Complex hybrid models combining deterministic and machine learning components for numerical climate modeling and weather prediction

Neural Networks

Volumn 19, Issue 2, 2006, Pages 122-134

  Krasnopolsky, Vladimir M ^a,b   Fox Rabinovitz, Michael S ^a  

^a UNIVERSITY OF MARYLAND   (United States)

^b CLIMATE PREDICTION CENTER   (United States)

Author keywords

Climate; Hybrid model; Machine learning; Neural networks; Numerical modeling; Weather

Indexed keywords

COMPUTER SIMULATION; LEARNING SYSTEMS; MATHEMATICAL MODELS; WEATHER FORECASTING;

HYBRID GCM (HGCM); HYBRID MODEL; MULTIDIMENSIONAL INTERDISCIPLINARY SYSTEMS; WEATHER;

NEURAL NETWORKS;

ARTICLE; ARTIFICIAL NEURAL NETWORK; CALCULATION; CLIMATE; FORECASTING; HYBRID; LEARNING; MACHINE; MATHEMATICAL COMPUTING; MATHEMATICAL MODEL; PHYSICS; PRIORITY JOURNAL; WEATHER;

ARTIFICIAL INTELLIGENCE; CLIMATE; COMPUTER SIMULATION; HUMANS; MODELS, STATISTICAL; NEURAL NETWORKS (COMPUTER); WEATHER;

EID: 33645994778     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.neunet.2006.01.002     Document Type: Article

References (26)

1. 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
2. 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
3. Chevallier F., Chéruy F., Scott N.A., and Chédin A. A neural network approach for a fast and accurate computation of longwave radiative budget. Journal of Applied Meteorology 37 (1998) 1385-1397
4. 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
5. Chevallier F., Morcrette J.-J., Chéruy F., and Scott N.A. Use of a neural-network-based longwave radiative transfer scheme in the EMCWF atmospheric model. Quarterly Journal of the Royal Meteorological Society 126 (2000) 761-776
6. Chou, M. -D., Suarez, M. J., Liang, X. -Z., & Yan, M. M. -H. (2001). A thermal infrared radiation parameterization for atmospheric studies. In: Max J. Suarez (Ed.), Technical report series on global modeling and data assimilation, NASA/TM-2001-104606 (Vol. 19).
7. Collins W.D. Parameterization of generalized cloud overlap for radiative calculations in general circulation models. Journal of the Atmospheric Sciences 58 (2001) 3224-3242
8. Collins W.D., Hackney J.K., and Edwards D.P. A new parameterization for infrared emission and absorption by water vapor in the National Center for Atmospheric Research Community Atmosphere Model. Journal of Geophysical Research 107 D22 (2002) 1-20
9. Cybenko G. Approximation by superposition of sigmoidal functions. Mathematics of Control Signals and Systems 2 (1989) 303-314
10. Funahashi K. On the approximate realization of continuous mappings by neural networks. Neural Networks 2 (1989) 183-192
11. Hornik K. Approximation capabilities of multilayer feedforward network. Neural Networks 4 (1991) 251-257
12. Journal of Climate, 11(6) (the special issue) (1998).
13. 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) 11,033-11,045
14. Krasnopolsky, V., Breaker, L. C., & Gemmill, W. H. (1997). A neural network forward model for direct assimilation of SSM/I brightness temperatures into atmospheric models. Research activities in atmospheric and oceanic modeling. CAS/JSC working group on numerical experimentation, report no. 25, WMO/TD-No. 792, pp. 1.29-1.30.
15. Krasnopolsky V., Chalikov D.V., and Rao D.B. Application of neural networks for efficient calculation of sea water density or salinity from the UNESCO equation of state. Proceedings of the second conference on artificial intelligence (pp. 27-30) (2000), AMS, Long Beach, CA
16. Krasnopolsky V., Gemmill W.H., and Breaker L.C. A multi-parameter empirical ocean algorithm for SSM/I retrievals. Canadian Journal of Remote Sensing 25 (1999) 486-503
17. 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
18. 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 (2005) 1370-1383
19. Krasnopolsky V.M., Fox-Rabinovitz M.S., and Chou M.-D. Robustness of the NN approach to emulating atmospheric long wave radiation in complex climate models. Proceedings of the international joint conference on neural networks, July 31-August 4, 2005, Montréal, Qué., Canada (2005) (pp. 2661-2665)
20. Krasnopolsky V.M., and Schiller H. Some neural network applications in environmental sciences. Part I: Forward and inverse problems in satellite remote sensing. Neural Networks 16 (2003) 321-334
21. Lee J.W., and Oh J.-H. Hybrid learning of mapping and its Jacobian in multilayer neural networks. Neural Computation 9 (1997) 937-958
22. Nguyen, D., & Widrow, B. (1990). Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights. Proceedings of the international joint conference of neural networks (Vol. 3) (pp. 21-26).
23. Schoendorf J., Rabitz H., and Li G. A fast and accurate operational model of ionospheric electron density. Geophysical Research Letters 30 (2003) 1492-1495
24. Tolman, H. L., & Krasnopolsky, V. M. (2004). Nonlinear interactions in practical wind wave models. Eighth international workshop on wave hindcasting and forecasting, Turtle Bay, Hawaii, CD-ROM, E.1.
25. Tolman H.L., Krasnopolsky V.M., and Chalikov D.V. Neural network approximations for nonlinear interactions in wind wave spectra: Direct mapping for wind seas in deep water. Ocean Modelling 8 (2005) 253-278
26. Wessels L.F.A., and Bernard E. Avoiding false local minima by proper initialization of connections. IEEE Transactions on Neural Networks 3 (1992) 899-905