Location
Job description
Some features of our web site require JavaScript to function properly. Please enable JavaScript in your browser.
Position
Assistant Professor
Employer
Tara .D,E
TU Delft is an equal-opportunity employer and values diversity. We encourage applications from all qualified individuals regardless of gender, race, nationality, age, religion, or disability. We are committed to creating an inclusive environment where every researcher can thrive.
Homepage: https://link.springer.com/article/10.1007/s10064-026-05069-w
Location
H, Netherlands
Sector
Academic
Relevant divisions
Geodesy (G)
Geodynamics (GD)
Natural Hazards (NH)
Type
Full time
Level
Experienced
Salary
3059 - 3881 € / Year
Preferred Education
Master
Application deadline
Open until the position is filled
Posted
27 June 2026
Job Description
PhD Position in AI-Driven Landslide Susceptibility Mapping Using Deep Learning & Remote Sensing
Delft University of Technology (TU Delft), The Netherlands
About The Position
We are inviting applications for a fully-funded PhD position in the field of Natural Hazard Modeling, focusing on landslide susceptibility assessment through the integration of advanced machine learning, deep learning architectures, and multi-source remote sensing data.
This position is hosted at the Faculty of Civil Engineering and Geosciences, TU Delft – one of Europe's top-ranked universities in earth sciences, geomatics, and environmental engineering. You will work under the direct supervision of Prof. [Your Last Name] and join a dynamic, internationally recognized research group working at the intersection of geohazards, artificial intelligence, and spatial data science.
Research Context and Objectives
Landslides are among the most destructive and recurrent natural hazards worldwide, causing thousands of fatalities and billions of euros in economic losses annually. Despite significant advances in susceptibility mapping, traditional statistical models often fail to capture the complex, non-linear interactions between topographic, geological, hydrological, and climatic triggering factors.
This PhD project aims to push the boundaries of current methodologies by:
The ultimate goal is to produce a transferable AI-based workflow that can be applied to data-scarce regions, contributing to safer infrastructure planning and disaster risk reduction.
Key Responsibilities
As a PhD Candidate, You Will
We are looking for a highly motivated candidate with the following profile:
Essential
Desirable (Not Mandatory But a Plus)
What We Offer
How to apply
How to Apply
If you are excited about this opportunity, please submit your application via email to:
rfsdeepai@gmail.com
Your Application Must Include (in a Single PDF File)
Important: Please use the subject line: "PhD Application – Landslide AI – [Your Full Name]"
Application Deadline
Applications will be reviewed on a rolling basis, and the position will remain open until filled. However, for full consideration, we encourage you to submit your application as soon as possible. The preferred starting date is January 2027 (flexible).
Equal Opportunity Statement
Go back
Position
Assistant Professor
Employer
Tara .D,E
TU Delft is an equal-opportunity employer and values diversity. We encourage applications from all qualified individuals regardless of gender, race, nationality, age, religion, or disability. We are committed to creating an inclusive environment where every researcher can thrive.
Homepage: https://link.springer.com/article/10.1007/s10064-026-05069-w
Location
H, Netherlands
Sector
Academic
Relevant divisions
Geodesy (G)
Geodynamics (GD)
Natural Hazards (NH)
Type
Full time
Level
Experienced
Salary
3059 - 3881 € / Year
Preferred Education
Master
Application deadline
Open until the position is filled
Posted
27 June 2026
Job Description
PhD Position in AI-Driven Landslide Susceptibility Mapping Using Deep Learning & Remote Sensing
Delft University of Technology (TU Delft), The Netherlands
About The Position
We are inviting applications for a fully-funded PhD position in the field of Natural Hazard Modeling, focusing on landslide susceptibility assessment through the integration of advanced machine learning, deep learning architectures, and multi-source remote sensing data.
This position is hosted at the Faculty of Civil Engineering and Geosciences, TU Delft – one of Europe's top-ranked universities in earth sciences, geomatics, and environmental engineering. You will work under the direct supervision of Prof. [Your Last Name] and join a dynamic, internationally recognized research group working at the intersection of geohazards, artificial intelligence, and spatial data science.
Research Context and Objectives
Landslides are among the most destructive and recurrent natural hazards worldwide, causing thousands of fatalities and billions of euros in economic losses annually. Despite significant advances in susceptibility mapping, traditional statistical models often fail to capture the complex, non-linear interactions between topographic, geological, hydrological, and climatic triggering factors.
