Fuzzy classifier of paddy growth stages based on synthetic MODIS data

This paper presents the development of a fuzzy model for classification of paddy growth stages based on synthetic MODIS data. Classification of growth stages is an important process in prediction of crop production using a remote-sensing technology. The proposed approach takes advantages of the nature of a fuzzy system which is able to capture gradual changes/movements by fitting its membership functions. A novel approach to shaping fuzzy input membership functions based on box-plot parameters is also presented. The developed fuzzy model was build and tested on 3935 sets of synthetic MODIS data. The results show that the proposed method was able to classify the growth stages satisfactorily and was robust to handle noises in the data.

[1]  Jingfeng Huang,et al.  Discrimination of rice panicles by hyperspectral reflectance data based on principal component analysis and support vector classification , 2010, Journal of Zhejiang University SCIENCE B.

[2]  Rong-Kuen Chen,et al.  Modeling Rice Growth with Hyperspectral Reflectance Data , 2004 .

[3]  Huang Jingfeng,et al.  Change Law of Hyperspectral Data in Related with Chlorophyll and Carotenoid in Rice at Different Developmental Stages , 2004 .

[4]  Nadirah,et al.  Coupling ground and airborne-based hyperspectral (HyMap) detection over rice canopy to predict leaf area index (LAI) and SPAD value using support vector machine (SVM) technique in irrigated wetland rice, west Java, Indonesia , 2009 .

[5]  Linda Markowsky,et al.  The Octave Fuzzy Logic Toolkit , 2011, 2011 IEEE International Workshop on Open-source Software for Scientific Computation.

[6]  R. Jenssen,et al.  1 THE HYMAP TM AIRBORNE HYPERSPECTRAL SENSOR : THE SYSTEM , CALIBRATION AND PERFORMANCE , 1998 .

[7]  Nadirah,et al.  Quantitative analysis from unifying field and airborne hyperspectral in prediction biophysical parameters by using partial least square ( PLSR ) and Normalized Difference Spectral Index ( NDSI ) , 2009 .

[8]  Sidik Mulyono,et al.  Genetic algorithm based new sequence of principal component regression (GA-NSPCR) for feature selection and yield prediction using hyperspectral remote sensing data , 2012, 2012 IEEE International Geoscience and Remote Sensing Symposium.