Author Archives: istefanou1

Discover our new research paper “Reinforcement Learning-based adaptive time-integration for nonsmooth dynamics”

Traditional time integrators struggle with nonsmooth systems, often slowing down or losing accuracy. Our new approach uses Reinforcement Learning to automatically choose optimal time steps, adapting even when the dynamics are nonsmooth. Tested on three challenging problems, a sliding-mode control system, a diode circuit, and a seismic fault model, our RL-based integrator significant speed-ups, reaching up to 10× faster in the hardest cases. A promising new direction for efficient time integration across complex dynamical systems.
For more details: https://link.springer.com/article/10.1007/s44379-025-00048-6

How to tame earthquakes

On September 29, 2025, ENSTA Paris | IP Paris interviewed Ioannis Stefanou, principal investigator of the ERC INJECT project — his second ERC grant as scientific coordinator. He discusses what inspired his journey into this evolving field, presents his project’s interdisciplinary objectives, and highlights how his research could advance clean geoenergy production and storage.

Ioannis Stefanou, ou comment dompter les séismes | ENSTA

Welcome to INJECT!

INJECT is an ERC-funded project focused on preventing human-induced seismicity as part of the fight against climate change. Through this site, we’ll share the latest news, research findings, innovative tools, and valuable resources related to our mission.

Explore our website to learn more about the project, the scientific challenges we address, our team, open positions, and more. Stay tuned as we share our curiosity and discoveries in this evolving field!