Research at PaCE

We build transparent, data‑driven methods to forecast conflict risk. Explore our publications and methods.

Methodology Publications Dissemination

Methods at a glance

We combine transparent statistical models with event, financial, and geospatial data to forecast conflict fatalities over 1–6 month horizons.Read more

Featured publication

Structured Pixels: Satellite Imagery as the Cause in Causal Effect Estimation

Lu C & Chadefaux T — Hawaii International Conference on System Sciences, 2025
Paper
Highlights
  • Peer‑reviewed venue
  • Recent (2025)
  • See details on Publications
Featured publication

Endogenous conflict and the limits of predictive optimization

Chadefaux T & Schincariol T — EPJ Data Science, 2025
Paper
Highlights
  • Peer‑reviewed venue
  • Recent (2025)
  • See details on Publications
See all publications

Data & Code

Forecast datasets

Monthly country and sub‑national forecasts with uncertainty, CSV and JSON.

Methods & docs

Modeling notes, evaluation metrics, and design decisions.

Code on GitHub

Open‑source repos and notebooks from the lab.

Impact & updates

  1. 2026-01
    HICSS presentation on Structured Pixels (GeoAI causal methods)
  2. 2025-10
    Forecasts refresh with improved uncertainty calibration
  3. 2025-07
    DTW evaluation study on conflict trajectories
Also see