Mapping plant functional types from MODIS data using multisource evidential reasoning

Reliable information about the geographic distribution and abundance of major plant functional types (PFTs) around the world is increasingly needed for global change research. Using remote sensing techniques to map PFTs is a relatively recent field of research. This paper presents a method to map PFTs from the Moderate Resolution Imaging Spectroradiometer (MODIS) data using a multisource evidential reasoning (ER) algorithm. The method first utilizes a suite of improved and standard MODIS products to generate evidence measures for each PFT class. The multiple lines of evidence computed from input data are then combined using Dempster's Rule of combination. Finally, a decision rule based on maximum support is used to make classification decisions. The proposed method was tested over the states of Illinois, Indiana, Iowa, and North Dakota, USA where crops dominate. The Cropland Data Layer (CDL) data provided by the United States Department of Agriculture were employed to validate our new PFT maps and the current MODIS PFT product. Our preliminary results suggest that multisource data fusion is a promising approach to improve the mapping of PFTs. For several major PFT classes such as crop, trees, and grass and shrub, the PFT maps generated with the ER method provide greater spatial details compared to the MODIS PFT. The overall accuracies increased for all the four states, with the biggest improvement occurring in Iowa from 51% (MODIS) to 64% (ER). The overall kappa statistic also increased for all the four states, with the biggest improvement occurring in Iowa from 0.03 (MODIS) to 0.38 (ER). The paper concludes with a discussion of several methodological issues pertaining to the further improvement of the ER approach.

[1]  I. C. Prentice,et al.  Evaluation of ecosystem dynamics, plant geography and terrestrial carbon cycling in the LPJ dynamic global vegetation model , 2003 .

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

[3]  John A. Richards,et al.  Knowledge-based techniques for multi-source classification , 1990 .

[4]  Benjamin Smith,et al.  Representation of vegetation dynamics in the modelling of terrestrial ecosystems: comparing two contrasting approaches within European climate space , 2008 .

[5]  Gary Riley,et al.  Expert Systems: Principles and Programming , 2004 .

[6]  Mahta Moghaddam,et al.  Remote sensing in BOREAS: Lessons learned , 2004 .

[7]  W. Moon.  On Mathematical Representation and Integration of Multiple Spatial Geoscience Data Sets , 1993 .

[8]  Glenn Shafer,et al.  A Mathematical Theory of Evidence , 2020, A Mathematical Theory of Evidence.

[9]  A. Strahler.  MODIS Land Cover Product Algorithm Theoretical Basis Document (ATBD) Version 5.0 , 1994 .

[10]  Michael T. Coe,et al.  Testing the performance of a dynamic global ecosystem model: Water balance, carbon balance, and vegetation structure , 2000 .

[11]  Elgene O. Box,et al.  Plant functional types and climate at the global scale , 1996 .

[12]  Derek R. Peddle,et al.  An Empirical Comparison of Evidential Reasoning, Linear Discriminant Analysis, and Maximum Likelihood Algorithms for Alpine Land Cover Classification , 1993 .

[13]  Tong Lee,et al.  Probabilistic and Evidential Approaches for Multisource Data Analysis , 1987, IEEE Transactions on Geoscience and Remote Sensing.

[14]  Steven E. Franklin,et al.  Classification of permafrost active layer depth from remotely sensed and topographic evidence , 1993 .

[15]  Lisa J. Graumlich,et al.  Interactive Canopies for a Climate Model , 1998 .

[16]  E. A. Clark,et al.  Plant Functional Types. Their Relevance to Ecosystem Properties and Global Change , 1998 .

[17]  Leen-Kiat Soh,et al.  ARKTOS: an intelligent system for SAR sea ice image classification , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[18]  I. C. Prentice,et al.  An integrated biosphere model of land surface processes , 1996 .

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

[20]  J. K. Lein.  Applying evidential reasoning methods to agricultural land cover classification , 2003 .

[21]  M. Goldberg,et al.  A hierarchical expert system for updating forestry maps with Landsat data , 1985, Proceedings of the IEEE.

[22]  Shunlin Liang,et al.  A direct algorithm for estimating land surface broadband albedos from MODIS imagery , 2003, IEEE Trans. Geosci. Remote. Sens..

[23]  Keith W. Oleson,et al.  The Effects of Remotely Sensed Plant Functional Type and Leaf Area Index on Simulations of Boreal Forest Surface Fluxes by the NCAR Land Surface Model , 2000 .

[24]  B. Bonan,et al.  A Land Surface Model (LSM Version 1.0) for Ecological, Hydrological, and Atmospheric Studies: Technical Description and User's Guide , 1996 .

[25]  William F. Caselton,et al.  Decision making with imprecise probabilities: Dempster‐Shafer Theory and application , 1992 .

[26]  Wooil M. Moon,et al.  Integration Of Geophysical And Geological Data Using Evidential Belief Function , 1990 .

[27]  J. Townshend,et al.  Spatially and temporally continuous LAI data sets based on an integrated filtering method: Examples from North America , 2008 .

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

[29]  H. Mooney,et al.  Modeling the Exchanges of Energy, Water, and Carbon Between Continents and the Atmosphere , 1997, Science.

[30]  S. Running,et al.  A general model of forest ecosystem processes for regional applications I. Hydrologic balance, canopy gas exchange and primary production processes , 1988 .

[31]  R. Colwell.  Remote sensing of the environment , 1980, Nature.

[32]  A. Scott Denning,et al.  Simulations of terrestrial carbon metabolism and atmospheric CO2 in a general circulation model: Part 1: Surface carbon fluxes , 1996 .

[33]  Arthur P. Dempster,et al.  Upper and Lower Probabilities Induced by a Multivalued Mapping , 1967, Classic Works of the Dempster-Shafer Theory of Belief Functions.

[34]  G. J. Collatz,et al.  Simulations of terrestrial carbon metabolism and atmospheric CO2 in a general circulation model. Part 1: Surface carbon fluxes , 1996 .

[35]  Feng Gao,et al.  Land boundary conditions from MODIS data and consequences for the albedo of a climate model , 2004 .

[36]  D. Peddle.  Knowledge formulation for supervised evidential classification , 1995 .

[37]  Derek R. Peddle,et al.  MERCURY ⊕ : an evidential reasoning image classifier , 1995 .

[38]  Yafit Cohen,et al.  Analysis of convergent evidence in an evidential reasoning knowledge-based classification , 2005 .

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

[40]  Catherine Ottlé,et al.  Multi-scale data fusion using Dempster-Shafer evidence theory , 2003 .

[41]  W. Cramer,et al.  A global biome model based on plant physiology and dominance, soil properties and climate , 1992 .

[42]  Sylvie Le Hégarat-Mascle,et al.  Multi-scale data fusion using Dempster-Shafer evidence theory , 2002, IEEE International Geoscience and Remote Sensing Symposium.

[43]  Alan H. Strahler,et al.  Global land cover mapping from MODIS: algorithms and early results , 2002 .

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