Reducing uncertainties in neural network Jacobians and improving accuracy of neural network emulations with NN ensemble approaches

Neural Networks

Volumn 20, Issue 4, 2007, Pages 454-461

  Krasnopolsky, Vladimir M ^a,b  

^a SAIC FREDERICK INC   (United States)

^b Bldg 142   (United States)

Author keywords

Climate; Data assimilation; Ensembles; Neural networks; Numerical modeling; Weather

Indexed keywords

CLIMATE CHANGE; DATA ACQUISITION; ERROR ANALYSIS; JACOBIAN MATRICES; NUMERICAL METHODS; UNCERTAINTY ANALYSIS;

DATA ASSIMILATION SYSTEMS; EMULATION JACOBIANS; LINEAR CONSERVATIVE;

NEURAL NETWORKS;

ACCURACY; ARTICLE; ARTIFICIAL NEURAL NETWORK; CLIMATE; DATA ANALYSIS; ENVIRONMENTAL MANAGEMENT; ERROR; INFORMATION PROCESSING; MATHEMATICAL COMPUTING; MATHEMATICAL MODEL; PRIORITY JOURNAL; SIMULATION; STATISTICAL ANALYSIS; TECHNIQUE; WEATHER;

ARTIFICIAL INTELLIGENCE; COMPUTER SIMULATION; NEURAL NETWORKS (COMPUTER); NONLINEAR DYNAMICS; OCEANS AND SEAS; PATTERN RECOGNITION, AUTOMATED; UNCERTAINTY;

EID: 34249865363     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.neunet.2007.04.008     Document Type: Article

References (22)

1. Aires F., Schmitt M., Chedin A., and Scott N. The "weight smoothing" regularization of MLP for Jacobian stabilization. IEEE Transactions on Neural Networks 10 (1999) 1502-1510
2. Aires F., Prigent C., and Rossow W.B. Neural network uncertainty assessment using Bayesian statistics with application to remote sensing: 3. Network Jacobians. Journal of Geophysical Research 109 (2004) D10305
3. Barai S.V., and Reich Y. Ensemble modeling or selecting the best model: Many could be better than one. Artificial Intelligence for Engineering Design, Analysis and Manufacturing 13 (1999) 377-386
4. Bishop C.M. Neural networks for pattern recognition. (482 pp.) (1995), Oxford University Press, Oxford, UK
5. Chevallier F., and Mahfouf J.-F. Evaluation of the Jacobians of infrared radiation models for variational data assimilation. Journal of Applied Meteorology 40 (2001) 1445-1461
6. Funahashi K. On the approximate realization of continuous mappings by neural networks. Neural Networks 2 (1989) 183-192
7. Fox-Rabinovitz M.S., Krasnopolsky V.M., and Belochitski A. Neural network ensemble approach for improving the accuracy of climate simulations that use neural network emulations of model physics. Proceedings of the IJCNN2006 (2006) 9321-9326 CD-ROM
8. Hashem S. Optimal linear combination of neural networks. Neural Networks 10 (1997) 599-614
9. Hornik K., Stinchcombe M., and White H. Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks. Neural Networks 3 (1990) 551-560
10. Hsieh W.W. Nonlinear principal component analysis by neural networks. Tellus 53A (2001) 599-615
11. Krasnopolsky V., Breaker L.C., and Gemmill W.H. A neural network as a nonlinear transfer function model for retrieving surface wind speeds from the special sensor microwave imager. Journal of Geophysical Research 100 (1995) 11033-11045
12. Krasnopolsky, V. (1997). A neural network-based forward model for direct assimilation of SSM/I brightness temperatures. Technical note, OMB contribution No. 140, NCEP/NOAA
13. Krasnopolsky V.M., Gemmill W.H., and Breaker L.C. A multiparameter empirical ocean algorithm for SSM/I retrievals. Canadian Journal of Remote Sensing 25 (1999) 486-503
14. Krasnopolsky V.M., Chalikov D.V., and Tolman H.L. A neural network technique to improve computational efficiency of numerical oceanic models. Ocean Modelling 4 (2002) 363-383
15. Krasnopolsky V.M., Fox-Rabinovitz M.S., and Chalikov D.V. New approach to calculation of atmospheric model physics: Accurate and fast neural network emulation of long wave radiation in a climate model. Monthly Weather Review 133 5 (2005) 1370-1383
16. Krasnopolsky V.M., and Fox-Rabinovitz M.S. Complex hybrid models combining deterministic and machine learning components for numerical climate modeling and weather prediction. Neural Networks 19 (2006) 113-121
17. Krasnopolsky V.M., et al. Using neural network to enhance assimilating sea surface height data into an ocean model. Proceedings of the IJCNN2006 (2006) 8732-8734 CD-ROM
18. Maclin, R., & Shavlik, J. (1995). Combining the predictions of multiple classifiers: Using competitive learning to initialize neural networks. In Proceedings of the eleventh international conference on artificial intelligence (pp. 775-780)
19. Naftaly U., Intrator N., and Horn D. Optimal ensemble averaging of neural networks. Network: Computation in Neural Systems 8 (1997) 283-294
20. Opitz D., and Maclin R. Popular ensemble methods: An empirical study. Journal of Artificial Intelligence Research 11 (1999) 169-198
21. Sharkey A.J.C. On combining artificial neural nets. Connection Science 8 (1996) 299-313
22. Vapnik V.N. The nature of statistical learning theory. (p. 189) (1995), Springer, New York