Start training smarter with Xert

With new advanced training systems, athletes have greater flexibility in deciding how they wish to train.  Gone are the days of sitting on your trainer during the off-season doing workout after workout.  Athletes are now able to incorporate different types of training – from indoor rides and races to outdoor coffee rides to more sophisticated indoor workouts to using the latest in training tools like Xert Magic Buckets.  All these types of training activities can now be included as part of your day-to-day training.

Xert Breakthrough Training was the first system to allow athletes to train using a variety of methods, quantifying their training strain scores in multiple dimensions giving athletes the confidence to pick and choose how they prefer to train on any given day.

Athletes are often using more than one system, using one system for a while and switching to another for variety or to save costs. From using Zwift, Rouvy and MyWhoosh, to using the Garmin, Hammerhead or Wahoo device, to TrainerRoad, icTrainer, TrainingPeaks Virtual or just watching a movie or race footage as they work out.  They record on all these systems, sometimes recording on multiple devices to take advantage of features available on one system that are not available on another.  Magic Buckets is a great example where athletes may be riding on Rouvy, say, but also using their Garmin with Magic Buckets to guide their training.  Sometimes users record on multiple devices in order to separate their power data from one source vs. another. For example, they may use a trainer power for Zwift but prefer to use their power meter for their training data.

Many systems today also record multiple rides one after the other to ensure race files are not combined with warmups and cooldowns.  For Xert users, this separation of activities can pose issues as fatigue isn’t carried over from one activity to the next.  Single, contiguous activities are better for Xert’s analysis as well as better for long term record keeping purposes. These will be provide a better view of your responsiveness to training and provide greater information on how you fatigue.

Our Solution – Xert’s New Training Manager – The Xert Today Page

Watch 2 minute intro video on YouTube

Xert’s Today page is our response to requests by our users to help them better manage all their training activity using an intuitive and easy-to-understand page with all their essential information and features they need to manage their training.  Our goals in the development of your Today page were:

1. The UI/UX needs to be simple to understand and use.
2. Users can see what their training is for today and decide how they will do their training.
3. Users can easily adjust their daily training to suit their availability, motivation or readiness to train.
4. Users can dual/multi-record their activities and decide which ones to use for their training data and which to just keep for their own records.
5. Users can merge one or more consecutive activities to better track fatigue and overall training strain scores.
6. Users can decide which activities to share on Strava.
7. The page needs to be fully-featured on mobile devices.
8. The page performance has to use the latest website technology to make it reactive and highly-responsive to user actions.

With all these in mind, we developed a new page that sets a new bar for how athletes will manage their day-to-day training in terms of planning and managing their information after recording activities.

A New User Experience

Xert’s new Today page has a number of key elements on the page, all laid out in an easy-to-understand and use format.  At the top is your training for today and if you planned anything specific for today, that will show at the top of the screen.  This is your daily training front and center.

Below this is any activities you have recorded.  These are shown in chronological order with duplicates indicated if you recorded the activity on multiple devices.

If your recordings come in separate, consecutive activity recordings, you can merge them quickly and easily. Note: Activities that came from Strava cannot be merged with other activities at this time.

You can decide to send your activity to Strava manually and take advantage of the new features to decide which activities to send to Strava, which to use for training and which to keep hidden and not counted.  Be sure to disable the Sync New Xert Activities to Strava on the Strava Sync page for greater control and management.

You can see which targets are going to be sent to Magic Buckets when it fetches your current targets.  No more wondering where the XSS values came from when Magic Buckets runs on Xert EBC or your Garmin.

You can decide which system is going to receive a given workout.  Perhaps you prefer to do one workout outdoors but would opt to do another indoors.  You can manage each individually now.

Filtering workouts could not be easier with the sidebar that allows you to filter instantly.

Not behind your desktop or laptop?  No problem, just use your mobile browser and get the same functions and features.

Summary

With Xert’s new Today page functionality, you can consult it before your daily training rides to manage your day’s training, decide on what training you will do and send workouts to platforms you utilize.  In addition, you can review your daily activities, manage them as part of your training,  retain them for future reference and apply them towards your training.

For Xert users, we are now your go-to system for all your training data.

Always remember: If it ain’t on Xert, it doesn’t count.

