A genetic-programming-based method for hyperspectral data information extraction: Agricultural applications

被引：24

作者：

Chion, Clement ^{[1
]}

Landry, Jacques-Andre ^{[1
]}

Da Costa, Luis ^{[2
]}

机构：

[1] Univ Quebec, Ecole Technol Super, Montreal, PQ H3C 1K3, Canada

[2] TAO Team, INRIA Futurs, F-78153 Paris, France

来源：

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING | 2008年 / 46卷 / 08期

关键词：

Compact Airborne Spectrographic Imager (CASI) sensor; crop nitrogen; feature selection; genetic programming (GP); hyperspectral remote sensing; precision farming; site-specific management; spectral vegetation indices (SVIs);

D O I：

10.1109/TGRS.2008.922061

中图分类号：

P3 [地球物理学]; P59 [地球化学];

学科分类号：

0708 ; 070902 ;

摘要：

A new method, called genetic programming-spectral vegetation index (GP-SVI), for the extraction of information from hyperspectral data is presented. This method is introduced in the context of precision farming. GP-SVI derives a regression model describing a specific crop biophysical variable from hyperspectral images (verified with in situ observations). GP-SVI performed better than other methods [multiple regression, tree-based modeling, and genetic algorithm-partial least squares (GA-PLS)] on the task of correlating canopy nitrogen content in a cornfield with pixel reflectance. It is also shown that the band selection performed by GP-SVI is comparable with the selection performed by GA-PLS, a method that is specifically designed to deal with hyperspectral data.

引用

页码：2446 / 2457

页数：12

共 63 条

[1]

[Anonymous], 1997, Proceedings of the Seventh International Conference on Genetic Algorithms

[2]

[Anonymous], 1992, Proceedings of the 5th Australian Joint Conference on Artificial Intelligence (AI'92), DOI DOI 10.1142/9789814536271

[3] Impact of tissue, canopy, and landscape factors on the hyperspectral reflectance variability of arid ecosystems [J].

Asner, GP ;

Wessman, CA ;

Bateson, CA ;

Privette, JL .

REMOTE SENSING OF ENVIRONMENT, 2000, 74 (01) :69-84

[4]

Bellman R. E., 1961, ADAPTIVE CONTROL PRO, DOI DOI 10.1515/9781400874668

[5]

Bengio Y, 2004, J MACH LEARN RES, V5, P1089

[6] Comparing prediction power and stability of broadband and hyperspectral vegetation indices for estimation of green leaf area index and canopy chlorophyll density [J].

Broge, NH ;

Leblanc, E .

REMOTE SENSING OF ENVIRONMENT, 2001, 76 (02) :156-172

[7] Evaluation of the consistency of long-term NDVI time series derived from AVHRR, SPOT-Vegetation, SeaWiFS, MODIS, and Landsat ETM+ sensors [J].

Brown, Molly E. ;

Pinzon, Jorge E. ;

Didan, Kamel ;

T Morisette, Jeffrey ;

Tucker, Compton J. .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2006, 44 (07) :1787-1793

[8]

Brumby S. P., 2001, INT C IM FUS FUSION

[9]

CLEVERS JGP, 1991, 9039 BCRS

[10] Predicting Sphaeropsis sapinea damage in Pinus radiata canopies using spectral indices and spectral mixture analysis [J].

Coops, NC ;

Goodwin, N ;

Stone, C .

PHOTOGRAMMETRIC ENGINEERING AND REMOTE SENSING, 2006, 72 (04) :405-416

← 1 2 3 4 5 6 7 →