Precipitable Water Vapor Retrieval Using Neural Network from Infrared Hyperspectral Soundings

Abstract:

A neural network (NN) based algorithm for retrieval of precipitable water vapor (PWV) from the Atmospheric Infrared Sounder (AIRS) observations is proposed. An exact radial basis function (RBF) network is selected, in which the at-sensor brightness temperatures are the input variables, and PWV is the output variable. The training data sets for the RBF network are mainly simulated from the fast radiative transfer model (Community Radiative Transfer Model, CRTM) and the latest global assimilation data. The algorithm is validated by retrieving the PWV over west area in China using AIRS data. Compared with the AIRS PWV products, the RMSE of the PWV retrieved by our algorithm is 0.67 g/cm², and a comparison between the retrieved PWV and radiosonde data is carried out. The result suggests that the RBF neural network based algorithm is applicable and feasible in actual conditions. Furthermore, spatial resolution of water vapor derived by RBF neural network is superior as compared to that of AIRS-L 2 standard product. Finally a PCA scheme is used for the preliminary investigation of the compression of AIRS high dimension observations.

• Periodical: Key Engineering Materials (Volume 500)
• Pages: 390-396
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.500.390
• Online since: January 2012
• Authors: Sheng Lan Zhang, Li Sheng Xu, Ji Lie Ding, Hai Lei Liu, Xiao Bo Deng
• Keywords: AIRS, CRTM, Neural Network (NN), Precipitable Water Vapor, Principal Component Analysis (PCA), Retrieval

References

[1] D. Anthony, D. Genio, The dust settles on water vapor feedback, Science, vol. 296, no. 5568, pp.665-666, 26 Apirl (2002).

DOI: 10.1126/science.1071400

[2] A. Raval, V. Ramanathan, Observational determination of the greenhouse effect, Nature, vol. 342, pp.758-761, 14 Dec. (1989).

DOI: 10.1038/342758a0

[3] S. Akatsuka, W. Takeuchi, H. Sawada: Estimation of precipitable water distribution over northeast Asia using NOAA AVHRR. Asia Conference on Remote Sensing 2008, Colombo, Sri Lanka, (2008).

[4] W. Wang, X. Sun, R. Zhang, Z. Li, Z. Zhu, H. Su, Multi-layer perceptron neural network based algorithm for estimating precipitable water vapor from MODIS NIR data, Int. J. Remote Sensing, vol. 27, pp.617-627, (2006).

DOI: 10.1080/01431160500227706

[5] J.A. Sobrino, J. EI Kharraz, Z.L. Li, Surface temperature and water vapor retrieval from AIRS data, Int. J. Remote Sensing, vol. 24, pp.5161-5182, (2003).

DOI: 10.1080/0143116031000102502

[6] N. Chrysoulakis, Y. Kamarianakis, L. Xu, Z. Mitraka, J. Ding, Combined use of AIRS, AVHRR and radiosonde data for the estimation of spatio-temporal distribution of precipitable water, J. Geophys. Res., vol. 113, D05, 101, (2008).

DOI: 10.1029/2007jd009255

[7] M. Chahine, H. Aumann, M. Goldberd, L. McMillin, P. Rosenkranz, D. Staelin, L. Strow, J. Susskind, AIRS Algorithm Theoretical Basis Document, AIRS-Team Retrieval for Core Products and Geophysical Parameters Level 2 (version 2. 2), Availabel from: < http: / eospso. gsfc. nasa. gov/eos_homepage/for_scientists/atbd/docs/AIRS/atbd-airs-L2. pdf>, pp.59-154, (2001).

DOI: 10.1109/tgrs.2002.808356

[8] M.G. Divakarla, C.D. Barnet, M.D. Goldberg, L.M. McMillin, E. Maddy, W. Wolf, L. Zhou, X. Liu., Validation of atmospheric infrared sounder temperature and water vapor retrievals with matched radiosonde measurements and forecasts, J. Geophys. Res., vol. 111, D09S15, (2006).

DOI: 10.1029/2005jd006116

[9] J. Susskinda, R. Atlasa, C. Barnetb, J. Blaisdellc, et al., Current results from AIRS/AMSUA/HSB, Proceedings of Thirteenth International TOVS Study Conference, (2003).

[10] D.C. Tobin, H.E. Revercomb, R.O. Knuteson, B.M. Lesht, et al., Atmospheric radiation measurement site atmospheric state best estimates for atmospheric infrared sounder temperature and water vapor retrieval validation, J. Geophys. Res., vol. 111, D09S14, (2006).

DOI: 10.1029/2005jd006103

[11] C. Otlle, M. Stoll, Effect of atmospheric absorption and surface emissivity on the determination of land temperature from infrared satellite data, Int. J. Remote Sensing, vol. 14, pp.2025-2037, (1993).

DOI: 10.1080/01431169308954018

[12] S. Hsu, T. Masters, M. Olson, M. Tenorio, T. Grogan, Comparavtive analysis of five neural networks models, Remote Sens. Rev., vol. 6, pp.319-329, (1992).

DOI: 10.1080/02757259209532159

[13] K. Hornik, M. Stinchcombe, H. White, Multilayer feedforward networks are universal approximators, Neural Netw., vol. 2, pp.359-366, (1989).

DOI: 10.1016/0893-6080(89)90020-8

[14] J. Park and I. Sandberg, Universal approximation using radial-basis-function networks, Neural Computation, vol. 3, p.246–257, (1991).

DOI: 10.1162/neco.1991.3.2.246

[15] E. E Borbas, S.W. Seemann, University of Wisconsin-Madison, Nov. (2005).

[16] Aires, F., W. B. Rossow, N. A. Scott, and A. Chedin, Remote sensing from the infrared atmospheric sounding interferometer instrument: 1. Compression, denoising, and first-guess retrieval algorithms, J. Geophys. Res., 107(D22), 4619, (2002).

DOI: 10.1029/2001jd000955