Computational intelligence in earth sciences and environmental applications: Issues and challenges

被引:56
作者
Cherkassky, V. [1 ]
Krasnopolsky, V.
Solomatine, D. P.
Valdes, J.
机构
[1] Univ Minnesota, Dept Elect & Comp Engn, Minneapolis, MN 55455 USA
[2] NOAA, SAIC, EMC, NCEP, Camp Springs, MD USA
[3] Univ Maryland, Earth Syst Sci Interdisciplinary Ctr, College Pk, MD 20742 USA
[4] UNESCO, IHE, Delft, Netherlands
[5] Natl Res Council Canada, Inst Informat Technol, Montreal, PQ, Canada
关键词
neural networks; predictive learning; earth sciences; environment; climate; hydrology;
D O I
10.1016/j.neunet.2006.01.001
中图分类号
TP18 [人工智能理论];
学科分类号
081104 [模式识别与智能系统]; 0812 [计算机科学与技术]; 0835 [软件工程]; 1405 [智能科学与技术];
摘要
This paper introduces a generic theoretical framework for predictive learning, and relates it to data-driven and learning applications in earth and environmental sciences. The issues of data quality. selection of the error function. incorporation of the predictive learning methods into the existing modeling frameworks. expert knowledge model uncertainty. and other application-domain specific problems are discussed. A brief overview of the papers in the Special issue is provided follow by discussion of open issues and directions for future research. (c) 2006 Elsevier Ltd. All rights reserved.
引用
收藏
页码:113 / 121
页数:9
相关论文
共 37 条
[1]
Neural network uncertainty assessment using Bayesian statistics: A remote sensing application [J].
Aires, F ;
Prigent, C ;
Rossow, WB .
NEURAL COMPUTATION, 2004, 16 (11) :2415-2458
[2]
[Anonymous], 1982, ESTIMATION DEPENDENC
[4]
BEALE R., 1990, Neural Computing: An Introduction, DOI DOI 10.1887/0852742622
[5]
Bishop C. M., 1996, Neural networks for pattern recognition
[6]
Multiple model regression estimation [J].
Cherkassky, V ;
Ma, YQ .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2005, 16 (04) :785-798
[7]
CHERKASSKY V, 2001, ICANN 2001
[8]
CHERKASSKY V, 2005, NEW FORMULATIONS PRE
[9]
Cherkassky V.S., 1998, LEARNING DATA CONCEP, V1st ed.
[10]
Chevallier F, 1998, J APPL METEOROL, V37, P1385, DOI 10.1175/1520-0450(1998)037<1385:ANNAFA>2.0.CO