Call for Papers

We invite researchers, industry professionals, innovators, and policymakers to submit their papers for the 2026 Tire Society Conference, under the theme “Reinventing the Tire - Digital Transformation, Data-Driven Advances, and Predictive Methods”. Exploring the role of transformative enablers in the industry, we are looking for original, unpublished papers that address, but are not limited to, the following topics:

Advances in Tire Modeling: Showcase how big data, predictive methods or self-improving algorithms are transforming tire models. Topics may include model training from test and telemetry data, adaptive modeling techniques, and the use of predictive methods to estimate tire performance across operating conditions.

Smart Testing and Validation: Discuss technology’s role in augmenting physical testing needs through predictive modeling, anomaly detection, and test automation, leveraging tools such as digital twins and reinforcement learning strategies.

Tire Design Optimization: Investigate how computational tools and digital workflows accelerate tire design, from geometry and tread pattern to compound and material selection. Submissions may highlight multi-objective optimization, inverse design, or generative approaches driven by performance goals.

Manufacturing and Quality Control: Discuss the integration of systems in smart manufacturing processes, including predictive maintenance of tire production equipment to image-based defect detection and process control.

Connected Tires and Real-Time Intelligence: Investigate how tires are becoming active components in vehicle intelligence systems. This includes real-time data acquisition from embedded sensors, model-based diagnostics, condition monitoring, and contributions to vehicle safety, performance, or efficiency. Discuss integration with autonomous vehicles where applicable.

Simulation Acceleration and Surrogate Modeling: Present methods that reduce the computational burden of high-fidelity simulations, including surrogate models, reduced-order models, and ML-based accelerators.