Previous
abstract 
Next
abstract
Astrometry from fast wide-field Schmidt telescopes is compounded by complex structures that are not well represented by traditional plate-modeling polynomials. For stars at the average magnitude of the reference catalog, approximately V = 9.5 mag, these may be removed by any one of a number of modern techniques, eg. masks, sub-plates, or filters. The results of these new methods have, for the first time, allowed one to appreciate the true quality of stellar positions obtained from the large, fast Schmidt telescopes; even below the level of the 0."5 position-only dependent biases. A combination of these techniques has been used to construct version 1.2 of the Guide Star Catalog (GSC). Using data from the plate collection of the GSC, re-reduced with such techniques, we show that there exist large amplitude systematic errors which are a function of magnitude and radial distance from the plate-center. (Previous attempts to detect this effect were unsuccessful because they were less well-conceived, particularly with respect to the confusing effects of the plate-based systematics and to the use of leverage provided by the fainter stars.) The newly characterized magnitude effect is small for radii less than 2.5 deg from the plate center, then increases outward. The average offset of the faint stars at V = 15 mag versus the reference stars at V = 10 mag is ~ 0."35, while at the corners the offset reaches 0."6. In the GSC plate material, the effect occurs both on the Palomar and UK Schmidt plates. The size and shape of the magnitude effect differs slightly between them. Thus, the effect, for the GSC plate data, is relatively independent of telescope, emulsion, passband, and to some degree, exposure depth.
