Biodiversity Data Lab | Uppsala University
Our Mission: Develop data-driven methods that provide insights into the distribution and dynamics of biodiversity, through integration of environmental DNA, remote sensing, and machine learning.
One focus of our group is to improve field- and lab-work protocols to produce more accurate biodiversity assessments using environmental DNA. The other focus of our group is to develop computational methods that utilize these data to help us better understand and manage the spatial distribution of biodiversity.
Our research is interdisciplinary, including the fields of ecology, environmental genetics, geomatics, bioinformatics, data science, and machine learning. If you have a background or interest in any of these fields and care about contributing with your work towards helping biodiversity, the Biodiversity Data Lab is the place for you!
We are developing and applying genetic methods to detect small traces of DNA that organisms leave behind in their habitat (environmental DNA). This provides us with comprehensive biodiversity measures of the species community at a site, which even includes the large hidden diversity of species that have not yet been scientifically described (the vast majority of species!).
In our computational models we apply high-resolution geographic data produced by different remote sensing techniques. Some examples are satellite images or 3D-point clouds from airborne laser-scanning. We use these data to correlate biodiversity measures with the complex biotic and abiotic environment. Our aim is to eventually be able to make biodiversity predictions for areas that lack biodiversity data, allowing the generation of biodiversity heat maps.
We are actively working on building state-of-the-art machine learning models to learn the complex associations of species with their environment. These models are capable to detect areas that are of high conservation value and can aid in conservation planning and selecting sites for biodiversity offsets. Further, these methods allow us to simulate the expected response of biodiversity to specific management scenarios or other factors such as climate change.
A multidisciplinary field that brings together large-scale, multidimensional data and advanced computational methods to provide new insights about biodiversity.
Featured work
A quick look at the projects that shape our current research portfolio.
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.
Lab life
Conferences, workshops, and field trips. Click a photo to browse the full set.
Get involved
We welcome students, collaborators, and visitors who want to develop better biodiversity data, models, and conservation tools.
