Applications of neural network methods to the processing of Earth observation satellite data

被引:28
作者
Loyola, Diego G. R. [1 ]
机构
[1] German Aerosp Ctr, DLR, Remote Sensing Technol Inst, D-82205 Wessling, Germany
关键词
multi-neural networks; Earth observation satellites; forward and inverse modeling; ozone and clouds;
D O I
10.1016/j.neunet.2006.01.010
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The new generation of earth observation satellites carries advanced sensors that will gather very precise data for studying the Earth system and global climate. This paper shows that neural network methods can be Successfully used for solving forward and inverse remote sensing problems, providing both accurate and fast solutions. Two examples of multi-neural network systems for the determination of cloud properties and for the retrieval of total columns of ozone using satellite data are presented. The developed algorithms based on multi-neural network are currently being used for the operational processing of European atmospheric satellite sensors and will play a key role in related satellite missions planed for the near future. (c) 2006 Elsevier Ltd. All rights reserved.
引用
收藏
页码:168 / 177
页数:10
相关论文
共 26 条
[1]  
Ali AH, 2004, J ATMOS OCEAN TECH, V21, P149, DOI 10.1175/1520-0426(2004)021<0149:AONNPC>2.0.CO
[2]  
2
[4]   Bagging predictors [J].
Breiman, L .
MACHINE LEARNING, 1996, 24 (02) :123-140
[5]  
Burrows JP, 1999, J ATMOS SCI, V56, P151, DOI 10.1175/1520-0469(1999)056<0151:TGOMEG>2.0.CO
[6]  
2
[7]   Stability problems with artificial neural networks and the ensemble solution [J].
Cunningham, P ;
Carney, J ;
Jacob, S .
ARTIFICIAL INTELLIGENCE IN MEDICINE, 2000, 20 (03) :217-225
[8]  
Freund Y., 1996, ICML
[9]   Artificial neural networks (the multilayer perceptron) - A review of applications in the atmospheric sciences [J].
Gardner, MW ;
Dorling, SR .
ATMOSPHERIC ENVIRONMENT, 1998, 32 (14-15) :2627-2636
[10]   NEURAL NETWORKS AND THE BIAS VARIANCE DILEMMA [J].
GEMAN, S ;
BIENENSTOCK, E ;
DOURSAT, R .
NEURAL COMPUTATION, 1992, 4 (01) :1-58