So many things go into training program and many athletes aren’t sure what questions they should ask when choosing a plan.  Often they just pick something to do, not knowing whether it’ll be good or bad for them.  Maybe the program title sounds like something they want: “FTP Builder” or “Mid-High Volume with a Little Bit of Sweetspot Program”.  But is this the right program for you?

To help you understand what’s important and why, we’re going to highlight the 10 most important questions to get answered when choosing any endurance training program.  We’ll give you an idea of what answers you will get with a typical training plan, what a coach might provide and what Xert does to address them.

This guide will help you better understand the various settings that go into deciding on what fitness will you have on race day (or on the day you’re looking to reach your achievement).  The settings affect how you’ll need to train and what will be needed to achieve the outcome you are looking for.

Main Three Options

 

Target Information Section

This is the main section that determines what fitness you’ll need to reach in order to achieve the outcome of completing the race/ride:

Training Plan Create/Update You can choose whether to update the existing plan you’re on (and associate your historical training) or you can create a new plan and start over again. Date This is the target date for the race or achievement.  The further away the date is, the more likely it will be for you be able to reach the fitness needed. Max Weekly Hours This value will restrict the number of hours will be asked to train over the course of the training plan.  This will be applied when the training plan is generated. Difficulty Score You can aim to limit the amount of Difficulty you will experience in trying to perform this race.  Generally, Difficulty Scores over 150 are rare and will be challenging to complete.  Races that involve and lot of hard, repeated efforts will increase the Difficulty Score.  Increasing this number will require less fitness for you to reach and improve a race’s fitness achievability but be harder to do on race day. Carbs Per Hour You can aim to reduce the estimated carbs per hour you will burn during the race.  This setting is particularly useful for longer events where self pacing to limit the fuelling demands will be needed for success at the race.  Lowering this value, increases the fitness you will need to reach.  Increasing this value, reduces the fitness you will need but will increase the fuelling demands and intensity you’ll need to race at. Event Readiness The default value of 2 is an ideal setting for a general race preparation.  Lower values improve your durability for the race but also will require more training to be prepared.  Higher values reduce the training you’ll need to do leading into the event.  If you are unable to get to achievability for the race, increasing this value will make the fitness more achievable.  However, this will come with greater chance your performance will fade during the race.   See the help page on Event Readiness for more details. Target Weight You can adjust your targeted race weight.  Reducing your weight on race day will lower the power requirements for the race. The greater the hilliness of the race, the more a reduction in weight will affect the outcome.  Reducing your weight beyond what you can reach can make the race more achievable however achieving the target weight may come at a cost of less power than predicted. Similarly, an increase in weight may mean you plan on going to the gym and will expect to be able to produce more power.  This can end up being higher that what the system predicts on race day and may in fact improve your chances of success.  Note: the fitness signature predictions do not account for the likely reductions/increases in fitness signature from changes to your weight.  It only affects the relative power you will need to produce to replicate the efforts.

 

Weekly Availability Section

This section helps you decide on what days you will expect to be training over the course of the plan.   (If you have specific dates that need to be accounted for, use the Planner to make changes to individual days before analyzing and forecasting a race plan).  Note that any changes here are not saved to your profile until the Forecast is saved.  This allows you to try “what-if” scenarios to see what level of commitment will be required to achieve a particular outcome.

 

General Settings Section

 

Periodization Level When generating a plan, Forecast AI will use this setting to wait until you need to do the training before assigning it.  If you like to ride a lot and want to get started early, slide this to the left.  If you’d prefer to just ride easy and do Zone 2 as long as possible, slide this to the right. Polarization Level Polarized Training involves splitting your low and high intensity into a set pattern, typicall 80/20 or 4 low intensity sessions for each 1 high intensity.  Forecast AI can look to lay out a training plan that uses these ratios for you.  The greater the ratio, the greater amount of high/peak intensity XSS you’ll get prescribed which also means more days of endurance/Zone 2 training.  If you respond well to the polarized training method and like minimizing intensity days, keep this at 80/20.  But if you’re often not motivated to go many days without intensity, slide this to the left.  This increases the frequency of high intensity training days you will get prescibed but with lower high/peak XSS training targets.  Note that in order for Forecast AI to fit the training needed into your availabile schedule, the ratio may need to be decreased. For example, if you only have an hour on your high intensity day, you may not be able to accumulate enough high/peak intensity XSS to reach your training needs so you may see greater high intensity training frequency in your schedule. Recovery Demands Xert automatically balances the recovery you need based on the form for each system every day.  This ensures that you have sufficient recovery throughout your plan.  You can fine tune the amount of recovery you will get by using this slider.  Slide it right to add more recovery time or slide it left for more aggressive training.  Sliding it right can reduce the likelihood of getting a forecasted training plan that reaches the outcome you’re looking for.  Review this link for more info. XSSR Preference You can adjust the degree of difficulty for your training by adjusting this slider.  If you’re time limited but are prepared to invest in more challenging workouts to achieve your race targets, slide this to the right.  If you have the time and are the type to go deep on race day but are not motivated to go as deep on training days, slide this left.

