I have been awarded an ERC Starting Grant for the project BRIDGE, where I will study how artificial intelligence and knowledge graphs can transform the way peace and conflict data is connected, understood and used. The project will convert existing datasets, data ontologies, unstructured notes, and qualitative research claims about conflict actors and conflicts into structured knowledge graphs, and investigate how these align. The project will start January 1 2027.

In Halvard Buhaug's project POLIMPACT (ERC Advanced Grant), I am investigating how political factors integrate with economic development in the long term. The goal is to produce quantitative scenarios of governance, conflict, and economic development over the 21st century.

As part of the PSI project (RCN INFRASTRUCTUR) I am currently building PRIOGRID version 3. This version is an R-package that simplifies the process of downloading and transforming GIS data in peace and conflict research to standardized raster formats. The goal is to make a flexible tool that reduces the labor cost for researchers aiming to analyze this data, as well as to make it flexible enough to investigate assumptions related to data aggregation. Users can now easily recalculate PRIOGRID for different spatial resolutions, spatial projection and temporal resolutions. We also aim to make it simple to add new data sources to the package, and to provide pre-calculated data in easily accessible ways.

I co-hosted the VIEWS Prediction Competition (23/24) where we asked the participants to report probabilistic monthly battle-deaths forecasts at both the PRIOGRID and country level. For heavy-tailed outcomes such as battle-deaths, it is necessary to elicit more than the point forecast to sufficiently evaluate performance.

My Phd, which I defended in March 2018 was entitled "Climate, development, and conflict: Learning from the past and mapping uncertainties of the future". The main conclusion in the dissertation was that causal effects of climate variability on conflict is dependent on context and conflict type. Particularly, conflict types where organized actors challenging capable state militaries tend not to be affected. Rather, effects can be observed when violence is used for material gains in areas of limited statehood. When thinking about future effects of climate change on conflict, it is just as important to think about how the context will change as how climate exposure will change. The Phd also identify several methodological issues related to causal inference, and attempt to solve some of these.

Languages spoken:

Norwegian and English. R and Python.