Can someone point me in the right direction on how to understand forecast AI and get it setup correctly? I tried using it once this past year but it said my fitness would actually go down for my target event. I just tried to set it up again for a race in March I want to target and it’s giving me projected numbers that are little changed from my current fitness and are well below numbers I was putting out in 2024. When I increase the target power numbers even a little it say they are not attainable, even though they are still numbers I can achieve with 100% certainty.
1 Like
Pay attention to the TL and low/high/peak table deltas before running a forecast.
See this post: How Are You Using Xert’s Forecast AI Training Plans? - Training - Xert Community Forum
If you are not seeing what you like try different forecasts using Goal versus Event versus Race (with Readiness option). More than one road can lead to Rome.
You can choose Achievability between “will likely” versus “may not” or “will likely not” and review the forecast results before deciding which plan you prefer.
“will likely” is going to be a conservative prediction. I’ve hit or exceeded predictions prior to target date during my XFAI testing, but I’d rather do that than assume a loftier goal is attainable. YMMV
Tap the keys below the forecast chart to isolate whatever data set you’re interested in.
Here’s an example Goal forecast for an increase in 4 minute power over 9 weeks.
You can also hover over HIT matchsticks to get an idea what you’re in for during the plan.
how useful is the “AI” if I have to keep massaging the thing to get it to give me some sort of useful plan? Should it not be able to at least look at my past 1-2 years of data and see that I’ve easily surpassed the max power numbers It is predicting I can achieve by the target event? My training load is currently 121, I’ve been as high as 140 in the past 2 years. My TP is currently only 88% of what I’ve seen the past 2 years, my max power is down 200 watts due to the off season and my HIE is down 8. Maybe I’ll just stick to the old system until this AI becomes usable in some way.
1 Like
There is something amiss with the setup guide. I believe the issue is related to Readiness and Max Hours versus Acheivability. I will be reporting this issue once I can replicate the steps consistently.
IME Forecast AI works fine – and should accomplish what you want – by following these steps.
- If signature is stale ride one of the fitness tests in Slope mode to confirm your current signature. Even if no BT you’ll know if your sig is in the right ballpark.
- Select Change Program or Modify Plan and choose Goal.
- Enter Target Date and the Focus Type/Specificity from your Event or Race AI entry. For example, 22 March, Mixed Rouleur.
- Start increasing Focus Power watts while watching the TL and Signature tables.
Keep going until you see the TP and TL values you expect based on past performances. - Note the Acheivability text as it changes between green (“will likely”) to yellow (“may not”) to red (“likely not”).
- Slide Max hours/week to what you reasonably expect you can reach by your Target Date.
- Run Forecast regardless whether Acheivability indicates likely or not. Bypass any warning.
- Review the results. If Final Sig, Focus, and TL look good to you Save the forecast.
Using the steps above I can generate successful forecasts that meet or exceed numbers I have reached in the past (at associated TL) as long at Target Date provides a sufficient plan duration.
I can even get a green checkmark when the pre-run warning text is red (“likely not”).
When I inspect details on the forecast chart everything looks good for a plan to follow.
So the Acheivablity text warning can be false and that’s what I’ll be reporting as a bug.
I don’t think XFAI should automatically create a forecast that matches fitness levels in the past, but I understand why you think it should. Others are expecting the same behavior so it’s something Xert needs to address regardless which XFAI setup option you select.
1 Like
Thanks for the response,. I’ve just now had the time to sit down and work on this again. My signiture might be slightly off, TP is probably 10-15 watts higher than what my current signature shows since I haven’t done a real breakthrough effort in a month. I’ll do one on my next high intensity day where I’m fully recovered, as soon as possible.
When I run the forecast the numbers are very off. For example, I’ve had my TP as high as 325 the last 2 years and that was with just doing base training. I’ve had my HIE up to nearly 29 and my PP just under 1300 watts. The forecast says I can only reach 293 TP, HIE of 24.1 and a peak power of 1090. My HIE and PP numbers are just from this past summer, MY TP was in the 320 range at the time. I’m around 165 lbs with race weight being around 145 lbs.