 

 

 

Everyone is familiar with training plans.  They generally give you workouts with perhaps the goal of preparing you for a race or maybe just to “get fit”.  How fit you will be at the end of the training plan is a bit of an unknown.  Will you be ready for the demands of the race? Will you be fit enough to podium?  Will you get dropped? Will you be “fit”? Lots of unknowns.

Wouldn’t it be great if we knew what fitness it took to podium?  Finish in the top 100? Not get dropped on the club ride? Is it just about increasing my threshold power?  Maybe I need to be punchier on the climbs because that’s where I get dropped.  Maybe I need to improve my endurance so I don’t fade later in the race.  Maybe the race ends in a bunch sprint and I need more top end power. What aspect of my fitness and performance needs to improve and by how much?

Everyone that’s ever done a workout would love an answer to this, from the beginner wanting to be able to keep up on the weekend club ride to the professional that longs to be as strong as Tadej Pogacar or Mathieu van der Poel.  We all aspire to have the fitness to achieve our goals.  If only we knew what it took and have the ability train towards achieving them.

It’s now here.  It’s called Race AI.

Here at Xert, we’ve endeavoured to answer this question and solve this very complex puzzle. As you’ll appreciate after reading this post, the effort has been a major undertaking … but we’ve finally done it.

The Race AI Solution – Break Down the Problem into Steps

Like many hard problems, it’s often good to break down a hard problem into individual steps you can solve.  Then put all the steps together and you solve the problem.  If we’re trying to take Rider A and train them towards being able to perform like Rider B did during a race or ride, we have the following steps we need to solve:

1. What’s our target? We need to analyze what Rider B did during the race/ride and assess what fitness Rider A would need to reach to do the same.
2. Is the fitness level something Rider A could achieve?
3. If not, what might they need to change in order to get there?
4. Can we ultimately generate a realistic training plan?  Is there a plan that Rider A can fit within the time they have available, accounts for their unique preferences such that they can follow the program?

If we can solve each of these 4 steps, then we’ve got the basis for generating a training plan that is uniquely tailored to you.  It should help you reach these goals by accounting for your current training status, your capacity for improvement and your ability to follow the plan.

What is the Target?

Understanding and defining the target fitness and performance level the training needs to achieve is as important as anything else that we do. Is it to raise FTP, improve durability i.e. power at the end of the race, handle shorter hills better, increase top end sprinting power or all of the above but in some balance?  Getting the target (or targets even) is the most important step since if we don’t have the right targets to aim for, everything else will be wrong, even if we did all the training and never missed a workout.

So we asked ourselves: What would be the best way to define what the target needs to be?

Best answer: Use a power file from that athlete you wish to perform like.  Many athletes make their data publicly available or if not you can request them to share a ride or race you wish to be able to do and use that.  If the power file was a race winning ride for the event you’re targeting, then being able to produce similar power would be an important step towards reaching a similar outcome.  A properly chosen power file will contain all the elements of what you need to target for your fitness in order to perform at the same level.

There’s a snag though.

If the rider was bigger or smaller than you, then their power data is not likely to be well-suited.  If it was a climber’s course and they raced at 20kg less than you, performing at the same power they did won’t help you in the race.  Similarly, if the course was flat they raced at 20kg heavier than you, performing at the same watts/kg won’t work either.  Watts and watts/kg are both not exactly ideal in this scenario. To do this correctly, the data needs to be transformed from the power they performed at, at the grade they performed it at, to the power you will need to perform to get the same result.

