Re: circular domain and color scale for Visad 3D display

Hi Charlie,

> Here the temperature is only discretely sampled across the plate,
> first I use the
> original (x,y, temperature) data to construct a flatfield, then
> construct an Irregular2DSet which covers the whole plate(using polar
> coordinate, so can cover the whole plate), then the flatfield
> resamples the Irregular2DSet. But the edge looks ugly due to no
> temperature measurements at the edge of the plate, and the edge will
> be exactly circular if I artificially add some temperature
> mensurements at the edge or outside the plate. I guess the reason is
> that NaN values are generated for the the plate's region that is not
> measured.  Is there any way to fix this(artificially adding extra
> sampled points at the edge is not good)?

It sounds like your original temperatures are sampled on
a square grid with NaNs at any grid points outside the
circular plate, and that you then reample to a more
circular Irregular2DSet. If so, then the problem is that
you don't have temperature values at the edge of the plate,
and any procedure for creating them is just guessing. So
the problem is with the original data, and you'll have to
solve it there.

> The 2nd problem: Can we use the SAME color scale for several Visad 3D
> displays? (It seems Visad always uses red for the highest altitude and
> blue for the lowest altitude for the current display, so any display's
> color ranges from red to blue.)

Yeah, you can explicitly set the color scale by calling
setRange() on the ScalarMaps to RGB. To make displays
have the same color scale, pass the same range to setRange()
for the ScalarMaps to RGB in each display.

Good luck,
Bill