Question for you, I guess it doesn’t really matter what it expects my numbers to be. Since my numbers will adjust as I get fitter and do breakthroughs, All the forecast does is prescribe me enough work in the zones I need to improve. Correct me if I’m wrong.
If I’m correct, then all good and I’ll just move forward with this. I’m not sure how it differs from the old non AI training plan however. I’ll try to spend some time doing reading and getting caught up on the changes.
I want to like Forecast AI, but I can never get it to work. I just asked it to project a training plan over a three-month period to raise my climbing power by 10W, and it required 13h per week to do so. Then I asked it to raise my climbing power by just 1W, and it also required 13h per week. Makes no sense to me.
1 Like
Same here. I’m certainly not going to trust it blindly. The forecast I just ran says that I’ll basically make no improvement over the next 2.5 months yet I’ll be increasing my intensity significantly. I’ll just use it as a basic guide for now and see how it adjusts to my training. XATA is doing the same thing now though, I ran it through both systems and got the same results, no improvement possible yet the numbers given by both systems are significantly below known power levels I can attain.
1 Like
I believe so. In my testing during the beta I hit or surpassed the Focus Power target before I reached the target date.
I have reported the issue but it’s not exactly what I thought.
All three options can be configured to generate a successful plan based on my best fitness levels in the past, but I don’t think it’s intuitive for the average user.
Are you saying when following Step 4 above you can’t get TL to your historical high with an expected power increase and signature to match?
No. I followed the steps exactly and it didn’t change anything. I"d wager if I follow the plan and adjust the numbers myself that my TP will be 40-50, HIE 4-5, and PP 250 watts higher than what the AI predicts I will be at.
Another question, I had to move todays high intensity ride to tomorrow since I still wasn’t recovered from the last one I did Friday + I lifted heavy weights (squats) yesterday. How can I move that prescribed ride or just make a workout myself that matches the numbers so I can use buckets to free ride it? I free ride everything, can’t stand doing structured workouts anymore.
There are many factors involved in generating a successful plan. If you can consider everything that comes into play:
- Your goal increase
- Your goal date
- Your day-to-day availability
- Your recovery demands
- Any preplanned rides you already have in your planner
- Your training responsiveness
- Your maximum weekly training hours
- Your XSSR Preference (Degree of Difficulty)
And there are other things as well such as Polarization Level.
This also presumes you have a correct starting signature if you want to reach a specific goal or race outcome.
So always check your constraints if a goal/event/race can’t be forecasted. Sometimes it’ll say you can achieve it but when you run Forecast AI, it can’t find a plan. Sometimes the opposite. The initial achievability assessment doesn’t take into account everything above since that’s what the Forecast does. It needs to actually create a plan to confirm that one exists and the outcome is achievable.
So always review things closely. It’s probably running into one or more constraints that you have set if it doesn’t find a plan that you think it should find.
I’ve flipped days before by finding a past activity with the breakdown of XSS I want, then schedule and pin it. After it’s scheduled and pinned, I then update the forecast and it will adapt around the changes if possible. After you have the ‘flipped’ activity scheduled, pinned, and the forecast is updated, it will be reflected in your buckets.
how am I suppose to know what the issue is though? Could the issue be that I’m starting the plan after I already did base training and my goal is only 2 months away?
Is there a blog post that explains each one of your points so I can try to make adjustments? I have no limitations on any of those except I don’t know what my recovery demands are and I didn’t adjust XSSR preference as far as I know.
too much work and I’m not going to end up with the exact number anyways so what’s the point? Yesterday I just looked at the High and Peak bucket numbers from the previous workout that I skipped and kept it in my head. I didn’t get to use the visual of the buckets filling but it still tracks the number. Seems like an easy thing to have, let us users put in the bucket numbers we want to target and also let us move the workouts manually by dragging them. Can’t do either.
