Doctoral student in induced and natural seismicity forecasting

The doctoral student will develop, integrate, and evaluate forecasting models of induced and natural earthquakes. The responsibilities include:

• Model Integration: Incorporating state-of-the-art models, specifically ETAS-f and Oracle, into the SED's forecast management and scheduling system
• Systematic Evaluation: Performing rigorous model comparison tests to determine forecast quality
• Surrogate Modeling: Building, training, and evaluating machine learning surrogate models to emulate complex seismic behaviors and accelerate forecasting
• Data Engineering: Populating and managing data lakes with large-scale natural ETAS simulations and synthetic datasets to provide the foundation for AI training
• Scientific Communication: Publishing findings in high-impact journals and presenting at international conferences

• Education: An MSc degree in Geophysics, Physics, Mathematics, Data Science, or a related quantitative field
• Technical Skills: Strong programming proficiency (primarily Python)
• Domain Interest: A deep interest in seismology, induced seismicity, and the application of statistics and machine learning to earth science problems
• Analytical Skills: High-level quantitative skills and a structured approach to complex problem-solving
• Communication: Ability to work effectively in a collaborative environment with full proficiency in English (written and oral)