2 Bioclimatic (Bioclim) variables were used. RF, a machine learning classifier, was used to generate a PFT map using these datasets. The overall accuracy of the resulting PFT map was found to be 83.33% with a Kappa coefficient of 0.71. The present study provides an effective approach for PFT classification using different well-established, freely available satellite data and products in the GEE platform. This approach can also be implemented in different ecological settings by using various meaningful variables at varying resolutions.

[1]  Robert H. Whittaker,et al.  Vegetation of the Great Smoky Mountains , 1956 .

[2]  P. G. Holland,et al.  Vegetational responses to latitudinal variations in slope angle and aspect , 1975 .

[3]  B. Hofmann-Wellenhof,et al.  Introduction to spectral analysis , 1986 .

[4]  Ramakrishna R. Nemani,et al.  A remote sensing based vegetation classification logic for global land cover analysis , 1995 .

[5]  D. Randall,et al.  A Revised Land Surface Parameterization (SiB2) for Atmospheric GCMS. Part I: Model Formulation , 1996 .

[6]  Thomas M. Smith,et al.  Plant functional types : their relevance to ecosystem properties and global change , 1998 .

[7]  E. Maarel,et al.  Plant functional types – a strategic perspective , 2000 .

[8]  J. E. Hunt,et al.  Commentary: Carbon Metabolism of the Terrestrial Biosphere: A Multitechnique Approach for Improved Understanding , 2000, Ecosystems.

[9]  Keith W. Oleson,et al.  Landscapes as patches of plant functional types: An integrating concept for climate and ecosystem models , 2002 .

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

[11]  S. Weiss,et al.  GLM versus CCA spatial modeling of plant species distribution , 1999, Plant Ecology.

[12]  M. Castro,et al.  Sensitivity of the Continental Hydrological Cycle to the Spatial Resolution over the Iberian Peninsula , 2004 .

[13]  Johannes R. Sveinsson,et al.  Random Forests for land cover classification , 2006, Pattern Recognit. Lett..

[14]  C. Nobre,et al.  A new world natural vegetation map for global change studies. , 2008, Anais da Academia Brasileira de Ciencias.

[15]  Shunlin Liang,et al.  Methodologies for Mapping Plant Functional Types , 2008 .

[16]  Hongliang Fang,et al.  Mapping plant functional types from MODIS data using multisource evidential reasoning , 2008 .

[17]  Damien Sulla-Menashe,et al.  MODIS Collection 5 global land cover: Algorithm refinements and characterization of new datasets , 2010 .

[18]  Niklaus E. Zimmermann,et al.  Plant functional type mapping for earth system models , 2011 .

[19]  Mario Chica-Olmo,et al.  An assessment of the effectiveness of a random forest classifier for land-cover classification , 2012 .

[20]  Species diversity and community structure in sal (Shorea robusta) forests of two different rainfall regimes in West Bengal, India , 2012, Biodiversity and Conservation.

[21]  Y. Malhi,et al.  Improving simulated Amazon forest biomass and productivity by including spatial variation in biophysical parameters , 2013 .

[22]  B. Poulter,et al.  Use of various remote sensing land cover products for plant functional type mapping over Siberia , 2013 .

[23]  P. Ciais,et al.  Terrestrial carbon cycle affected by non-uniform climate warming , 2014 .

[24]  Yanning Guan,et al.  Mapping Plant Functional Types over Broad Mountainous Regions: A Hierarchical Soft Time-Space Classification Applied to the Tibetan Plateau , 2014, Remote. Sens..

[25]  Christine M. Albano,et al.  Ecologically-Relevant Maps of Landforms and Physiographic Diversity for Climate Adaptation Planning , 2015, PloS one.

[26]  B. Shrestha,et al.  Facing north or south: Does slope aspect impact forest stand characteristics and soil properties in a semiarid trans-Himalayan valley? , 2015 .

[27]  Stuart R. Phinn,et al.  Mapping woody vegetation clearing in Queensland, Australia from Landsat imagery using the Google Earth Engine , 2015 .

[28]  R. Betts,et al.  Plant functional type classification for earth system models: results from the European Space Agency's Land Cover Climate Change Initiative , 2015 .

[29]  Mariana Belgiu,et al.  Random forest in remote sensing: A review of applications and future directions , 2016 .

[30]  D. Lobell,et al.  Landsat-based classification in the cloud: An opportunity for a paradigm shift in land cover monitoring , 2017 .

[31]  Michael Dixon,et al.  Google Earth Engine: Planetary-scale geospatial analysis for everyone , 2017 .

[32]  Stephen E. Fick,et al.  WorldClim 2: new 1‐km spatial resolution climate surfaces for global land areas , 2017 .

[33]  V. Brovkin,et al.  Harmonizing plant funtional type distributions for evaluating Earth System Models. (In open review for Climate of the Past) , 2018 .

[34]  A. Huete,et al.  A 30-m landsat-derived cropland extent product of Australia and China using random forest machine learning algorithm on Google Earth Engine cloud computing platform , 2018, ISPRS Journal of Photogrammetry and Remote Sensing.

[35]  Lei Shi,et al.  Mapping Vegetation and Land Use Types in Fanjingshan National Nature Reserve Using Google Earth Engine , 2018, Remote. Sens..

[36]  S. Nandy,et al.  Remote Sensing-Based Forest Biomass Assessment in Northwest Himalayan Landscape , 2018, Remote Sensing of Northwest Himalayan Ecosystems.

[37]  Álvaro Moreno-Martínez,et al.  Numerical Terradynamic Simulation Group 7-2018 Global Estimation of Biophysical Variables from Google Earth Engine Platform , 2018 .

[38]  Spatial patterns of plant functional types and environmental proxies of plant richness in alpine region of Western Himalaya, India , 2018, Biodiversity and Conservation.

[39]  S. Nandy,et al.  CO2 Flux Tower and Remote Sensing: Tools for Monitoring Carbon Exchange over Ecosystem Scale in Northwest Himalaya , 2018, Remote Sensing of Northwest Himalayan Ecosystems.

[40]  J. Zscheischler,et al.  Modelling carbon sources and sinks in terrestrial vegetation. , 2018, The New phytologist.

[41]  Remote Sensing of Northwest Himalayan Ecosystems , 2019 .

[42]  Saeid Homayouni,et al.  The First Wetland Inventory Map of Newfoundland at a Spatial Resolution of 10 m Using Sentinel-1 and Sentinel-2 Data on the Google Earth Engine Cloud Computing Platform , 2018, Remote. Sens..

[43]  Ritika Srinet,et al.  Estimating leaf area index and light extinction coefficient using Random Forest regression algorithm in a tropical moist deciduous forest, India , 2019, Ecol. Informatics.

[44]  V. Brovkin,et al.  Harmonising plant functional type distributions for evaluating Earth system models , 2019, Climate of the Past.

[45]  N. R. Patel,et al.  Integration of eddy covariance and process-based model for the intra-annual variability of carbon fluxes in an Indian tropical forest , 2019, Biodiversity and Conservation.

[46]  Ghosh,et al.  Finding a Suitable Niche for Cultivating Cactus Pear (Opuntia ficus-indica) as an Integrated Crop in Resilient Dryland Agroecosystems of India , 2019, Sustainability.