You can manually adjust the values using the XSS Buckets data field settings in ConnectIQ app to input whatever numbers you want to target.
However, we don’t have a “swap” feature, as that’s not how Forecast AI is designed to work. The AI provides specific XSS targets on each given day based on a variety of factors like availability, periodization & polarization settings, and of course your training status.
For example, Xert might give me a workout today with High/Peak XSS targets that will leave me in a yellow status for ~2.8 days, because it knows that my next High-Intensity day needs to be in 3 days. If I were to “swap” this workout with tomorrow’s, it wouldn’t just be impacting today’s training. It could throw off the rest of my training by pushing my yellow status into my next high-intensity session, disrupting the entire flow of my program. Deviation from a tightly structured program might mean that the desired outcomes can no longer be achieved.
If you need to adjust your training, @Garrick’s suggestion to select a workout for another day, pin it, and then adapt the rest of your plan around that change is the most effective way to go. However, if you prefer to schedule and adjust your workouts manually, XATA may provide the flexibility you’re looking for and may be a better fit for your needs.
Hope that helps!
Thanks Scott. What I want to be able to do is, if necessary, push a high intensity day back a day and either take a day off or do an easy day. What’s interesting is that the AI has me scheduled to do a high intensity day today and I’m in the yellow.
If I can adjust the numbers in the buckets on my own via the app that would work fine, now I have to figure out how to do that. More detailed instructions would be helpful. Do I start my Garmin then adjust from there? This doesn’t appear to be an option. Do I do it via my phone app? I don’t know what you mean by adjusting it through the Garmin IQ. Thanks.
1 Like
Navigate to XSS Buckets on Garmin Connect (on your phone)
With the Garmin Connect IQ app configure your Xert Username and Xert Password under the data field settings so that the data field can log in to www.xertonline.com and obtain your daily training targets.
There are other settings you can adjust:
- Bars : You can pick which horizontal bars to show along the top. Note that content filtering may remove some of these if your field layout is too small.
- XSS Targets : this allows you to override the values that the XERT server sends to your device, in case you plan to perform a different kind of workout and already know the L/H/P XSS targets that you’d like to achieve.
Regarding adjusting the XSS numbers… Garmin has the data field settings buried a bit, but @ridgerider2 has the idea. Use the Garmin ConnectIQ app to access your Edge device > Data Fields > XSS Buckets. You can adjust settings & set XSS targets manually if you want. You can even do this in the middle of a ride if you wanted.
Perhaps an easier way that doesn’t involve digging through the menus on menus of the CIQ app would be to simply select a workout/activity that has the XSS split that you want to achieve on a particular day and the XSS Buckets data field will fetch the XSS split from that workout/activity instead of the XSS targets from the Forecast AI placeholder.
More Details
Note: The completed activity XSS will still be compared to the Forecast Placeholder XSS values in order to assign the Green, Yellow, Red XSS circle.
E.g. XFAI has a high intensity workout scheduled, but I choose an endurance workout instead. When I start the Garmin on that day, XSS Buckets will pull the endurance workout targets to your Garmin. When the ride is uploaded, the XSS circle would be red because I was supposed to do high-intensity training, but I did low intensity training instead.
1 Like
I figured it out, I did change the numbers and saved them however it didn’t update them to my Garmin. I was locked out of the buckets app for a while after doing this, it was only showing the Xert logo and nothing else. Not sure I want to mess with it anymore and cause myself bigger issues.
I figured out how to put the buckets into my Garmin, however, If there is a workout scheduled for that day it over rides those numbers. Is there a way around this without deleting the workout? I’m just having to move my hard workouts back or forward a day depending on my schedule and recovery, I don’t want to lose the prescribed ride by deleting it. Worst case is I just keep the target numbers in my head but it seems silly to have to do that.