Upload your race GPX. Get an ML-powered finish time prediction based on the actual course profile — not a Riegel-formula guess.
The predictor uses an XGBoost regression model trained on 21,000+ split-level ultra results. For each segment of your GPX, the model takes terrain features (elevation gain per km, average and max grade, grade variability), distance completed, cumulative elevation gained so far, and a baseline fitness reference derived from your recent race result.
Your recent race time is converted to a flat-marathon-equivalent pace using the Riegel formula (1.06 exponent), then the model handles the projection forward — including how pace degrades with distance and terrain. The Riegel scaling is only used to normalize the reference; the actual prediction uses the trained model.
No model nails everything — nutrition, weather, sleep, and a bad day are not in the GPX. The confidence range you get back reflects model uncertainty on similar courses in the training data, not your day-of execution.
“A 100K with 4,000 m of climbing is not 2.4× a marathon. It's a different sport.”
The Riegel formula was validated for distances up to the marathon. Past that, it systematically under-predicts finishing time because it ignores elevation, technical terrain, and the non-linear fatigue curve of ultra-distance running. Most online “race time predictors” are wrappers around Riegel — useful for road 5K-to-marathon projections, near-useless for trail ultras.
UTMB is 171 km with about 10,000 m of climbing across the Alps. Generic predictors miss the elevation entirely. Upload the UTMB course GPX (available on the official site) and the model will account for the major climbs — Col du Bonhomme, Grand Col Ferret, Tête aux Vents — and the descent dynamics that wreck quad strength late in the race.
Western States is 161 km with around 5,500 m of climbing and 7,000 m of descent — and almost all the descent is runnable. The model handles this asymmetry: long runnable descents pull your average pace down in a way that mountainous out-and-backs don't. Heat is not in the GPX, so plan for canyon-temperature reality on top of the prediction.
For first-time ultra runners, course-aware prediction matters more than experienced ones. You don't yet know your degradation curve. Upload the course, plug in a recent marathon or 50K, and use the per-segment splits to plan aid station ETAs. Aim for the upper end of the confidence range on race day — first ultras almost always run slow.
Course-aware ML predictions are typically within 5–10% of finishing time for trained ultra runners on courses similar to those in the training data. Generic predictors that only use distance (like the Riegel formula) lose accuracy quickly past the marathon — they ignore elevation, technical terrain, and accumulated fatigue. This predictor uses the actual course profile from your GPX.
Yes. The underlying model is trained on per-segment terrain features — elevation gain per km, average and maximum grade, grade variability — alongside cumulative fatigue. It learns how pace degrades with terrain rather than applying a fixed elevation penalty like Naismith's rule.
That works. The predictor uses Riegel-equivalent scaling (the 1.06 exponent validated across distances up to the marathon) to estimate your flat marathon-equivalent pace, then the ML model handles the projection out to ultra distance — including how your pace will degrade with terrain and fatigue. Shorter, more recent reference races usually produce better predictions than older or longer ones.
Two reasons. First, fatigue compounds non-linearly past the marathon — the model learns this from real ultra split data. Second, elevation gain on most ultras adds substantial time that flat-road predictors ignore. A 100K with 4,000m of climbing is not a 2.4× marathon; it's a different sport.
You need some fitness anchor. If you don't have a recent race, use a recent hard time trial of 5–10K — the predictor only needs distance and time. Without a reference, any prediction would be a guess.
It's an XGBoost regressor trained on 21,000+ split-level ultra results across distances from 50K to 100M. It predicts per-kilometer pace from terrain (elevation, grade), distance completed, cumulative fatigue, and a baseline-fitness reference. Validation R² is 0.79 on held-out races.
Both. The model takes terrain features from your GPX directly, so a flat 100K and a mountainous 100K get different predictions automatically. Road ultras are well-represented in the training data.
No. This tool is stateless — your GPX is processed in memory and discarded. No account, no upload history, no tracking of the file contents.
