Identification of Ecosystem Functional Types from Coarse Resolution Imagery Using a Self-Organizing Map Approach: A Case Study for Spain

Ecosystem state can be characterized by a set of attributes that are related to the ecosystem functionality, which is a relevant issue in understanding the quality and quantity of ecosystem services and goods, adaptive capacity and resilience to perturbations. This study proposes a major identification of Ecosystem Functional Types (EFTs) in Spain to characterize the patterns of ecosystem functional diversity and status, from several functional attributes as the Normalized Difference Vegetation Index (NDVI), Land Surface Temperature (LST) and Albedo. For this purpose, several metrics, related to the spatial variability in seasonal and annual patterns (e.g., relative range), have been derived from remote sensing time series of 1 km MODIS over the period 2000–2009. Moreover, precipitation maps from data provided by the AEMet (Agencia Estatal de Meteorologia) and the corresponding aridity and humidity indices were also included in the analysis. To create the EFTs, the potential of the joint use of Kohonen’s Self-Organizing Map (SOM) and the k-means clustering algorithm was tested. The EFTs were analyzed using different remote sensing (i.e., Gross Primary Production) and climatic variables. The relationship of the EFTs with existing land cover datasets and climatic data were analyzed through a correspondence analysis (CA). The trained SOM have shown feasible in providing a comprehensive view on the functional attributes patterns and a remarkable potential for the quantification of ecosystem function. The results highlight the potential of this technique to delineate ecosystem functional types as well as to monitor the spatial pattern of the ecosystem status as a reference for changes due to human or climate impacts.

[1]  Mark A. White,et al.  A Quantitative Approach to Developing Regional Ecosystem Classifications , 1996 .

[2]  M. Gilabert,et al.  Vegetation dynamics from NDVI time series analysis using the wavelet transform , 2009 .

[3]  M. Netto,et al.  An unsupervised method of classifying remotely sensed images using Kohonen self‐organizing maps and agglomerative hierarchical clustering methods , 2008 .

[4]  Donald W. Bouldin,et al.  A Cluster Separation Measure , 1979, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Marion Stellmes,et al.  Assessment and monitoring of land condition in the Iberian Peninsula, 1989–2000 , 2010 .

[6]  John R. Jensen,et al.  Fuzzy learning vector quantization for hyperspectral coastal vegetation classification , 2006 .

[7]  Bing Zhang,et al.  Land cover classification of the North China Plain using MODIS_EVI time series , 2008 .

[8]  Qihao Weng,et al.  A survey of image classification methods and techniques for improving classification performance , 2007 .

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

[10]  Jean-Louis Roujean,et al.  ECOCLIMAP-II: An ecosystem classification and land surface parameters database of Western Africa at 1 km resolution for the African Monsoon Multidisciplinary Analysis (AMMA) project , 2010 .

[11]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[12]  L. Firbank,et al.  Identifying and managing the conflicts between agriculture and biodiversity conservation in Europe - a review , 2008 .

[13]  N. Pettorelli,et al.  Tracking the effect of climate change on ecosystem functioning using protected areas: Africa as a case study , 2012 .

[14]  Hossein Tabari,et al.  Moisture index for Iran: Spatial and temporal analyses , 2013 .

[15]  A. Moreno Martínez,et al.  Retrieval and assessment of CO2 uptake by mediterranean ecosystems using remote sensing and meteorological data , 2014 .

[16]  Chad J. Shuey,et al.  Validating MODIS land surface reflectance and albedo products: methods and preliminary results , 2002 .

[17]  M. V. Velzen,et al.  Self-organizing maps , 2007 .

[18]  L. Deguillaume,et al.  Modeling study of strong acids formation and partitioning in a polluted cloud during wintertime , 2003 .

[19]  Darrel L. Williams,et al.  BOREAS in 1997: Experiment overview, scientific results, and future directions , 1997 .

[20]  José M. Paruelo,et al.  Remote sensing of protected areas to derive baseline vegetation functioning characteristics , 2004 .

[21]  S. Liang.  Narrowband to broadband conversions of land surface albedo I Algorithms , 2001 .

[22]  Nuno Carvalhais,et al.  Estimating air surface temperature in Portugal using MODIS LST data , 2012 .

[23]  Ujjwal Maulik,et al.  Performance Evaluation of Some Clustering Algorithms and Validity Indices , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[24]  Hai Ren,et al.  Spatiotemporal dynamics of forest net primary production in China over the past two decades , 2008 .

[25]  C. Woodcock,et al.  Consistency of MODIS surface bidirectional reflectance distribution function and albedo retrievals: 2. Validation , 2003 .

[26]  Ryotaro Kamimura,et al.  Supposed maximum information for comprehensible representations in SOM , 2011, Neurocomputing.

