Research
Measuring, modelling, and mapping biodiversity at useful resolution.
Ongoing Projects
BIOSCANN implements a deep-learning segmentation model that integrates multiple layers of environmental data -- satellite images, airborne laser scanning, and soil information -- to identify forests of high biodiversity value in Sweden. With this approach we produce a national data product for Sweden with high-resolution biodiversity predictions.
We predict the expected insect biodiversity across Sweden at 10-m resolution using models trained on DNA data gathered from Malaise traps. The models integrate biodiversity data with high-resolution environmental layers such as land cover, vegetation structure, hydrology, and climate. This jSDM-eDNA framework delivers scalable, standardized biodiversity monitoring at management-relevant spatial resolution.
This project investigates the predictive accuracy of large-scale biodiversity models. Using a global dataset of 25,987 sites from 681 studies, we evaluate linear mixed models and Bayesian hierarchical models for alpha and beta diversity. The models are tested on interpolation and extrapolation capabilities, revealing clear limits to prediction.
A tool for downloading environmental data for sampling points or occurrence records.
envoi adds environmental data from Google Earth Engine to your sample points, such as species occurrence records, without installing anything. Upload a CSV file with your points and an Earth Engine service-account key, then choose data products, like elevation, climate, or land cover. You can get point-wise values or summary statistics within a window around it, or image raster tiles. You download them with quality checks and metadata in one ZIP file.
envoi is an open-source Python package, and the web app runs a simplified version of it. For more flexibility and larger downloads, you can run the app locally or use envoi in Python.
Research outputs
Peer-reviewed articles from the lab and its collaborators.
