> Markdown version of [/jobs/ext/4106983-thesis-machine-learning-for-leak-detection-in-water-distribution-networks](https://www.wearedevelopers.com/jobs/ext/4106983-thesis-machine-learning-for-leak-detection-in-water-distribution-networks). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Thesis Machine Learning for Leak Detection in Water Distribution Networks

- **Company:** Diehl Stiftung & Co. KG
- **Location:** Nürnberg, Germany (Remote available)
- **Contract:** Permanent contract
- **Skills:** Data Analysis, Python (Programming Language), Machine Learning, Information Technology, Data Analytics
- **Published:** October 19, 2026
- **Apply:** https://www.indeed.com/viewjob?jk=d73ea2f784818d8b

## About the Role

* You are enrolled in a Master's degree program in Computational Engineering, Computer Science, Data Science, Physics, Mathematics, or a related engineering or scientific discipline.
 * You have solid programming skills in Python and a strong interest in data-driven problem solving.
 * You bring basic knowledge of Machine Learning and ideally have experience working with time-series data and data analysis techniques.
 * You are characterized by a structured and independent working style, strong analytical thinking, and enthusiasm for tackling research-oriented challenges.
 * You are a proactive team player with excellent communication and presentation skills, very good English proficiency, and a strong motivation to learn and apply new Machine Learning technologies and methods.

## Description

* Analyze smart meter and sensor data from simulated and real-world water distribution networks to identify patterns related to leaks.
 * Develop and implement machine learning models for leak detection and localization in water distribution systems.
 * Evaluate and compare different machine learning approaches for anomaly detection and assess their suitability for practical applications.
 * Validate model performance under varying network conditions and investigate the robustness and limitations of the developed methods.
 * Document your findings, derive recommendations for real-world deployment, and collaborate closely with experts from Diehl Metering and academic research partners.