Classification and assessment of turbulent fluxes above ecosystems in North-America with self-organizing feature map networks

Abstract We determined key environmental and meteorological drivers that influence the magnitude of the fluxes of carbon dioxide, latent heat, and sensible heat using data from different vegetation types at 56 sites of the AmeriFlux network in combination with a self-organizing feature map neural network. The technique was combined with a subsequent k -means clustering procedure to classify the turbulent fluxes. This method is a direct approach to assess the importance of several environmental parameters for the turbulent exchange rates above vegetated areas, based on eddy covariance measurements. The synthesis of the available dataset was achieved by merging 225 pre-clusters of fluxes that were found by the SOFM into 9 final clusters exhibiting mean CO 2 fluxes from −5.8 μmol m −2  s −1 to 3.8 μmol m −2  s −1 . The spatial and temporal comprehensive dataset covering 305 site years, combined with the independence from mechanistic ecological assumptions of the SOFM network approach provides an opportunity to assess the strength of the influence of various environmental parameters on the turbulent fluxes over vegetated areas. After ranking the environmental and meteorological variables according to their cluster separation strength, the pattern of turbulent fluxes turned out to be three times more sensitive to photosynthetic photon flux density and vegetation type than air temperature. Furthermore, the results indicate a strong influence of the water vapor deficit on the magnitude of the turbulent exchange.

[1]  P. Bolstad,et al.  Annual soil respiration in broadleaf forests of northern Wisconsin: influence of moisture and site biological, chemical, and physical characteristics , 2005 .

[2]  Mohd. Noor Md. Sap,et al.  Rough Kohonen Neural Network for Overlapping Data Detection , 2008 .

[3]  David G. Stork,et al.  Pattern Classification , 1973 .

[4]  H. Fock,et al.  A new approach to measure gross CO2 fluxes in leaves. Gross CO2 assimilation, photorespiration, and mitochondrial respiration in the light in tomato under drought stress. , 2001, Plant physiology.

[5]  Kadim Tasdemir.  Exploring Topology Preservation of SOMs with a Graph Based Visualization , 2008, IDEAL.

[6]  Ü. Rannik,et al.  Respiration as the main determinant of carbon balance in European forests , 2000, Nature.

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

[8]  Markus Peura,et al.  The Self-Organizing Map of Trees , 1998, Neural Processing Letters.

[9]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[10]  Tomoyuki Yambe,et al.  An automatic monitoring system for artificial hearts using a hierarchical self-organizing map , 2006, Journal of Artificial Organs.

[11]  J. Canadell,et al.  Recent patterns and mechanisms of carbon exchange by terrestrial ecosystems , 2001, Nature.

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

[13]  Ke-Lin Du,et al.  Clustering: A neural network approach , 2010, Neural Networks.

[14]  E. Schulze,et al.  The responses of stomata and leaf gas exchange to vapour pressure deficits and soil water content , 1985, Oecologia.

[15]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[16]  William W. Hargrove,et al.  New analysis reveals representativeness of the AmeriFlux network , 2003 .

[17]  E. Arsuaga Uriarte,et al.  Topology Preservation in SOM , 2008 .

[18]  W. Oechel,et al.  Environmental controls over carbon dioxide and water vapor exchange of terrestrial vegetation , 2002 .

[19]  D. Broomhead,et al.  Radial Basis Functions, Multi-Variable Functional Interpolation and Adaptive Networks , 1988 .

[20]  Victor Brovkin,et al.  CLIMBER-2: a climate system model of intermediate complexity. Part I: model description and performance for present climate , 2000 .

[21]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[22]  Jiquan Chen,et al.  Carbon fluxes in a young, naturally regenerating jack pine ecosystem , 2006 .

[23]  A. Risch,et al.  Diurnal and Seasonal Patterns in Ecosystem CO2 Fluxes and Their Controls in a Temperate Grassland , 2010 .

[24]  Raúl Rojas,et al.  Neural Networks - A Systematic Introduction , 1996 .

[25]  Bojan Cukic,et al.  Performance Analysis of Dynamic Cell Structures , 2007, Trends in Neural Computation.

