Machine learning regression algorithms for biophysical parameter retrieval: Opportunities for Sentinel-2 and -3

被引:427
作者
Verrelst, Jochem [1 ]
Munoz, Jordi [1 ]
Alonso, Luis [1 ]
Delegido, Jesus [1 ]
Pablo Rivera, Juan [1 ]
Camps-Valls, Gustavo [1 ]
Moreno, Jose [1 ]
机构
[1] Univ Valencia, Image Proc Lab IPL, E-46003 Valencia, Spain
关键词
Sentinel-2; Sentinel-3; Machine learning; Regression algorithms; Support vector regression (SVR); Kernel ridge regression (KRR); Gaussian Processes regression (GPR); Biophysical parameter retrieval; LEAF CHLOROPHYLL CONTENT; NEURAL-NETWORK ESTIMATION; RED EDGE POSITION; VEGETATION INDEXES; AREA INDEX; REFLECTANCE MEASUREMENTS; SPECTRAL REFLECTANCE; REMOTE ESTIMATION; MODEL INVERSION; PIGMENT CONTENT;
D O I
10.1016/j.rse.2011.11.002
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
ESA's upcoming satellites Sentinel-2 (S2) and Sentinel-3 (53) aim to ensure continuity for Landsat 5/7, SPOTS, SPOT-Vegetation and Envisat MERIS observations by providing superspectral images of high spatial and temporal resolution. S2 and S3 will deliver near real-time operational products with a high accuracy for land monitoring. This unprecedented data availability leads to an urgent need for developing robust and accurate retrieval methods. Machine learning regression algorithms may be powerful candidates for the estimation of biophysical parameters from satellite reflectance measurements because of their ability to perform adaptive, nonlinear data fitting. By using data from the ESA-led field campaign SPARC (Barrax, Spain) we have compared the utility of four state-of-the-art machine learning regression algorithms and four different S2 and S3 band settings to assess three important biophysical parameters: leaf chlorophyll content (Chl), leaf area index (LAI) and fractional vegetation cover (FVC). The tested Sentinel configurations were: S2-10 m (4 bands), S2-20 m (8 bands), 52-60 m (10 bands) and S3-300 m (19 bands), and the tested methods were: neural networks (NN), support vector regression (SVR), kernel ridge regression (KRR), and Gaussian processes regression (GPR). GPR outperformed the other retrieval methods for the majority of tested configurations and was the only method that reached the 10% precision required by end users in the estimation of Chl. Also, although validated with an RMSE accuracy around 20%, GPR yielded optimal LAI and FVC estimates at highest S2 spatial resolution of 10 m with only four bands. In addition to high accuracy values, GPR also provided confidence intervals of the estimates and insight in relevant bands, which are key advantages over the other methods. Given all this, GPR proved to be a fast and accurate nonlinear retrieval algorithm that can be potentially implemented for operational monitoring applications. (C) 2011 Elsevier Inc. All rights reserved.
引用
收藏
页码:127 / 139
页数:13
相关论文
共 73 条
[1]  
Alonso L., 2005, P 3 CHRIS PROBA WORK
[2]  
[Anonymous], 2009, Kernel methods for remote sensing data analysis
[3]  
[Anonymous], ESA B
[4]   Efficient Kernel Orthonormalized PLS for Remote Sensing Applications [J].
Arenas-Garcia, Jeronimo ;
Camps-Valls, Gustavo .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2008, 46 (10) :2872-2881
[5]   Object-based retrieval of biophysical canopy variables using artificial neural nets and radiative transfer models [J].
Atzberger, C .
REMOTE SENSING OF ENVIRONMENT, 2004, 93 (1-2) :53-67
[6]   Comparative analysis of three chemometric techniques for the spectroradiometric assessment of canopy chlorophyll content in winter wheat [J].
Atzberger, Clement ;
Guerif, Martine ;
Baret, Frederic ;
Werner, Willy .
COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2010, 73 (02) :165-173
[7]   Neural network estimation of LAI, fAPAR, fCover and LAIxCab, from top of canopy MERIS reflectance data:: Principles and validation [J].
Bacour, C. ;
Baret, F. ;
Beal, D. ;
Weiss, M. ;
Pavageau, K. .
REMOTE SENSING OF ENVIRONMENT, 2006, 105 (04) :313-325
[8]   Estimating and mapping crop residues cover on agricultural lands using hyperspectral and IKONOS data [J].
Bannari, A. ;
PacheCo, A. ;
Staenz, K. ;
McNairn, H. ;
Omari, K. .
REMOTE SENSING OF ENVIRONMENT, 2006, 104 (04) :447-459
[9]   POTENTIALS AND LIMITS OF VEGETATION INDEXES FOR LAI AND APAR ASSESSMENT [J].
BARET, F ;
GUYOT, G .
REMOTE SENSING OF ENVIRONMENT, 1991, 35 (2-3) :161-173
[10]   Estimating canopy characteristics from remote sensing observations: Review of methods and associated problems [J].
Baret, Frederic ;
Buis, Samuel .
ADVANCES IN LAND REMOTE SENSING: SYSTEM, MODELING, INVERSION AND APPLICATION, 2008, :173-+