Offer Description
Monitoring reforestation success in semi-arid regions is crucial for combating land degradation and climate change. Traditional monitoring methods are labor-intensive and lack scalability. This project aims to overcome these challenges by leveraging high-resolution drone and satellite imagery, combined with advanced machine learning algorithms, to develop spatially explicit models of reforestation success. The goal is to create AI models that accurately estimate tree counts, biomass dynamics, and biodiversity, supporting effective and scalable reforestation efforts.
Responsibilities:
Data Collection & Integration: Acquire, preprocess, and integrate high-resolution datasets from drone and multispectral satellite imagery, ensuring data quality and consistency. Conduct fieldwork in Senegal in collaboration with Lignaverda.
AI Model Development: Design, refine and train deep learning models to extract tree counts, biodiversity indicators, and biomass estimates from high-resolution imagery. Validate models with ground-truth data.
Scalability & Validation: Assess model robustness across different spatial scales, conducting sensitivity analyses to simulate satellite imagery conditions and test upscaling potential.
Research & Dissemination: Publish findings in high-impact scientific journals and present results at conferences.
Collaboration & Supervision: Work closely with interdisciplinary research teams, co-supervise MSc students, and contribute to the research environment.
Where to apply Website
Requirements
Research Field Computer science Education Level Master Degree or equivalent
Research Field Environmental science Education Level Master Degree or equivalent
Languages ENGLISH Level Good
Additional Information
Benefits
What We Offer:
A fully funded 4-year PhD position within a dynamic and internationally recognized research environment under supervision of 4 (co-)promoters with diverse research expertise.
Opportunities to work with top research groups at KU Leuven, including Earth and Environmental Sciences and Electrical Engineering (ESAT).
Hands-on experience with AI-driven remote sensing technologies and real-world applications.
Fieldwork opportunities in Senegal in collaboration with Lignaverda.
Access to state-of-the-art research facilities and resources.
Support for publishing in leading scientific journals and attending international conferences.
A vibrant academic community in Leuven, a historical university town at the heart of Western Europe.
Eligibility criteria
We are looking for a highly motivated candidate with:
Master’s degree in environmental science, remote sensing, computer science, AI/deep learning, or a related discipline.
A strong background in quantitative data analysis and programming, with (the ability to develop) expertise in machine learning, deep learning, and image processing.
Proficiency in coding (e.g. Python). Experience with deep learning frameworks (e.g., TensorFlow, PyTorch) is an asset.
Excellent analytical and problem-solving skills.
Strong written and verbal communication skills in English.
Interest in interdisciplinary research, including fieldwork and collaboration across AI, remote sensing, and ecology.
Candidates who do not yet have experience in deep learning or image processing but have a strong analytical background and the ability to acquire these skills are encouraged to apply.
Selection process
For more information please contact Prof. dr. Stef Lhermitte, mail: .
Interested candidates should submit the following documents: – Resume (including transcripts of grades and, if possible, a link to the PDF of their MSc thesis). – Motivation Letter, explicitly stating the earliest possible start date. – References: Provide names and contact details of two referees (no reference letters required at this stage).
While the application deadline is strict, we remain open to later starting dates for outstanding candidates who may become available at a later time.
You can apply for this job no later than 30/04/2025 via the
Work Location(s)
Number of offers available 1 Company/Institute KU Leuven Country Belgium State/Province Vlaams Brabant City Leuven Postal Code 3000 Street Leuven Geofield
Contact State/Province
Leuven City
Vlaams Brabant Street
Leuven Postal Code
3000 E-Mail
[email protected]
STATUS: EXPIRED
Share this page
EURAXESS
You must sign in to apply for this position.