We solved this step problem by introducing the concept of Relative Power.  Relative Power answers the question: If Rider A at 65kg is doing 400W on a 2% climb, what would Rider B at 85kg need to do?  Using Xert’s new Relative Power algorithm, we now have the ability to transform one athlete’s race winning ride, or the athlete that was first to reach the coffee stop on the group ride, or the athlete the broke the record on the hill climb challenge, or the athlete that stole your KOM on the Strava segment, or, or …  We can transform this data into what you’d need to do at your weight (or better .. the weight you aim to be on race day .. hold that thought!).  This is the Race AI solution to Step 1.

Is it achievable?

Achievability means a lot of things since many dimensions of fitness and performance may have gone into the race/ride achievement that’s now encapsulated into the transformed data we can analyze.  What are these dimensions?

1. What FTP / Threshold Power will I need to be at?
2. How much punchiness is required, i.e. High Intensity Energy?
3. Are there no, a few or many sprint efforts involved, i.e. is Peak Power a factor?
4. Are there many repeated hard efforts over the course of a long ride, i.e. increased durability is needed?
5. Are the efforts going to put a strain on glycogen levels and require more fuelling than I’m used to?
6. Will I do better by losing a few pounds for the climbing efforts in the race or will maintaining big power on flatter parts of the course be more important?

Seems like a crazy idea to try and do all this, huh?  It was until we decided to use a secret weapon: MPA analysis.  To answer all of the above.  Step 2 of Race AI repeatedly performs MPA analysis thousands of times, and finds fitness signatures that meet all these constraints.  It then determines which of these fitness signatures are within reach based on the target date and finds the one that is the most attainable.

What if it’s not achievable?

Firstly and realistically, not every race result will be achievable.  As you will soon learn as you start interacting with the system, races performed by professionals at the top of their game, are not going to be reachable by most everyone except for the small few professionals that may have the capacity to perform at the same level.  Indeed, this could be the affirmation they need to invest into their training and seek a professional career in cycling.

Secondly, it might be possible to nudge things a bit and perhaps achieve the target as a stretch target.  For example, perhaps a reduction in your target weight might make things achievable.

Race AI allows you to make a number of adjustments to see if you can reach achievability.  Check out the Race AI Guide for more details:

When we’ve completed making all the necessary adjustments and selections, we can finally move to the last step…

Is there a training plan that I can follow?

The final step is where all the analysis and adjustments get put together and where Xert’s Forecast AI takes over and looks to map out a step-by-step, day-by-day training plan that fits within all the constraints you have – availability, weekly hours, etc.  When Forecast AI finds a training plan, you will have the so-called map that you can follow that will get you from point A to point B, where point A is where you are today and point B is having the fitness to be able to perform at the level that you had set out to achieve.

XFAI is a complex optimization process and accounts for various settings and constraints you can control and adjust:

Adjustment Explanation Availability Forecast AI will look at your riding history to determine which days of the week you like to ride, starting at what time and for how long.  If you plan on doing more (or less) training in trying to reach your target fitness, you can adjust these settings before running Forecast AI. Periodization Periodization level is an advanced setting that will instruct the system as to how much training can be postponed.  For those that are looking to do the least amount of training, move this setting to the right.  For those that like to train, and don’t wish to postpone any training, move this setting to the left. Polarization Polarized Training involves doing a high-intensity session on one day and then doing endurance work / Zone 1/2 work the following days.  This follows an 80/20 pattern or 4:1 of low intensity : high intensity training sessions.  Many athletes lack the motivation to do long endurance rides.  This is a common issue and athletes simply don’t follow programs that are polarized.  They would prefer more combined low/high intensity and with greater high-intensity repetition rates: 3:1, 2:1 or even 1:1.  Adjusting the slider to the left is intended for those athletes that do better with less polarization. Recovery Some athletes due to one reason or another, may need additional rest between sessions. They can still reach higher fitness goals but may take a bit longer to do so.  Other athletes feel that they want to do a lot more when tired.  Use the Recovery Demands slider to adjust to the level you believe is best for you.  Note that it may affect your target fitness achievability. XSSR Preference How much can you suffer during a training session?  This slider helps those athletes that want to get everything done quickly and efficiently (slide it right) whereas others need to build up their pain thresholds with training and prefer longer, easier workouts (slide it more left).

