This PhD project investigates the generalisation and transferability of machine-learning models for hydrological extremes. The research focuses on how data-driven models developed in well-instrumented experimental catchments perform in ungauged or data-scarce mountain basins.
Detailed information about the topic
Supervisor
For informal enquiries, feel free to contact the supervisor directly.
prof. Jakub Langhammer, Ph.D. (jakub.langhammer@natur.cuni.cz)
Thesis language
English / Czech
Keywords
Hydrology · Machine Learning · Hydrological Extremes · Transferability · Experimental Catchments · Sensor Networks
Motivation
Hydrological machine learning models often perform well where they are trained – but do they truly generalise?
How transferable are machine-learning models across catchments, scales, and monitoring conditions? Can data-driven hydrological models reliably predict extremes in ungauged or data-scarce basins?
We are seeking a motivated PhD candidate to address one of the emerging frontier questions in hydroinformatics: the transferability of machine-learning models for hydrological extremes.
The project addresses a central challenge in modern hydrology: understanding the generalisation and transferability of ML models beyond the environments where they are trained. The research will investigate how models developed in well-instrumented experimental catchments can be transferred to ungauged mountain and headwater basins, with an emphasis on flood and drought extremes.
Scientific vision
The PhD will combine experimental hydrology and data science to explore three core dimensions of model generalisation:
- transfer across catchments with contrasting physiography,
- transfer across spatial and temporal scales,
- dependence of predictability on monitoring network structure and data availability.
The candidate will work with unique high-frequency datasets from dense hydrological sensor networks operated in experimental mountain basins by Charles University, complemented by long-term observations, remote sensing products, and physiographic descriptors.
The goal is not only improved prediction, but also a deeper understanding of the limits, robustness, and physical consistency of data-driven hydrological models.
Candidate profile
We encourage applications from candidates with backgrounds in:
- hydrology or physical geography,
- Earth or environmental sciences,
- geoinformatics,
- data science, statistics, or related quantitative fields.
The ideal candidate demonstrates a strong interest in the research topic, scientific curiosity, and motivation to engage with interdisciplinary challenges at the interface of hydrology and data science. We value candidates who are eager to learn new concepts and methodologies, critically reflect on results, and develop innovative research approaches.
Applicants should be able to work independently and proactively, while contributing constructively to a collaborative and international research environment. Programming skills (Python) and prior experience with machine learning are advantageous but not required; willingness to acquire these skills during the PhD is expected.
Research environment
The position is hosted by the Hydrology Research Group, Faculty of Science, Charles University (Prague) — an internationally active group working on experimental catchments, sensor networks, hydrological extremes, and data-driven modelling. The PhD is conducted in collaboration with the T. G. Masaryk Water Research Institute (Prague), linking fundamental research with applied water management.
What we offer
- a fully funded doctoral position,
- access to unique experimental hydrological datasets,
- publication-oriented research with international visibility,
- conference participation and international collaboration,
- a friendly and vibrant research environment in Prague.
Prospective candidates are encouraged to contact the supervisor before submitting a formal application.
Supervisor agreement
Before submitting a formal PhD application, candidates must obtain the supervisor’s consent.
To request this consent, applicants must contact the supervisor and submit the required materials (CV and motivation letter) via the designated form no later than March 31, 2026. The form requires login using a Google account.
All submitted materials will be carefully reviewed by early April. Applicants will be informed about the results shortly thereafter. Candidates who best meet the criteria will be invited for an interview in mid-April.
Following a successful interview, selected candidates will be eligible to submit a formal PhD application through the Charles University Study Information System (SIS).
The official deadline for submitting the formal application via the Charles University Study Information System (SIS) is April 30, 2026.
Binding information and official application via SIS
Important dates
- Deadline for requesting supervisor consent (CV + motivation letter via Google form): March 31, 2026
- Interviews: mid-April 2026
- Official application deadline (via Charles University Study Information System): April 30, 2026
- Expected start date: October 1, 2026
