Improvement of Spatio-temporal Growth Estimates in Heterogeneous Forests Using Gaussian Bayesian Networks

Canopy leaf area index (LAI) is a quantitative measure of canopy foliar area. LAI values can be derived from Moderate Resolution Imaging Spectroradiometer (MODIS) images. In this paper, MODIS pixels from a heterogeneous forest located in The Netherlands were decomposed using the linear mixture model using class fractions derived from a high-resolution aerial image. Gaussian Bayesian networks (GBNs) were applied to improve the spatio-temporal estimation of LAI by combining the decomposed MODIS images with a spatial version of physiological principles predicting growth (3PG) model output at different moments in time. Results showed that the spatial-temporal output obtained with the GBN was 40% more accurate than the spatial 3PG, with a root-mean-square error below 0.25. We concluded that the GBNs improved the spatial estimation of LAI values of a heterogeneous forest by combining a spatial forest growth model with satellite imagery.

[1]  J. Chen,et al.  Retrieving Leaf Area Index of Boreal Conifer Forests Using Landsat TM Images , 1996 .

[2]  Federico Magnani,et al.  Application of the 3-PGS model to assess carbon accumulation in forest ecosystems at a regional level , 2009 .

[3]  Takashi Hirano,et al.  In situ comparison of four approaches to estimating soil CO2 efflux in a northern larch (Larix kaempferi Sarg.) forest , 2004 .

[4]  S. Running,et al.  Global products of vegetation leaf area and fraction absorbed PAR from year one of MODIS data , 2002 .

[5]  Toshihiko Hara,et al.  Simulating the carbon balance of a temperate larch forest under various meteorological conditions , 2007, Carbon balance and management.

[6]  Alfred Stein,et al.  Bayesian Network Modeling for Improving Forest Growth Estimates , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[7]  David P. Roy,et al.  MODIS land data storage, gridding, and compositing methodology: Level 2 grid , 1998, IEEE Trans. Geosci. Remote. Sens..

[8]  James M. Vose,et al.  Seasonal changes of leaf area index (LAI) in a tropical deciduous forest in west Mexico , 1995 .

[9]  Martin Brown,et al.  Linear spectral mixture models and support vector machines for remote sensing , 2000, IEEE Trans. Geosci. Remote. Sens..

[10]  Yuri Knyazikhin,et al.  Retrieval of canopy biophysical variables from bidirectional reflectance Using prior information to solve the ill-posed inverse problem , 2003 .

[11]  Nicholas C. Coops,et al.  Estimates of New Zealand forest and scrub biomass from the 3-PG model , 2000 .

[12]  Rasmus Fensholt,et al.  MODIS leaf area index products: from validation to algorithm improvement , 2006, IEEE Transactions on Geoscience and Remote Sensing.

[13]  R. Hall,et al.  A comparison of digital and film fisheye photography for analysis of forest canopy structure and gap light transmission , 2001 .

[14]  Ranga B. Myneni,et al.  The impact of gridding artifacts on the local spatial properties of MODIS data : Implications for validation, compositing, and band-to-band registration across resolutions , 2006 .

[15]  A. Gonsamo,et al.  The computation of foliage clumping index using hemispherical photography , 2009 .

[16]  Roger M. McCoy,et al.  Field Methods in Remote Sensing , 2004 .

[17]  Zhe Zhu,et al.  Toward near real-time monitoring of forest disturbance by fusion of MODIS and Landsat data , 2013 .

[18]  Alfred Stein,et al.  IMPROVING FOREST GROWTH ESTIMATES USING A BAYESIAN NETWORK APPROACH , 2012 .

[19]  S. Ahmed,et al.  Bayesian Networks and Decision Graphs (2nd ed.), by F. V. Jenson and T. D. Nielsen , 2008 .

[20]  A. Cracknell.  Review article Synergy in remote sensing-what's in a pixel? , 1998 .

[21]  Peter Sands,et al.  Understanding 3-PG using a sensitivity analysis , 2004 .

[22]  J. P. Hardya,et al.  Solar radiation transmission through conifer canopies , 2004 .

[23]  F. Baret,et al.  Review of methods for in situ leaf area index (LAI) determination: Part II. Estimation of LAI, errors and sampling , 2004 .

[24]  N. McDowell,et al.  Use of a physiological process model with forestry yield tables to set limits on annual carbon balances. , 2002, Tree physiology.

[25]  R. Leuning,et al.  Carbon and water fluxes over a temperate Eucalyptus forest and a tropical wet/dry savanna in Australia: measurements and comparison with MODIS remote sensing estimates , 2005 .

[26]  D. Watson.  Comparative Physiological Studies on the Growth of Field Crops: I. Variation in Net Assimilation Rate and Leaf Area between Species and Varieties, and within and between Years , 1947 .

[27]  Nicholas C. Coops,et al.  Assessing forest productivity at local scales across a native eucalypt forest using a process model, 3PG-SPATIAL , 2001 .

[28]  R. Waring,et al.  A generalised model of forest productivity using simplified concepts of radiation-use efficiency, carbon balance and partitioning , 1997 .

[29]  Nicholas C. Coops,et al.  The use of multiscale remote sensing imagery to derive regional estimates of forest growth capacity using 3-PGS , 2001 .

[30]  K. Eckhardt,et al.  Plant parameter values for models in temperate climates , 2003 .

[31]  Georgios Xenakis,et al.  Sensitivity and uncertainty analysis from a coupled 3-PG and soil organic matter decomposition model , 2008 .