Conclusion

Race AI is a remarkable accomplishment.  It has brought together many new and innovative solutions into an integrated offering.  It solves the longest-standing challenge that has faced the endurance sport community since training was created.

About 7 years ago, we were the first to introduce a multi-dimensional Impulse-Response Model.  We brought in Xert Strain Score, i.e. XSS and the 3 dimensional XPMC.  Since then, Xert has been helping athletes quantify their training in unique and powerful ways.

Over the course of these last 7 years, we’ve acquired quite a bit of understanding about performance and training.  We’ve come to recognize how these models represent deeper aspects of fitness that we didn’t initially realize.  We also learned about some drawbacks that needed to be addressed.  In the course of analyzing thousands and thousands of athletes and their data, we saw opportunities to improve how the system manages this data.  We then saw how we could use this new found knowledge to further optimize training prescription.

Understanding How Impulse-Response Models Work

Before we get into the details, let’s lay some groundwork for the concepts that we’ll be exploring in this universe.  Whether it’s called a Performance Management Chart (PMC), a Freshness-and-Fitness Chart or an Xert Progression Management Chart (XPMC), they all follow the foundational principles that are part of Banister’s original Impulse-Response Model for exercise and use the concepts presented below:

The 4 Main Issues with Traditional Impulse Response Models

Impulse-Response models are remarkably robust. Despite the many drawbacks highlighted below, they work astonishingly well in a great many situations, underscoring how our bodies actually adapt according to these natural mathematical principles.

1. Scores/Training Stress
   • The main challenge with every Impulse-Response model is how to quantify training loads or training stress, particularly if it’s a single-dimensional model.  Quantifying how much of the exercise should be counted towards the accumulation of training load is the biggest challenge. Many metrics have been used and proposed over the years, many based on heart-rate or average power but they often oversimplify the training stress and ultimately make the calculation of training loads less meaningful.  Despite these rougher training stress measurements, Impulse-Response models are still a foundational part of all training prescription.
2. Single Dimensional
   • All training stress isn’t the same and can affect performance in different ways.  For example, repeated sprinting for 20s has a very different effect than repeated jogging for 20s.  Sprinting for 200 metres is different that jogging for 200 metres.  Sprinting to burn 20 kilojoules is different than jogging for 20 kilojoules.  Sprinting for 10 TSS isn’t the same as jogging for 10 TSS.  Simply put, saying “sprinting” should be put in the same bucket as “jogging” is a mistake, even though both are the same activity – running.  Training intensities affect different systems in different ways so using a single dimension to measure training stress will simply never fully represent training stress.
3. Feedback needed
   • Impulse-Response models are used to predict performance but what performance are they trying to predict? What does performance mean? For many sports such as running, it’s pretty simple: you take an athlete’s performance in races.  If the athlete only has a couple of races per year though, then you might need additional tests.  For cycling, it’s a harder problem since races don’t always push the rider to perform at their very best.  Even when they do push and reach their limit during a race, a highest mean-maximal power calculation (i.e. maximum 20 minute power, for example) isn’t always in the data.  Lab testing is often needed and if the athlete is too busy racing, you may not get enough tests in to identify the pattern between training load and performance necessary for the proper application of the Impulse-Response model.
4. Form goes too high
   • A problem we’ve discovered here at Xert, is that value for Form can misrepresent that athlete’s readiness-to-train.  Let’s use a simple example to illustrate.  Say an athlete has a TL of 50 and RL of 50 and they train 50 XSS daily.  The 50 TL is essentially homeostatic, with Form returning to zero everyday.  This requires no recovery since the daily XSS is their average daily and they can do this everyday, by definition.  If one day the athlete happens to miss a day, the following day they would expect to be able to do ~100 XSS to return to homeostasis.  If they missed 2 days, ~150 XSS .. and so on.  RL continues to decrease every day.  But a single bout of 150 XSS isn’t going to bring the athlete to homeostasis, even if Form indicates it is.  The athlete will require some rest because all they have ever done is 50 XSS. 150 XSS is a big disruption to this homeostasis.  Since Form is a measure of readiness-to-train, then it can’t become too positive suggesting the athlete has extra readiness to do a lot more.  That simply isn’t true.  At some point the theory behind what’s possible in the Impulse-Response model using the regular calculation of Form will break down and misrepresent the athlete’s true Form.

