Fuzzy neural network classification of global land cover from a 1° AVHRR data set

被引:105
作者
Gopal, S [1 ]
Woodcock, CE [1 ]
Strahler, AH [1 ]
机构
[1] Boston Univ, Dept Geog, Ctr Remote Sensing, Boston, MA 02215 USA
基金
美国国家航空航天局; 美国国家科学基金会;
关键词
D O I
10.1016/S0034-4257(98)00088-1
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Phenological differences among broadly defined vegetation types can be a basis for global scale landcover classification ata very coarse spatial scale. Using an annual sequence of composited normalized difference vegetation index (NDVI) values from AVHRR data set composited to 1 degrees DeFries and Townshend (1994) classified eleven global land-cover types with a maximum likelihood classifier. Classification of these same data using a neural network architecture called fuzzy ARTMAP indicate the following: i) When fuzzy ARTMAP is trained using 80% of the data and tested on the remaining (unseen) 20% of the data, classification accuracy is more than 85% compared with 78% using the maximum likelihood classifier; ii) classification accuracies for various splits of training/testing data show that an increase in the size of training data does not result in improved accuracies; iii) classification results vary depending on the use of latitude as an input variable similar to the results of DeFries and Townshed; and iv) fuzzy ARTMAP dynamics including a voting procedure and the numbrer of internal nodes can be used to describe uncertainty in classification. This study shows that artificial neural networks are a viable alternative for global scale landcover classification due to increased accuracy and the ability to provide additional information on uncertainty. (C)Elsevier Science Inc., 1999.
引用
收藏
页码:230 / 243
页数:14
相关论文
共 33 条
  • [1] NEURAL NETWORK APPROACHES VERSUS STATISTICAL-METHODS IN CLASSIFICATION OF MULTISOURCE REMOTE-SENSING DATA
    BENEDIKTSSON, JA
    SWAIN, PH
    ERSOY, OK
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1990, 28 (04): : 540 - 552
  • [2] CONJUGATE-GRADIENT NEURAL NETWORKS IN CLASSIFICATION OF MULTISOURCE AND VERY-HIGH-DIMENSIONAL REMOTE-SENSING DATA
    BENEDIKTSSON, JA
    SWAIN, PH
    ERSOY, OK
    [J]. INTERNATIONAL JOURNAL OF REMOTE SENSING, 1993, 14 (15) : 2883 - 2903
  • [3] MULTISPECTRAL CLASSIFICATION OF LANDSAT-IMAGES USING NEURAL NETWORKS
    BISCHOF, H
    SCHNEIDER, W
    PINZ, AJ
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1992, 30 (03): : 482 - 490
  • [4] Carpenter G., 1991, Pattern recognition by self-organizing neural networks
  • [5] FUZZY ART - FAST STABLE LEARNING AND CATEGORIZATION OF ANALOG PATTERNS BY AN ADAPTIVE RESONANCE SYSTEM
    CARPENTER, GA
    GROSSBERG, S
    ROSEN, DB
    [J]. NEURAL NETWORKS, 1991, 4 (06) : 759 - 771
  • [6] ART neural networks for remote sensing: Vegetation classification from Landsat TM and terrain data
    Carpenter, GA
    Gjaja, MN
    Gopal, S
    Woodcock, CE
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1997, 35 (02): : 308 - 325
  • [7] FUZZY ARTMAP - A NEURAL NETWORK ARCHITECTURE FOR INCREMENTAL SUPERVISED LEARNING OF ANALOG MULTIDIMENSIONAL MAPS
    CARPENTER, GA
    GROSSBERG, S
    MARKUZON, N
    REYNOLDS, JH
    ROSEN, DB
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1992, 3 (05): : 698 - 713
  • [8] ARTMAP - SUPERVISED REAL-TIME LEARNING AND CLASSIFICATION OF NONSTATIONARY DATA BY A SELF-ORGANIZING NEURAL NETWORK
    CARPENTER, GA
    GROSSBERG, S
    REYNOLDS, JH
    [J]. NEURAL NETWORKS, 1991, 4 (05) : 565 - 588
  • [9] A MASSIVELY PARALLEL ARCHITECTURE FOR A SELF-ORGANIZING NEURAL PATTERN-RECOGNITION MACHINE
    CARPENTER, GA
    GROSSBERG, S
    [J]. COMPUTER VISION GRAPHICS AND IMAGE PROCESSING, 1987, 37 (01): : 54 - 115
  • [10] ART-2 - SELF-ORGANIZATION OF STABLE CATEGORY RECOGNITION CODES FOR ANALOG INPUT PATTERNS
    CARPENTER, GA
    GROSSBERG, S
    [J]. APPLIED OPTICS, 1987, 26 (23) : 4919 - 4930