Exploration of walking speed prediction: a data-driven approach

Abstract

Hikers and hillwalkers typically use the gradient in the direction of travel (walking slope) as the main variable in established methods for predicting walking speeds along a route. Research into fell-running has suggested further variables which impact speed in this context. Recent improvements in data availability, as well as widespread use of GPS tracking now make it possible to test these variables on a large scale. Here we tested various models used to predict walking speed against public GPS data from almost 93,000 km of UK walking / hiking tracks. Tracks were filtered to remove breaks and non-walking sections. A generalised linear model (GLM) was found to be most accurate at determining walking speeds. Key differences between the GLM and commonly used rules were that the GLM considered the gradient of the terrain (hill slope) irrespective of walking slope, as well as the terrain type and level of terrain obstruction in off-road travel. All of these factors were shown to be highly significant, and this is supported by a lower root-mean-square-error compared to existing functions, particularly in the areas where the majority of travel occurs. We also noted an increase in RMSE between the GLM and established methods as hill slope increases, further exemplifying the importance of this variable. As well as providing a new walking speed formula, the underlying dataset can be used in future work to test alternate models.