Where is this dang thing pointing?
Wire antennas generally have directionality broadside to the antenna but multi-band antennas have "lobes" of directionality that vary greatly as you go up in frequency from their fundamental frequency. I can generate a KML file of my contacts from the Log4OM logging software, but it is a bit overwhelming and I don't have the ability to break it down by band.
I wondered what Google Gemini AI would determine from evaluating the contacts from my LOTW logs and how that differed from the theoretical directionality of the antenna. I have over 2800 logged QSOs in LOTW that I provided for evaluation.
I have made a lot of contacts when portable but I paper log those and they rarely make it back into my electronic logs, so nearly all of these logs are from my station operation and 95% of those have been on the 80m OCF.
I have made a lot of contacts when portable but I paper log those and they rarely make it back into my electronic logs, so nearly all of these logs are from my station operation and 95% of those have been on the 80m OCF.
Gemini provided me with this evaluation
- 80m: Broad "figure-8" pattern with maximum radiation broadside to the wire at 55° (NE) and 235° (SW).
- 40m: A "four-leaf clover" pattern. Your strongest performance is at 45° and 315°, perfectly hitting Europe and the US Midwest.
- 20m: Four sharp lobes that pull closer to the wire axis. Your log shows high-gain "spikes" at 35° (Europe) and 330° (West Coast).
- 10m: Eight or more very narrow lobes. Your 10m contacts are extremely directional, primarily clustering at 50° and 130°.
I then asked Gemini to evaluate how my log results differ from the theoretical directionality of the antenna. In general the results match the theoretical performance of the antenna. I also asked it to include the results from 30m and 17m in this analysis:
- 80m, Broad Figure-8, Strongly Biased NE/SW: Contacts cluster at 55° and 235°. Coverage is broad but noticeably stronger toward the Northeast US/Canada. High: Matches the broadside radiation of a dipole.
- 40m, 4-Leaf Clover, 4 Strong Peaks: Contacts are highly concentrated at 45°, 135°, 225°, and 315°. You are successfully hitting Europe and the US West Coast via these distinct lobes. Very High: Confirms the 2nd harmonic pattern.
- 30m, Distorted 6-Lobe, NW Dominant: You have a massive cluster toward the Northwest (330°). This band is notoriously asymmetrical on an OCF antenna, and your log shows you've "found" the dominant lobe. Moderate: The theoretical pattern is messy; your data simplifies it.
- 20m, 4 Long, Sharp Lobes, Sharp Spikes: Contacts are extremely localized at 35° (Northern Europe) and 330° (Washington/Oregon). This matches the narrowing of lobes as frequency increases. High: Matches the "tilting" of lobes toward the wire axis.
- 17m, 6 Very Sharp Lobes , Strategic Clusters: Contacts cluster at 13° (New York/New England) and 225° (Mexico). The narrowness of these clusters indicates you are operating within high-gain "fingers" of radiation. High: Confirms the 5th harmonic pattern.
- 10m, 8+ Needle-Thin Lobes, Pinpoint DX: You have specific, isolated successes at 50° and 130°. Many other directions show "nulls" where no contacts were made. Moderate: High-QSB (fading) makes this band less predictable.
Conclusions
Using AI to provide me with analysis of my antenna directionality was certainly faster than manually breaking down all the data and plotting it myself. I can also see how much I'm likely missing on 20m and 10m due to the severe directionality of the few lobes. I would be well served by having separate antennas for those bands, but I am very limited where I can put outdoor antennas given the lack of tall support structures at my house. The OCF works because the tallest thing in my lot is the peak of my roof and I have too short a distance to the tree in front of my house for a fan dipole to work.
I did look at some tools for evaluating directionality based on logs such as https://qsomap.org but the ones I found are visual and require manually evaluating the graphics. There are likely other tools that would do what the AI is doing but I'm not aware of them yet. Please leave a comment if there are log analysis tools that you use for this purpose.
I did look at some tools for evaluating directionality based on logs such as https://qsomap.org but the ones I found are visual and require manually evaluating the graphics. There are likely other tools that would do what the AI is doing but I'm not aware of them yet. Please leave a comment if there are log analysis tools that you use for this purpose.
The analysis of the 30m being severely clumped showed me that I could likely do better using my attic antenna for that band, but I had pretty much given up using the attic antenna years ago due to high receive noise given it's proximity to all the noise in the house. Now that I have a Loop on Ground receive antenna that allows for quiet receive I will begin using the attic antenna for transmitting and try to determine how its directionality differs for the for the WARC bands that the 80m OCF is extremely inefficient on.
That's all for now,
Lower your power and raise your expectations, or let AI tell you what you should expect.
DE AA4OO - Rich
