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

TL;DR

This paper develops an explainable deep learning and machine learning approach to forecast tyre energy in F1 races, aiding strategic decisions like pit stops by providing interpretable insights.

Contribution

It introduces an explainable AI framework combining deep learning and XGBoost for tyre energy prediction using F1 telemetry data, enhancing race strategy optimization.

Findings

Deep models accurately forecast tyre energy during races.

Explainability methods reveal key factors influencing predictions.

The approach supports strategic decision-making in F1 racing.

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.