High Resolution Conflict Forecasting with Spatial Convolutions and Long Short-Term Memory



The 2020 Violence Early Warning System (ViEWS) Prediction Competition challenged participants to produce predictive models of violent political conflict at high spatial and temporal resolutions. This paper presents a convolutional long short-term memory (ConvLSTM) recurrent neural network capable of forecasting the log change in battle-related deaths resulting from state-based armed conflict at the PRIO-GRID cell-month level. The ConvLSTM outperforms the benchmark model provided by the ViEWS team and performs comparably to the best models submitted to the competition. In addition to providing a technical description of the ConvLSTM, I evaluate the model’s out-of-sample performance and interrogate a selection of interesting model forecasts. I find that the model relies heavily on lagged levels of battle-related fatalities to forecast future decreases in violence. The model struggles to forecast escalations in violence and tends to underpredict the magnitude of escalation while overpredicting the spatial spread of escalation.

View the associated slides presented at ISA 2022.

View at International Interactions.

Cite this Paper (BibTeX)
@article{radford:20220316,
    author={Benjamin J. Radford},
    title={High Resolution Conflict Forecasting with Spatial Convolutions and Long Short-Term Memory},
    journal={International Interactions},
    year={2022},
    volume={},
    number={},
    pages={1--20},
    DOI={10.1080/03050629.2022.2031182}}