PhD Candidate in Spatial Statistics for IoT and Remote Sensing Integration in Tree Crop Disease Monitoring
Develop innovative spatial statistical methods to integrate IoT sensor data, remote sensing, and in-situ observations for mapping and predicting tree crop diseases.
Best for:Best for recent MSc graduates in geoinformation science, spatial statistics, machine learning, or related fields with strong Python/R programming skills and a passion for interdisciplinary environmental research.
Overview
This PhD position at the University of Twente’s Faculty of Geo-Information Science and Earth Observation (ITC) focuses on advancing spatial statistical techniques to integrate ground-based IoT sensor data, remote sensing, and in-situ measurements. The project aims to monitor and mitigate tree crop diseases—such as cocoa’s Cocoa Swollen Shoot Virus (CSSV)—by addressing critical data integration challenges like spatial misalignment, temporal inconsistencies, and data quality issues. The successful candidate will collaborate with farmers in Ghana to deploy IoT sensor networks, analyze complex environmental interactions, and evaluate model transferability across economically important tree crops. The role emphasizes interdisciplinary research, fieldwork, and contributions to open science and knowledge dissemination.
What you'll do
- Develop spatial statistical methods to integrate IoT sensor data, remote sensing, and in-situ observations for mapping cocoa disease trends.
- Design and deploy IoT sensor networks in cocoa farms in Ghana, addressing spatial/temporal misalignments and data quality issues.
- Analyze complex interactions between above-ground and below-ground biotic/abiotic factors affecting tree crop health.
- Evaluate model transferability by comparing findings with other economically important tree crops in Dutch food forests.
- Collaborate with project partners and societal stakeholders to disseminate research findings and promote open science practices.
- Contribute to teaching and mentoring MSc students in spatial modeling and environmental systems.
- Publish research outcomes in peer-reviewed journals and present findings at international conferences.
Requirements
Degree required: Master’s degree in geoinformation science, earth observation, spatial statistics, spatial and spatiotemporal modeling, or a related quantitative field.
Degree offered: PhD
Language: English; proficiency at a level suitable for academic research and collaboration (no explicit test score required).
Instruction: English
- Proven expertise in spatial statistics, geostatistics, or machine learning for environmental data analysis.
- Strong programming skills in Python or R for data analysis and modeling.
- Experience handling multi-temporal and multi-spatial datasets (e.g., earth observation, IoT, in-situ data).
- Familiarity with fieldwork and sensor deployment in agricultural or ecological settings.
- Excellent command of English for academic communication and collaboration.
- No explicit nationality or residency restrictions mentioned.
- Open to all applicants meeting academic and skill requirements.
Funding & terms
How to apply
Deadline: 2026-10-31
Submit a one-page motivation letter, CV (including course grades, references, and publications if applicable), and a written example of scientific work (e.g., MSc thesis or report) via email. First-round interviews will be held in November 2026, with a potential second round in December.
- Motivation letter (1 page max)
- Curriculum Vitae (with course history, grades, reference contacts, and publication list if applicable)
- Written example of scientific work (e.g., MSc thesis, report, or article)
Contact
Frank Osei / Wieteke Willemen· Supervisors
Create a free profile to unlock your personal match score, the full requirements, funding details and how to apply — in English or Persian.