Doctoral student in Predicting Hydrological Extremes with Earth Data
Understanding and predicting hydrological extremes is essential for water management and climate resilience. In this context, the Department of Sustainable Development, Environmental Science and Engineering at KTH Royal Institute of Technology is offering a PhD position at the interface of hydrology, remote sensing, machine learning, and seasonal forecasting. This PhD project aims to develop global Earth observation–based indicators, machine learning prediction systems, and data assimilation methods to improve forecasting of transitions from drought to flood events. The project has three main objectives:
- Integrate multiple Earth observation sources to design indicators of drought-to-flood transitions.
- Develop machine learning models that capture the spatiotemporal interplay of hydro-climatic drivers for consecutive drought-to-flood events.
- Combine data assimilation with predictive models to improve seasonal forecasts using near real-time Earth observation data.
The student will be admitted to the PhD program in Environmental Engineering at KTH in Stockholm, Sweden.
Key qualifications and skills:
- At least 60 completed credits in environmental engineering or related fields
- Experience in hydrology or hydraulics
- Strong quantitative skills, including statistics and time-series analysis
- Familiarity with machine learning or deep learning methods
- Experience handling large datasets
- Ability to work independently, collaborate in teams
- Proficiency in English
Deadline: March 1st, 2026