End-to-End Hydrological Modelling Using Machine Learning : Leveraging Transformers and Opportunistic

Position ID: 1742

Faculty / Facility: Civil- and Environmental Engineering

Institute / Facility: Civil- and Environmental Engineering: IWS - Institute for Modelling Hydraulic and Environmental Systems

Research Association: N / A

Teaching Obligation: N / A

Application deadline: 10 / 01 / 2025

Anticipated Start Date: 10 / 01 / 2026

About Us

The international Doctoral Program Environment Water (ENWAT) of the Faculty of Civil and Environmental Engineering Sciences at the University of Stuttgart, Germany, in collaboration with the German Academic Exchange Service (DAAD), announces up to 2 PhD positions in Environment Water. Each project involves high-quality research using state-of-the-art techniques, supervised by excellent researchers. We seek highly motivated and talented students passionate about science, with excellent academic performance.

Position Title

End-to-End Hydrological Modelling Using Machine Learning: Leveraging Transformers and Opportunistic Sensor Data for Hydrological Predictions

Advisors

Prof. Dr.-Ing. Wolfgang Nowak, apl. Prof. Sergey Oladyshkin, Dr. rer. nat. Jochen Seidel

Research Group / Department

Chair of Stochastic Simulation and Safety Research for Hydrosystems (LS3)

Institute for Modelling Hydraulic and Environmental Systems (IWS)

Stuttgart Centre for Simulation Technology (SC SimTech)

Keywords

Hydrological modelling, Model development, Deep learning, Transformers, Data-driven modelling

Introduction / Background

[... detailed background description ...]

Your Tasks

Research goals: Our primary goal is to improve the accuracy and reliability of hydrological models through an innovative end-to-end framework, combining Transformers with Neural ODEs and integrating opportunistic sensor data to enhance predictions, especially during extreme events.

Methods to be used: The research focuses on integrating Transformer architectures and Neural ODEs to develop a cohesive hydrological model. Transformers will analyze raw rainfall data, while Neural ODEs will enforce physical mass balance principles to translate rainfall into runoff, validated against baseline models like HBV.

Your Profile

Prerequisites:

• MSc in hydrology, environmental sciences, hydrogeology, water management, or similar; or in data sciences, statistics, applied mathematics.
• Skills in programming (Python, MATLAB, Julia)
• Scientific writing and presentation skills
• Ability to work independently and in teams
• Experience in hydrological modelling or machine learning

Further Prerequisites:

• CV, list of publications, presentations, awards
• Dipl.-Ing. or equivalent in Civil Engineering, Water Resources Management, Environmental Engineering, or related sciences
• Copies of certificates and transcripts, with English translations if needed
• Residency in Germany for no more than 15 months at nomination time
• Proficiency in English (TOEFL, IELTS, etc.)
• Two reference letters from recent university professors
• Motivation letter (1 page)
• Summary of relevant information (1 page)

Your Benefits

Research Environment: Embedded in the Chair of Stochastic Simulation and Safety Research for Hydrosystems (LS3) at IWS, Faculty of Civil and Environmental Engineering. Possible association with SC SimTech.

Employment and Compensation:

• Max duration: 48 months
• Funding type: Scholarship
• Monthly stipend: 1300 EUR
• Full-time (39.5h/week)

Location: Stuttgart Campus Vaihingen

Contact Details

Contact person: Dr. Gabriele Hartmann

Mail: [Contact email]

Website: [URL]

Note: The last line indicates the page is not translated.

Key Skills

Python, MATLAB, Julia, Data Science, Hydrological Modelling

Employment Type: Full Time

Experience: [Specify years]

Vacancy: 1