Machine learning engineer Jobs in Stuttgart

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 :

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 University of Stuttgart Germany in collaboration with the German Academic Exchange Service (DAAD) opens a call for max. 2 PhD positions for research in Environment Water. Each project involves high-quality research and state-of-the-art techniques and is supervised by excellent researchers. We are looking for highly motivated and talented students with a passion for science. Candidates must demonstrate an excellent performance in their previous academic education.

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

Advisor : 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

The majority of hydrological models rely heavily on the principle of mass balance often represented through Ordinary Differential Equations (ODEs). These models encapsulate the conservation of mass within hydrological systems ensuring that the inflows outflows and storage changes are accurately accounted for. This fundamental principle coupled with assumed relationships between various components of the hydrological cycle (such as precipitation evapotranspiration runoff and infiltration) forms the core of traditional hydrological modeling approaches. Although powerful these models often use simplified linearized assumptions limiting their capacity to capture the nonlinear complexities inherent in real-world hydrological processes.

Recently there has also been the branch of neural hydrology where hydrological models are directly learned from data via machine learning (e.g. LSTM neural networks 1). Initially these models ignored all physical background knowledge and did not necessarily conserve mass as they used black-box model structures far away from that of rainfall-runoff models. For these reasons neural hydrology is often criticized by the conventional hydrological community. Alternatively it is well known that Neural ODEs 2 are capable of representing dynamic systems that are coded in ODEs. They can encapsulate the complex temporal dependencies and dynamics inherent in hydrological systems offering a promising direction for integrating machine learning with physical modeling. The potential of neural ODE models in hydrology has been discussed in 3.

Nevertheless both conventional hydrological approaches and neural hydrology typically depend on interpolated input data e.g. precipitation. Real-world data are often sparse and primarily obtained from meteorological stations and occasionally supplemented by opportunistic sensors. The integration of diverse opportunistic sensor data sources 4 such as private weather stations further broadens the capability of hydrological models to reliably forecast extreme hydrological events. However these data sets must initially undergo interpolation before integration into hydrological models.

Current research is developing combining Transformers 5 with Neural ODEs resulting in an end-to-end modelling framework. Transformers are particularly effective at capturing complex long-range spatiotemporal dependencies within heterogeneous and opportunistic sensor networks. Therefore such an approach may significantly improve rainfall and runoff predictions.

References

1. Kratzert F. Klotz D. Brenner C. Schulz K. & Herrnegger M. Rainfallrunoff modelling using long short-term memory (LSTM) networks. Hydrology and Earth System Sciences 22(11) 6005-6022. (2018).

2. Chen R. T. Rubanova Y. Bettencourt J. & Duvenaud D. K. Neural ordinary differential equations. Advances in Neural Information Processing Systems 31. (2018).

3. Hge M. Scheidegger A. Baity-Jesi M. Albert C. & Fenicia F. Improving hydrologic models for predictions and process understanding using neural ODEs.

• Hydrology and Earth System Sciences
• 26(19) 5085-5102. (2022).

4. Brdossy A. Seidel J. & El Hachem A. (2021). The use of personal weather station observations to improve precipitation estimation and interpolation. Hydrology & Earth System Sciences 25(2) 583601

5. Meo C. et al. (2024). Extreme precipitation nowcasting using transformer-based generative models. ICLR Workshop : Tackling Climate Change with Machine Learning.

Your Tasks

Research goals :

Our primary goal is to improve the accuracy and prediction reliability of hydrological models through an innovative end-to-end modelling framework. Specifically we aim to develop and evaluate a novel hybrid model that combines Transformers with Neural ODEs integrating both data-driven machine learning techniques and established physical hydrological principles. This novel hybrid approach should be then rigorously validated and compared against conventional hydrological modelling methods that explicitly use interpolation to pre-process precipitation addition the research should explore the integration of opportunistic sensor data to improve forecast performance particularly during extreme events addressing limitations inherent in traditional meteorological monitoring networks.

Methods to be used :

The research will focus on the integration of Transformer architectures 5 and Neural ODEs 2 creating a cohesive end-to-end hydrological model. Transformers will be utilized to pre-process and analyse the raw input data capturing essential spatial and temporal relationships in rainfall data. Neural ODEs (or initially more traditional hydrological models like HBV) will then enforce physically consistent mass balances to translate the pre-processed rainfall into runoff reliably. These methodologies will be employed to model dynamic systems where the dependencies between state variables and their temporal evolution will be the Neural ODEs state variables will be defined similarly to those in existing conceptual hydrological rainfall-runoff models such as HBV. However the storage terms and fluxes as functions of the current model states will be learned using Neural ODEs which inherently follows the principle of mass balance but have more flexibility in matching the complex rainfall-runoff relation. To validate and test the proposed hybrid framework selected case studies will be implemented and compared against suitable baseline models such as standard HBV with traditional rainfall interpolation. The selection of methods and case studies will be tailored to identify the most effective combination for addressing the challenges posed by the proposed research. This methodological flexibility is crucial for optimizing the models performance and ensuring its applicability to real-world hydrological systems.

Your Profile

Prerequisites :

Further Prerequisites :

Copies of Certificates and Transcripts including all undergraduate level certificates and university degrees. All documents which are not in English or in German must be accompanied by copies of a legally certified English translation (for the application we will accept copies; but please be aware that originals or legally certified copies will be needed for the final case any differences between the copies and the originals show up the application will be dismissed.)

Please make sure that the copies of the transcripts show not only the grades but also explain the home grades system (please add copy of the description of grade scale ).

Your Benefits

Research Environment :

This research will be embedded into the Chair of Stochastic Simulation and Safety Research for Hydrosystems (LS3) at the IWS Faculty of Civil and Environmental Engineering. Depending on qualification of the candidate a formal association of the project to the SC SimTech Science is possible.

Employment and compensation information

Maximal Funding Period or Duration of Employment : 48 months

Type of Funding : Scholarship

Compensation : 1300 per month

Percentage of weekly working hours (usually 39.5h 100%) : 100%

Employment at the cooperation partner :

Location : Stuttgart Campus Vaihingen

If Location other than Stuttgart or additional location(s) : N / A

Contact Details

Contact person : Dr. Gabriele Hartmann

Mail : Phone : 49 5

Website : targetblank>

Not translated in selected language

Key Skills

Bootstrap,CSS,Front-End Development,HTML5,React,Redux,Node.js,Angular,Less,JavaScript,backbone.js,Sass

Employment Type : Full Time

Experience : years

Vacancy : 1