How Xert Addresses the 4 Main Issues

Xert’s MPA to the Rescue

The discovery of the math behind MPA has led to more than just discovering what your FTP is and giving you fitness breakthroughs.  It’s gone far further than this and has helped shed light on how training stress and strain affect training loads and performance.  Your fitness signature is used to calculate MPA.  How close you perform to your MPA, as it changes during the course of your workout/ride, is how we calculate strain.  Unlike other measures, this isn’t some average value or value that isn’t visible in heart-rate data (since heart-rate doesn’t reflect short, very high intensity efforts, for example).  MPA allows the ability to derive strain second-by-second.  This addresses the first issue:  1. Score/Training Stress.

Your fitness signature helps quantify which proportions each fitness signature parameter contributes to the strain associated with the current effort during a ride.  With 3 parameters: Threshold Power, High Intensity Energy and Peak Power, we can determine which of the three is being affected by strain.  That is, we can take a strain value and divide it up into Low, High and Peak systems, each corresponding to Threshold Power, High Intensity Energy and Peak Power, respectively.  Here we resolve the single dimensional problem 2. Single Dimensional and use 3 dimensions instead.

Breakthroughs are fun.  But they are hard to get, sometimes almost impossible.  But you get them far more often than those times you get a new 20 minute best power for example.  You may never get a new 20 minute best power in an entire season.  Xert’s fitness breakthroughs are the foundation of how we solve 3. Feedback Needed, rather than rely on lab testing, we can rely on day-to-day maximal efforts that most athletes have within their data.  Indeed, achieving fitness breakthroughs not only informs the model on how you’ve been progressing, but they are fun, part of racing and improve your fitness all at the same time.  An interesting phenomenon that we’ve discovered in Xert is the degree to which you express an aspect of your fitness is the same as the amount of strain you apply on it.  That’s profound.

Improving Readiness-to-Train

Addressing the fourth issue above: 4. Form goes too high, requires rethinking the Impulse-Response model fundamentals.  If we are looking to use day-to-day Form as a way to assess an athlete’s readiness-to-train, i.e. establishing a Tired or Very tired training status for example, then we’ll need to prevent Form from going too high.  This is the same as preventing RL from continuously decreasing.  We should cap RL to a more realistic value.  If an athlete has a TL of say, 100 then, in principle, 100 is their homeostatic Training Load and Recovery Load should return to 100 minimum whenever an activity with 100 XSS is performed.  RL should not decline more than what is required to return to zero form after an average day.  We recently introduced this updated calculation of RL and is clearly visible on your XPMC during periods of longer time between activities.  The consequence of this change is that you won’t see consecutive, high-volume training days with positive form.  From a planning perspective, you are not likely to feel overtrained returning from a few days off following Xert’s guidance.

​

Form goes negative immediately after a big ride since Form (i.e. freshness, readiness-to-train) is capped before the ride.

Things That Live in this Multi-Dimensional Impulse-Response Space

As you might envision, managing the data from thousands of activities and examining second-by-second XSS/strain data using your fitness signature at that time, power and MPA, then subdividing each second’s strain into Low, High and Peak XSS that then feeds each into a corresponding and different Impulse-Response model, to calculate TL, RL and Form values for each system every second is a computationally challenging effort. But Xert does precisely this.  In fact, once you have all this set up and tuned for a given athlete, a whole new universe of applications and actionable information become apparent and useful, both in predicting outcomes but also in optimizing a training program.  Let’s dig into this.

