In this study a regression algorithm was developed to retrieve the atmospheric parameters form TOVS (TIROS Operational Vertical Sounder) clear-sky radiances. The development of this algorithm requires calculations, at RAOB (RAdiosonde OBservation) sites, of the cross-covariances among fields obtained from rawinsonde observations, satellite radiances, and forecast products. The data were collected in every assimilation cycle for three months from May to August 1997.

The retrievals were verified statistically with the co-located RAOB measurements for two periods of experiments. The results show that the bias is comparable to the first guess. Compared with the forecast, the root mean square errors of the retrievals in the troposphere were better by about 1~1.5 K in temperature and 0.2~0.4 g/Kg in the mixing ratio. The root mean square error of retrievals at surface showed an improvement of 0.5~1 K in temperature and 1.5~2 g/Kg in the mixing ratio. The results during the August period were noticeably better than in the June period. This implies that the retrieved profiles were closer to the RAOB profiles than the 12-hour forecast profiles were.

The contour field of the retrievals showed a slight correction on the first guess field both in temperature and the mixing ratio except in the subtropical area. The results are also encouraging in that the retrievals in this case had a local coherence both in the horizontal and vertical.