Research
A cleaner home for ongoing projects and the field-to-model workflow behind the Biodiversity Data Lab.
Ongoing projects
Current work spans deep-learning biodiversity maps, insect diversity predictions, limits to model generalization, and automated environmental data pipelines.
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 Python package for automated environmental data retrieval in ecological modelling. The service gives users granular control over data synthesis, allowing efficient download of geospatial information from repositories including Google Earth Engine and downstream predictive modelling applications.
Measuring biodiversity
We produce comprehensive biodiversity inventories from environmental DNA and link them to spatial environmental data.
Insects are one of the most diverse and species-rich taxonomic groups, containing about half of all species that have so far been scientifically described. Insects also act as collectors of environmental DNA, because they feed from plants, fungi, and other organisms in their surroundings.
By applying Insect Malaise traps, we capture a large portion of the above-ground insect diversity, providing comprehensive DNA samples of insects as well as their gut contents and parasites.
When we think of biodiversity, we often think of charismatic animals and plants, but there is an immense hidden diversity below our feet in the soil. Soil core samplers reaching up to 40 cm below the surface help us access this hidden ecosystem.
These samples provide a glimpse into fungal, invertebrate, and plant species communities that can be found below the surface.
With approximately 13,000 wildfires in Spain each year and more than 100,000 hectares burned annually, wildfire prevention is a critical priority. Prescribed burning is a land-management strategy that removes dead biomass and reduces fuel continuity.
During a PhD stay in Spain, Monica Guilera Recoder participated in prescribed burns carried out by firefighters. See more fieldwork photographs in the gallery.
Research outputs