Here are various aspects of training and performance many of you may be aware of that live in this multi-dimensional space:

Concept	Explanation
Fitness and Performance	Having addressed all the main drawbacks of using an Impulse-Response model, we can correlate training loads with performance far more precisely and reliably.   We define performance as what your fitness signature parameter was at a given time.  This makes sense since your fitness breakthroughs express the changes in each of your fitness signature parameters.  By going back historically, we can see where your fitness (Low, High or Peak Training Loads ) was at a given point in time and what your corresponding Threshold Power, High Intensity Energy and Peak Power were at that time and calculate how changes in your Training Loads affect each parameter.  Xert does this for you and updates this relationship with each breakthrough processed.  The results end up computing your Training Responsiveness coefficients that you see in your Profile Settings:
Low/High/Peak Training Loads	In the course of a season, you will be doing various amounts of high-intensity training and your Low, High and Peak Training Loads will vary.  Sometimes you spend more time doing base/Zone 2 and your Low Training Load goes up while High and Peak may go down, for example.  Other times, you may be doing short Zwift races perhaps, and accumulate more High and Peak Training Load and see Low Training Load decline.  How each of your Low, High and Peak Training Loads move up and down reflects the type of training you’ve been doing.  You can evaluate where your Low, High and Peak Training Loads were at various points in the season.  It becomes readily visible that those times when you were performing well at specific types of rides and events, were those times when you were well-trained for them.  Training Loads reflect what kind of riding you had been focused on and also reflect what type of riding you were good at.  These are often one and the same.
Focus and Specificity	Similar to being able to review Low, High and Peak Training Loads, you can also interpret these as a Focus with an associated Specificity.  If you’ve been preparing for a major event in the Dolomites, you’d be training using long efforts around Threshold Power and accumulating mostly Low and High Training Loads.  You’d have few training rides that increase your Peak Training Load.  From an Xert Athlete Type standpoint, your Training Loads would have a more Climber Focus, i.e. a long duration Focus as would be appropriate for longer mountainous riding.  The ratios of your Low, High and Peak Training Loads reflect your training at a particular Focus Duration and Specificity.  This helps to better interpret what the relative effect Low, High and Peak Training Loads have on your performance.
Readiness-to-Train	Each system has its own TL, RL and Form values and we can use these values to establish a readiness-to-train.  One system may have a large negative value and requires recovery whereas another might have positive form and is ready for training.  Readiness-to-train now becomes a multi-dimensional number whereby you may need recovery in one dimension whilst being able to train another.  This is a unique aspect that can be used to identify the type of training that’s appropriate at a given point in time.  For example, if your High and Peak systems have a negative form from recent high-intensity rides but your Low system is still fresh with a positive form, then you can continue to ride but at an Endurance pace.  Xert does precisely this when it comes to identifying your readiness-to-train for High/Peak intensity workouts (Fresh/blue Training Status), readiness-to-train for Low intensity only (Tired/yellow Training Status) and full recovery needed (Very tired/red Training Status).
Recovery Demands	Not everyone handles training volume equivalently.  Some can train sooner after a workout whilst others might need a bit longer to recover.  Most of this is explained by the difference in Training Loads since those with a higher Training Load can handle more training than those with lower Training Loads (this is, again, a by definition statement and physiological assessment).  Those that average higher daily training volume than others are doing more and thus recover more quickly.  But when Training Loads are the same, some may need a bit of extra time compared to others.  In Xert, the value of Form that describes the Train/Recovery boundary is something you can tweak using the Recovery Demands slider.  Sliding it right increases the Form values for all three that define a Train/Recovery boundary.  Sliding it left decreases this.  Ultimately, this governs the amount of recovery the system assigns between each training requirement in your Training Program.
Durability and Event Readiness	Recently, the concept of durability has grown in prominence as an important training metric that’s key to your performance in races.  In Xert, we use Event Readiness as a way to characterize durability – if you’re ready for a race it means that you have built up enough durability to withstand the demands of the race, i.e. the Low, High and Peak XSS you’ll be required to perform. Durability lives in these models by virtue of being the opposite of fatigue.  Being durable equates to less fatigue.  If we know the demands of an event, we can pre-compute your accumulated fatigue both after and during. To withstand and reduce your fatigue, i.e. improve your durability, you’ll need to prepare by increasing your training accordingly.  Longer, more demanding events (think greater XSS values) require more Training Load (Low, High and Peak TL) to prepare. Determining how much Low, High and Peak TL you’ll need is a matter of seeing how each TL and RL will be affected during the course of the event’s Low, High and Peak XSS accumulation.  