Hybrid Human Model for Time of Hike Prediction

Accurate predictive models of human energy expenditure are essential for both individual health monitoring and optimizing performance in physically demanding environments. Estimating energy costs and traversal time in complex terrain is crucial for preventing overexertion-related injuries and guiding individuals through strenuous tasks. Beyond personal applications, these models play a critical role in search and rescue operations, where efficient resource allocation can determine mission success. However, these scenarios present challenges such as diverse terrain conditions, equipment constraints, and varying physical capabilities, all under time-sensitive decision-making. This paper examines terrain traversal time using publicly available GPS data from hikers. We introduce a hybrid predictive model that integrates two existing frameworks to estimate walking speed, energy expenditure, and time profiles while capturing fatigue dynamics. By linking energy estimates with human and terrain factors, our model provides a more comprehensive representation of physical exertion. Comparisons with conventional hiking-time formulas demonstrate that our approach significantly improves prediction accuracy, offering a powerful tool for planning and decision-making in high-stakes environments.Clinical relevance This work develops a hybrid model to enhance health monitoring by predicting physical energy expenditure and the time required to complete challenging hikes.