This PhD project aims to push the boundaries of current methodologies by:
- Developing novel hybrid deep learning frameworks (e.g., CNNs, Transformers, or Graph Neural Networks) for spatially explicit landslide prediction.
- Fusing multi-modal remote sensing data, including Sentinel-1/2, LiDAR, InSAR time-series, and high-resolution optical imagery.
- Incorporating temporal dynamics into susceptibility models to move from static maps to dynamic early-warning systems.
- Validating models using extensive field inventories and historical landslide databases from selected case-study regions.
The ultimate goal is to produce a transferable AI-based workflow that can be applied to data-scarce regions, contributing to safer infrastructure planning and disaster risk reduction.
Key Responsibilities
As a PhD Candidate, You Will
- Design, implement, and optimize state-of-the-art machine learning and deep learning pipelines for landslide susceptibility mapping.
- Process and analyze large volumes of Earth Observation (EO) data (optical, SAR, and LiDAR) using advanced remote sensing techniques.
- Develop reproducible and scalable code in Python (PyTorch/TensorFlow, GDAL, Xarray, Scikit-learn).
- Publish research findings in high-impact peer-reviewed journals (e.g., Remote Sensing of Environment, Engineering Geology, ISPRS Journal, Natural Hazards) and present at international conferences.
- Contribute to ongoing collaborations with research institutes and geological surveys in Europe and beyond.
- Participate in teaching activities (up to 10% of your time), including supervision of MSc thesis projects and assisting with relevant courses.
- Required Qualifications
We are looking for a highly motivated candidate with the following profile:
Essential
- A Master's degree (MSc) in Geoinformatics, Earth/Environmental Sciences, Computer Science, Data Science, Civil Engineering, or a closely related field (to be completed before the start date).
- Strong background in machine learning and/or deep learning, with hands-on experience in at least one major framework (PyTorch, TensorFlow, or JAX).
- Proven proficiency in Geographic Information Systems (GIS) (e.g., ArcGIS Pro, QGIS, SAGA GIS) and geospatial data handling.
- Solid experience with Remote Sensing data processing (optical, SAR, or LiDAR) using tools like SNAP, PCI Geomatica, or Google Earth Engine.
- Excellent programming skills in Python (including libraries such as NumPy, Pandas, Scikit-learn, Matplotlib, and Rasterio).
- Fluency in English (both written and spoken) – minimum IELTS 7.0 or TOEFL 100 (or equivalent).
Desirable (Not Mandatory But a Plus)
- Familiarity with InSAR time-series analysis (e.g., SBAS, PS-InSAR) and/or SAR interferometry.
- Experience with cloud computing platforms (Google Earth Engine, AWS, or Microsoft Planetary Computer).
- Knowledge of geostatistics and spatial autocorrelation methods.
- Previous publications or conference proceedings in related topics.
- Experience with version control (Git) and collaborative code development.
What We Offer
- A full-time 4-year PhD position with a competitive salary and benefits package in accordance with the Dutch Collective Labour Agreement for Universities.
- Access to state-of-the-art computational infrastructure, including GPU clusters and high-performance computing facilities.
- A vibrant, inclusive, and international working environment at TU Delft, with over 100 nationalities represented.
- Opportunities for professional development, including training in academic writing, project management, and teaching skills.
- A generous relocation package and support for international candidates, including assistance with visa arrangements and housing.
- The possibility to conduct fieldwork and international research visits with partner institutions.
How to apply
How to Apply
If you are excited about this opportunity, please submit your application via email to:
rfsdeepai@gmail.com
Your Application Must Include (in a Single PDF File)
- A detailed Curriculum Vitae (CV) – including your educational background, work experience, technical skills, publications (if any), and contact details of at least two academic referees.
- A cover letter (max 2 pages) – explaining your motivation, relevant research experience, and why you are the ideal candidate for this position. Please highlight any specific projects or courses related to landslides, AI, or remote sensing.
- Copies of MSc and BSc transcripts (in English or officially translated).
- (Optional) A link to your GitHub/portfolio showcasing relevant code or project work.
Important: Please use the subject line: "PhD Application – Landslide AI – [Your Full Name]"
Application Deadline
Applications will be reviewed on a rolling basis, and the position will remain open until filled. However, for full consideration, we encourage you to submit your application as soon as possible. The preferred starting date is January 2027 (flexible).
Equal Opportunity Statement
Go back
