Towertalk
[Top] [All Lists]

Re: [TowerTalk] More Interference Pattern

To: towertalk@contesting.com
Subject: Re: [TowerTalk] More Interference Pattern
From: David Gilbert via TowerTalk <towertalk@contesting.com>
Reply-to: David Gilbert <ab7echo@gmail.com>
Date: Thu, 16 Apr 2026 11:06:23 -0700
List-post: <mailto:towertalk@contesting.com>

Exactly so.  That's a great comparison.   That diffuse refractive ionospheric volume is also variable in density and position ... maybe not as extreme as the my local terrain or the big rocks below the surface of my lot, but the analogy holds.

Your comment on polarization brings up an interesting question.  I know that both vertically and horizontally polarized waves end up being elliptical as they get refracted by the ionosphere, but is one or the other treated more efficiently as it passes through?  I asked that question to ChatGPT and got the answer below.  I know nothing about O-mode versus X-mode, so I guess I have some studying to do.

But maybe when we think of using both horizontal and vertical polarization to better receive what really is an elliptical signal, the difference in the path absorption is also having an effect for transmit.  I separately asked ChatGPT what the difference in ionospheric coupling efficiency was IGNORING GROUND LOSSES, and it replied that the difference was typically about 3 dB but could sometimes be a bit more than that.

73,
Dave   AB7E

From ChatGPT:

When an HF wave enters the ionosphere, it doesn’t just gradually become elliptical. It *splits into two characteristic propagation modes*:

 * *Ordinary wave (O-mode)*
 * *Extraordinary wave (X-mode)*

These modes are defined by the plasma + Earth’s magnetic field interaction (Appleton–Hartree physics). Each mode:

 * Has a *different refractive index*
 * Follows a slightly *different path*
 * Experiences *different absorption*

Both modes are generally *elliptically polarized*, regardless of what you launched from the ground.

------------------------------------------------------------------------


   Why launch polarization still matters

Even though everything becomes elliptical up there, your *initial polarization determines how efficiently you excite those two modes*.


     Horizontal polarization (typical dipole)

 * Couples *strongly into both O and X modes*
 * Tends to produce *more balanced mode excitation*
 * Results in *better overall returned power*, especially at mid-latitudes


     Vertical polarization (typical vertical antenna)

 * Often couples *less efficiently into one of the modes*
 * More energy can be lost due to:
     o *D-layer absorption*
     o Ground losses on launch
 * Can result in *lower skywave efficiency*, especially at lower
   takeoff angles over average الأرض

------------------------------------------------------------------------


   The big practical effect: absorption differences

The *D-layer* (especially during daytime) is where much of the loss happens.

 * The *O-mode is usually more strongly absorbed*
 * The *X-mode penetrates better*

If your antenna launches energy in a way that favors the more absorptive mode, you lose signal.

👉 Horizontal antennas tend to distribute energy in a way that:

 * Ensures *some energy survives in the lower-loss X-mode*
 * Reduces total absorption loss




On 4/16/2026 9:08 AM, Jim Lux wrote:
In some sense, it's like modeling ionospheric "reflection" as a single height, when in reality it's a diffuse refractive effect spanning many 10s-100s of km.
That said, I think one can come up with a frequency specific "single useful number" given an 
assumed soil profile.  You'd get an "effective depth" and a rolled up reflection 
coefficient (which would be angle dependent).

I suspect, also, that for H-pol, it's WAY simpler than for V-pol, just because the 
"first surface" is so reflective at low angles.


_______________________________________________



_______________________________________________
TowerTalk mailing list
TowerTalk@contesting.com
http://lists.contesting.com/mailman/listinfo/towertalk
<Prev in Thread] Current Thread [Next in Thread>