[27]  T. Andrew Black,et al.  Modelling Carbon Dynamics of Boreal Forest Ecosystems Using the Canadian Land Surface Scheme , 2002 .

[28]  José A. Sobrino,et al.  The Yearly Land Cover Dynamics (YLCD) method: An analysis of global vegetation from NDVI and LST parameters , 2009 .

[29]  Stefan Sommer,et al.  Ecosystem functional units characterized by satellite observed phenology and productivity gradients: A case study for Europe , 2013 .

[30]  J. Paruelo,et al.  Biozones: vegetation units defined by functional characters identifiable with the aid of satellite sensor images , 1992 .

[31]  M. Kent,et al.  Plant functional types: an alternative to taxonomic plant community description in biogeography? , 2000 .

[32]  Alan H. Strahler,et al.  Validation of the MODIS bidirectional reflectance distribution function and albedo retrievals using combined observations from the aqua and terra platforms , 2006, IEEE Transactions on Geoscience and Remote Sensing.

[33]  José M. Paruelo,et al.  Identification of current ecosystem functional types in the Iberian Peninsula , 2006 .

[34]  J. Kerr,et al.  From space to species: ecological applications for remote sensing , 2003 .

[35]  Miguel Delibes,et al.  The ecosystem functioning dimension in conservation: insights from remote sensing , 2012, Biodiversity and Conservation.

[36]  Miguel Delibes,et al.  Ecosystem functioning of protected and altered Mediterranean environments: A remote sensing classification in Doñana, Spain , 2010 .

[37]  Antonio Jordán,et al.  Intensity and persistence of water repellency in relation to vegetation types and soil parameters in Mediterranean SW Spain , 2009 .

[38]  J. Townshend,et al.  Assessment of Paraguay's forest cover change using Landsat observations , 2009 .

[39]  Jin Chen,et al.  A simple method for reconstructing a high-quality NDVI time-series data set based on the Savitzky-Golay filter , 2004 .

[40]  Achim Röder,et al.  Mediterranean desertification and land degradation: Mapping related land use change syndromes based on satellite observations , 2008 .

[41]  Tae-Soo Chon,et al.  Self-Organizing Maps applied to ecological sciences , 2011, Ecol. Informatics.

[42]  Douglas A. Wiens,et al.  Tilt recorded by a portable broadband seismograph: The 2003 eruption of Anatahan Volcano, Mariana Islands , 2005 .

[43]  C. W. Thornthwaite.  An approach toward a rational classification of climate. , 1948 .

[44]  María Amparo Gilabert,et al.  A multi-temporal analysis of vegetation dynamics in the Iberian peninsula using MODIS-NDVI data. , 2010 .

[45]  A. Izac,et al.  Biodiversity and ecosystem services in agricultural landscapes: Are we asking the right questions? , 2004 .

[46]  Rui Xu,et al.  Survey of clustering algorithms , 2005, IEEE Transactions on Neural Networks.

[47]  W. Verstraeten,et al.  A comparison of time series similarity measures for classification and change detection of ecosystem dynamics , 2011 .

[48]  S. S. Wilks.  On the Independence of k Sets of Normally Distributed Statistical Variables , 1935 .

[49]  F. Giorgi,et al.  Increased aridity in the Mediterranean region under greenhouse gas forcing estimated from high resolution simulations with a regional climate model , 2008 .

[50]  Huajun Tang,et al.  Regional yield estimation for winter wheat with MODIS-NDVI data in Shandong, China , 2008, Int. J. Appl. Earth Obs. Geoinformation.

[51]  Andres Schmidt,et al.  Classification and assessment of turbulent fluxes above ecosystems in North-America with self-organizing feature map networks , 2011 .

[52]  Francisco Javier García-Haro,et al.  Conventional and fuzzy comparisons of large scale land cover products: Application to CORINE, GLC2000, MODIS and GlobCover in Europe , 2012 .

[53]  G. Matheron.  Principles of geostatistics , 1963 .

[54]  Domingo Alcaraz-Segura,et al.  Environmental and Human Controls of Ecosystem Functional Diversity in Temperate South America , 2013, Remote. Sens..

[55]  Sergio M. Vicente-Serrano,et al.  Aridity influence on vegetation patterns in the middle Ebro Valley (Spain): Evaluation by means of AVHRR images and climate interpolation techniques , 2006 .

[56]  Z. Wan,et al.  Preliminary estimate of calibration of the moderate resolution imaging spectroradiometer thermal infrared data using Lake Titicaca , 2002 .

[57]  J. Cihlar.  Land cover mapping of large areas from satellites: Status and research priorities , 2000 .

