Biophysical Parameter Estimation With a Semisupervised Support Vector Machine

被引:42
作者
Camps-Valls, Gustavo [1 ]
Munoz-Mari, Jordi [1 ]
Gomez-Chova, Luis [1 ]
Richter, Katja [2 ]
Calpe-Maravilla, Javier [1 ]
机构
[1] Univ Valencia, Escola Tecn Super Engn, Dept Elect Engn, E-46100 Valencia, Spain
[2] Univ Naples Federico II, Fac Agr, Dipartimento Ingn Agr & Agron Territorio, I-80055 Portici, Na, Italy
关键词
Biophysical parameter; estimation; graph; kernel method; regression; retrieval; semisupervised learning (SSL); support vector machine;
D O I
10.1109/LGRS.2008.2009077
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
This letter presents two kernel-based methods for semisupervised regression. The methods rely on building a graph or hypergraph Laplacian with both the available labeled and unlabeled data, which is further used to deform the training kernel matrix. The deformed kernel is then used for support vector regression (SVR). Given the high computational burden involved, we present two alternative formulations based on the Nystrom method and the incomplete Cholesky factorization to achieve operational processing times. The semisupervised SVR algorithms are successfully tested in multiplatform leaf area index estimation and oceanic chlorophyll concentration prediction. Experiments are carried out with both multispectral and hyperspectral data, demonstrating good generalization capabilities when a low number of labeled samples are available, which is usually the case in biophysical parameter retrieval.
引用
收藏
页码:248 / 252
页数:5
相关论文
共 18 条
[1]  
[Anonymous], 2006, IEEE T NEURAL NETWOR
[2]   Semi-supervised graph-based hyperspectral image classification [J].
Camps-Valls, Gustavo ;
Bandos, Tatyana V. ;
Zhou, Dengyong .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2007, 45 (10) :3044-3054
[3]   Robust support vector regression for biophysical variable estimation from remotely sensed images [J].
Camps-Valls, Gustavo ;
Bruzzone, Lorenzo ;
Rojo-Alvarez, Jose L. ;
Melgani, Farid .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2006, 3 (03) :339-343
[4]  
Chapelle O, 2002, ADV NEUR IN, V14, P609
[5]   Retrieval of sea water optically active parameters from hyperspectral data by means of generalized radial basis function neural networks [J].
Cipollini, P ;
Corsini, G ;
Diani, M ;
Grasso, R .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2001, 39 (07) :1508-1524
[6]  
De Martino M., 2002, Proceedings of the International Workshop on Geo-Spatial Knowledge Processing for Natural Resource Management, P54
[7]   Development and application of a neural network based ocean colour algorithm in coastal waters [J].
Dzwonkowski, B ;
Yan, XH .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 2005, 26 (06) :1175-1200
[8]   Forecasting Vegetation Greenness With Satellite and Climate Data [J].
Ji, Lei ;
Peters, Albert J. .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2004, 1 (01) :3-6
[9]  
Kimes D.S., 2000, Remote Sensing Reviews, V18, P381, DOI DOI 10.1080/02757250009532396
[10]   Deflation techniques for an implicitly restarted Arnoldi iteration [J].
Lehoucq, RB ;
Sorensen, DC .
SIAM JOURNAL ON MATRIX ANALYSIS AND APPLICATIONS, 1996, 17 (04) :789-821