Explainable Time Series Prediction of Tyre Energy in Formula One Race Strategy

2025-01-07

AI Summary

Real-time tire strategy optimization in Formula 1 requires accurate, interpretable forecasting of tire energy degradation across compound types (soft, medium, hard) to inform pit-stop timing and compound selection. Method: This paper proposes an interpretable time-series forecasting framework that tightly integrates explainable AI—specifically feature importance analysis and counterfactual explanation—into both deep learning architectures and the XGBoost framework, trained exclusively on real-world telemetry data from the Mercedes-AMG Petronas F1 Team. Contribution/Results: The model achieves state-of-the-art accuracy in predicting tire energy decay. Its explanation module quantitatively disentangles the mechanistic influence and relative contribution of critical driving dynamics—including vehicle speed, longitudinal/lateral acceleration, and cornering characteristics—enabling strategy-level causal attribution. The resulting system delivers both high predictive fidelity and actionable, human-interpretable insights, demonstrating readiness for operational deployment in live race strategy support.

Technology Category

• Humans and AI: Explainable AI (XAI) for Human Understanding
• Machine Learning: Transparent, Interpretable, Explainable ML
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Formula One (F1) race strategy takes place in a high-pressure and fast-paced environment where split-second decisions can drastically affect race results. Two of the core decisions of race strategy are when to make pit stops (i.e. replace the cars' tyres) and which tyre compounds (hard, medium or soft, in normal conditions) to select. The optimal pit stop decisions can be determined by estimating the tyre degradation of these compounds, which in turn can be computed from the energy applied to each tyre, i.e. the tyre energy. In this work, we trained deep learning models, using the Mercedes-AMG PETRONAS F1 team's historic race data consisting of telemetry, to forecast tyre energies during races. Additionally, we fitted XGBoost, a decision tree-based machine learning algorithm, to the same dataset and compared the results, with both giving impressive performance. Furthermore, we incorporated two different explainable AI methods, namely feature importance and counterfactual explanations, to gain insights into the reasoning behind the forecasts. Our contributions thus result in an explainable, automated method which could assist F1 teams in optimising their race strategy.

Problem

• F1 racing
• tire energy prediction
• optimization strategy

Innovation

• Deep Learning
• XGBoost
• Predictive Maintenance