If we presume you’ll be fully fresh at the start, we can calculate what your TL and RL  should be for each system such that you can complete the event without accumulating too much residual fatigue. For example, if Low XSS is 200 for an event, what should your Low TL be in order to be *ready* for it?  The answer depends on how ready you would like to be.  If you just want to finish, then your Event Readiness may be a higher number and you’re fine with less durability.  If you want to win and it’s a long race, you may want to improve your durability and increase your Event Readiness in order to withstand the demands as well as, if not better than your competition.  In Xert, you can configure the Event Readiness you wish to have for your event and the system will allocate the appropriate amount of training you’ll need to perform to be ready. At the 100 minute mark, this athlete requires a day of recovery at that point. Completing the race they’ll require 2.5 days of recovery. At the 100 minute mark, this athlete is still fresh and not impacted by the race demands. At the completion of the race they’ll require just 1 day of recovery.
Tapering	Similar to Durability and Event Readiness, your TL and RL values at the start of a race and the demands of the race itself, will help identify the amount of tapering needed.  For shorter events, going into the event with only a small taper might allow you to be at the top of your fitness whereas a longer, harder event might require all three systems to be fully recovered beforehand.  Note that since RL’s decline is now capped, you can over taper for an event by resting too much beforehand and end up with less than optimal fitness and freshness for the event.
Polarized Training	Polarized training is a training method often recommended by coaches and sports scientists as it has been shown to produce great results.  Polarized training means that you should follow an 80/20 rule between low intensity/high intensity training.  80% of your training (4 out of 5 workouts) should be low intensity and 20% (1 out of 5 workouts) should be high intensity. In Xert, by employing a 3 dimensional model with 3 systems, each with different time constants for TL and RL, and managing form across all three separately, we can see how some systems might need recovery while others are ready for training.  This separation is why Polarized Training is advantageous – while some systems recover, other systems can be trained so you don’t need complete rest. We use a Train/Recover Form boundary value for each system, which helps define whether the system is ready-to-train or needs recovery.  You can control this using the Recovery Demands slider. If Form is below this number, that system requires recovery.  If Form is above this number, that system can be trained.  This applies to all three systems in Xert – Low, High and Peak.  Due to how the time constants work, your Low system recovers much faster than your High and Peak systems.  Your Low system could be thought of as your endurance system so it makes sense that it can handle more and returns to ready-to-train much sooner, with your high and peak form taking longer to recover.  This conveniently allows you to do endurance/Zone 2 training since your Low system is ready for training whilst your High and Peak system are still recovering. In Xert, Polarization Level can be adjusted and training programs like Forecast AI, can use your preferred Polarization Level, to allot the appropriate amount of high-intensity training such that you will recover according to the Polarization Level you choose.  This ensures that your training isn’t just polarized but you will be doing sufficient high-intensity to fill the 80/20 or whichever Polarization Level you choose.  One of the key tenets of polarized training is that high-intensity workouts are hard and low-intensity workouts are easy and the not hard enough and not easy enough workouts should be avoided.  The natural expression of the Xert model’s time constants with your chosen Polarization Level is used to enforce this. It ensures you get an appropriate amount of high-intensity training such that you’ll recover in time to perform the next high-intensity training according to your Polarization Level.  Note that if you don’t have time available to do all of the high and peak intensity needed for this, Forecast AI will spread out the intensity reducing the Polarization Level cycle in order for you to continue to progress towards your training target.
Periodization	It’s been well established that the human body responds to high-intensity training much faster (in terms of how quickly you improve from training) as compared to low-intensity training.  This means that what you need to train to optimize outcomes changes over the course of a training program.  This change is a type of periodized training.  In the Impulse-Response models, this translates into each system’s Training Load time constant.  Those with longer time constants, take longer to buildup and those shorter time constants, can be built up sooner.  This means that your Low intensity system (defaults to 60 days) and your High/Peak systems (default to 22 days) will need training at different times during the training program.  Xert Adaptive Training Advisor implements a standard, preset 120-day Base-Build-Peak periodization method but Xert Forecast AI manages this build from low-intensity to high/peak-intensity based on the time constants you have set and your Periodization setting.  Using the existing 22-day time constant, that’s been default TL time constant for High and Peak systems many years in fact, you’ll notice from the diagram below that a 120-day program will be naturally periodized into Base Build Peak over similar phases as the one used by the Adaptive Training Advisor by virtue of this time constant.  This discovery and interpretation of the multi-dimensional system was a confirmation of how the model implements known training best practices without having to apply any arbitrary rules.