Master’s Thesis: Robust and Uncertainty-Aware Urban Land-Cover Mapping at Property Scale
- Application deadline
- Mon 30 November 2026
This master’s thesis project involves using AI, aerial imagery, and GIS data to develop robust and uncertainty-aware methods for urban land-cover mapping at the property scale. The goal is to improve the reliability of climate and biodiversity planning by creating detailed land-cover maps that can be used for urban heat, permeability, and water runoff assessments. The project builds on existing models, data, and mapping workflows, and explores methods to enhance model robustness under challenging conditions such as seasonal changes, shadows, and tree canopies.
The thesis can be carried out in Stockholm, Gothenburg, or Malmö, Sweden. It is a hybrid position with flexible start dates and is part of the Krontech research project, which involves collaboration with IVL Swedish Environmental Research Institute and its project partners.
Key qualifications:
- Experience in programming in Python.
- Experience in training and using neural networks.
- Experience with computer vision, semantic segmentation, GIS, remote sensing, PyTorch, QGIS, GeoPandas, GDAL, or rasterio is beneficial.
Deadline: November 30th, 2026