[26]  Andres Schmidt,et al.  Gap Filling and Quality Assessment of CO2 and Water Vapour Fluxes above an Urban Area with Radial Basis Function Neural Networks , 2008 .

[27]  Vladimir Cherkassky,et al.  Learning rate schedules for self-organizing maps , 1994, Proceedings of the 12th IAPR International Conference on Pattern Recognition, Vol. 3 - Conference C: Signal Processing (Cat. No.94CH3440-5).

[28]  Juha Vesanto,et al.  SOM-based data visualization methods , 1999, Intell. Data Anal..

[29]  P. Cox,et al.  How positive is the feedback between climate change and the carbon cycle? , 2003 .

[30]  Nikos A. Vlassis,et al.  The global k-means clustering algorithm , 2003, Pattern Recognit..

[31]  Michael G. Ryan,et al.  Seasonal and annual respiration of a ponderosa pine ecosystem , 1999 .

[32]  Vineet Yadav,et al.  A geostatistical synthesis study of factors affecting gross primary productivity in various ecosystems of North America , 2010 .

[33]  Kevin L. Priddy,et al.  Artificial neural networks - an introduction , 2005, Tutorial text series.

[34]  Peter R. Griffiths,et al.  Classification and recognition of compounds in low-resolution open-path FT-IR spectrometry by Kohonen self-organizing maps , 1998 .

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

[36]  E. Davidson,et al.  Effects of experimental drought on soil respiration and radiocarbon efflux from a temperate forest soil , 2002 .

[37]  B. Yegnanarayana,et al.  Artificial Neural Networks , 2004 .

[38]  Neelima Arora,et al.  Application of Kohonen maps for solving the classification puzzle in AGC kinase protein sequences , 2009, Interdisciplinary Sciences: Computational Life Sciences.

[39]  B. Law,et al.  Contrasting soil respiration in young and old‐growth ponderosa pine forests , 2002 .

[40]  Anil K. Jain,et al.  Algorithms for Clustering Data , 1988 .

[41]  W. Oechel,et al.  FLUXNET: A New Tool to Study the Temporal and Spatial Variability of Ecosystem-Scale Carbon Dioxide, Water Vapor, and Energy Flux Densities , 2001 .

[42]  Ben Bond-Lamberty,et al.  Temperature-associated increases in the global soil respiration record , 2010, Nature.

[43]  A. Clare,et al.  A comparison of unsupervised neural networks and k-means clustering in the analysis of multi-element stream sediment data , 2001, Geochemistry: Exploration, Environment, Analysis.

[44]  Kevin Schaefer,et al.  Global monthly averaged CO2 fluxes recovered using a geostatistical inverse modeling approach: 2. Results including auxiliary environmental data , 2008 .

[45]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[46]  Ke Chen,et al.  Trends in Neural Computation , 2007, Studies in Computational Intelligence.

[47]  D. Baldocchi.  Assessing the eddy covariance technique for evaluating carbon dioxide exchange rates of ecosystems: past, present and future , 2003 .

[48]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[49]  M. Heimann,et al.  Terrestrial ecosystem carbon dynamics and climate feedbacks , 2008, Nature.

[50]  T. Kohonen.  Self-organized formation of topographically correct feature maps , 1982 .

[51]  H. Grubmüller,et al.  Self-organization of associative memory and pattern classification: recurrent signal processing on topological feature maps , 1990, Biological Cybernetics.

[52]  Jonas Ardö,et al.  Patterns and controls of the variability of radiation use efficiency and primary productivity across terrestrial ecosystems , 2010 .

[53]  Christoph Thomas,et al.  Seasonal hydrology explains interannual and seasonal variation in carbon and water exchange in a semiarid mature ponderosa pine forest in central Oregon , 2009 .

[54]  K. Caldeira,et al.  Quantifying the effects of CO2‐fertilized vegetation on future global climate and carbon dynamics , 2004 .

[55]  W. Oechel,et al.  Variability in exchange of CO2 across 12 northern peatland and tundra sites , 2009 .