[58]  R. Fensholt,et al.  Evaluation of Earth Observation based global long term vegetation trends — Comparing GIMMS and MODIS global NDVI time series , 2012 .

[59]  André Carlos Ponce de Leon Ferreira de Carvalho,et al.  Efficiency issues of evolutionary k-means , 2011, Appl. Soft Comput..

[60]  A. Huete,et al.  A comparison of vegetation indices over a global set of TM images for EOS-MODIS , 1997 .

[61]  Nicholas C. Coops,et al.  MODIS enhanced vegetation index predicts tree species richness across forested ecoregions in the contiguous U.S.A , 2006 .

[62]  Harold A. Mooney,et al.  International Ecosystem Assessment , 1999, Science.

[63]  B. Holben.  Characteristics of maximum-value composite images from temporal AVHRR data , 1986 .

[64]  Jennifer N. Hird,et al.  Noise reduction of NDVI time series: An empirical comparison of selected techniques , 2009 .

[65]  Slobodan Petrovic,et al.  A Comparison Between the Silhouette Index and the Davies-Bouldin Index in Labelling IDS Clusters , 2006 .

[66]  Domingo Alcaraz-Segura,et al.  Baseline characterization of major Iberian vegetation types based on the NDVI dynamics , 2009, Plant Ecology.

[67]  P. Pingali,et al.  Millenium Ecosystem Assessment: Ecosystems and human well-being , 2005 .

[68]  Teuvo Kohonen,et al.  Self-organized formation of topologically correct feature maps , 2004, Biological Cybernetics.

[69]  M. H. Ghaseminezhad,et al.  A novel self-organizing map (SOM) neural network for discrete groups of data clustering , 2011, Appl. Soft Comput..

[70]  Joaquín Meliá,et al.  MONITORING DROUGHT CONDITIONS IN THE IBERIAN PENINSULA USING MODERATE AND COARSE RESOLUTION SATELLITE DATA , .

[71]  R. Dickinson.  Land Surface Processes and Climate—Surface Albedos and Energy Balance , 1983 .

[72]  Teuvo Kohonen,et al.  The self-organizing map , 1990, Neurocomputing.

[73]  K. Davis,et al.  The MODIS (Collection V005) BRDF/albedo product: Assessment of spatial representativeness over forested landscapes , 2009 .

[74]  David M. Lawrence,et al.  An annual cycle of vegetation in a GCM. Part II: global impacts on climate and hydrology , 2004 .

[75]  E. Lambin,et al.  Dynamics of Land-Use and Land-Cover Change in Tropical Regions , 2003 .

[76]  V. Caselles,et al.  Comparison between different sources of atmospheric profiles for land surface temperature retrieval from single channel thermal infrared data , 2012 .

[77]  O. Sala,et al.  Current Distribution of Ecosystem Functional Types in Temperate South America , 2001, Ecosystems.

[78]  Tomoaki Miura,et al.  Phenological Classification of the United States: A Geographic Framework for Extending Multi-Sensor Time-Series Data , 2010, Remote. Sens..

[79]  G. Powell,et al.  Terrestrial Ecoregions of the World: A New Map of Life on Earth , 2001 .

[80]  T. Villmann,et al.  Topology Preservation in Self-Organizing Maps , 1999 .

[81]  A. Savitzky,et al.  Smoothing and Differentiation of Data by Simplified Least Squares Procedures. , 1964 .

[82]  M. Facciotti,et al.  Functional Groups , 2021, A Framework for Community Ecology.

[83]  J. Paruelo,et al.  Long-term Satellite NDVI Data Sets: Evaluating Their Ability to Detect Ecosystem Functional Changes in South America , 2008, Sensors.

[84]  H. Mannstein,et al.  Surface Energy Budget, Surface Temperature and Thermal Inertia , 1987 .

[85]  Massimo Menenti,et al.  Mapping isogrowth zones on continental scale using temporal Fourier analysis of AVHRR-NDVI data , 1999 .

[86]  N. Cressie.  The origins of kriging , 1990 .

[87]  Shunlin Liang,et al.  Validating MODIS land surface temperature products using long-term nighttime ground measurements , 2008 .

[88]  Ramakrishna R. Nemani,et al.  A global framework for monitoring phenological responses to climate change , 2005 .

[89]  Agustín Rubio,et al.  Geostatistical modelling of air temperature in a mountainous region of Northern Spain , 2007 .

[90]  A. Fischlin,et al.  Ecosystems, their properties, goods and services , 2007 .

[91]  Domingo Alcaraz-Segura,et al.  Ecosystem functional changes associated with land clearing in NW Argentina , 2012 .

[92]  A. Huete,et al.  Overview of the radiometric and biophysical performance of the MODIS vegetation indices , 2002 .