[56]  Roland Pieruschka,et al.  Control of transpiration by radiation , 2010, Proceedings of the National Academy of Sciences.

[57]  L. Mahrt,et al.  Relationship of Area-Averaged Carbon Dioxide and Water Vapour Fluxes to Atmospheric Variables , 2002 .

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

[59]  Energy and CO2 exchanges of a Mediterranean shrubland ecosystem , 2006 .

[60]  M. Keller,et al.  Carbon in Amazon Forests: Unexpected Seasonal Fluxes and Disturbance-Induced Losses , 2003, Science.

[61]  Corinne Le Quéré,et al.  Climate Change 2013: The Physical Science Basis , 2013 .

[62]  Jahan B. Ghasemi,et al.  A quantitative structure–retention relationship study for prediction of chromatographic relative retention time of chlorinated monoterpenes , 2011 .

[63]  Hans Peter Schmid,et al.  Influence of vegetation and seasonal forcing on carbon dioxide fluxes across the Upper Midwest, USA: Implications for regional scaling , 2008 .

[64]  M. Aubinet,et al.  Determinants of terrestrial ecosystem carbon balance inferred from European eddy covariance flux sites , 2007 .

[65]  Brian D. Ripley,et al.  Pattern Recognition and Neural Networks , 1996 .

[66]  J. Raich,et al.  Vegetation and soil respiration: Correlations and controls , 2000 .

[67]  F. Woodward,et al.  Terrestrial Gross Carbon Dioxide Uptake: Global Distribution and Covariation with Climate , 2010, Science.

[68]  N. Kiang,et al.  How plant functional-type, weather, seasonal drought, and soil physical properties alter water and energy fluxes of an oak-grass savanna and an annual grassland , 2004 .

[69]  H. L. Miller,et al.  Climate Change 2007: The Physical Science Basis , 2007 .

[70]  Jarkko Venna,et al.  Analysis and visualization of gene expression data using Self-Organizing Maps , 2002, Neural Networks.

[71]  Willem Bouten,et al.  Water and carbon fluxes above European coniferous forests modelled with artificial neural networks , 1999 .

[72]  Alberto Muñoz,et al.  Self-organizing maps for outlier detection , 1998, Neurocomputing.

[73]  Boris Gnedenko,et al.  Theory of Probability , 1963 .

[74]  J. Dufresne,et al.  On the magnitude of positive feedback between future climate change and the carbon cycle , 2002 .

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

[76]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[77]  F. Chemat,et al.  Relative characterization of rosemary samples according to their geographical origins using microwave-accelerated distillation, solid-phase microextraction and Kohonen self-organizing maps , 2007, Analytical and bioanalytical chemistry.

[78]  R. Schnur,et al.  Climate-carbon cycle feedback analysis: Results from the C , 2006 .

[79]  T. Ferryman,et al.  Data outlier detection using the Chebyshev theorem , 2005, 2005 IEEE Aerospace Conference.

[80]  Paul D. Gader,et al.  Neural networks with enhanced outlier rejection ability for off-line handwritten word recognition , 2002, Pattern Recognit..

[81]  Esa Alhoniemi,et al.  Clustering of the self-organizing map , 2000, IEEE Trans. Neural Networks Learn. Syst..

[82]  D. Baldocchi,et al.  Biogeosciences Biosphere-atmosphere exchange of CO 2 in relation to climate : a cross-biome analysis across multiple time scales , 2009 .

[83]  J. Hair.  Multivariate data analysis , 1972 .

[84]  R. Valentini,et al.  A new assessment of European forests carbon exchanges by eddy fluxes and artificial neural network spatialization , 2003 .

[85]  R. Betts,et al.  Acceleration of global warming due to carbon-cycle feedbacks in a coupled climate model , 2000, Nature.

[86]  A. Kowalski,et al.  Variations in daytime net carbon and water exchange in a montane shrubland ecosystem in southeast Spain , 2007, Photosynthetica.

[87]  Michael G. Ryan,et al.  Interpreting, measuring, and modeling soil respiration , 2005 .