Spatiotemporal Dynamics of Conflict Occurrence and Fatalities in Ethiopia: A Bayesian Model and Predictive Insights Using Event-level Data (1997--2024)

2025-11-02

AI Summary

This study investigates the spatiotemporal heterogeneity of conflict incidents and their fatal outcomes in Ethiopia from 1997 to 2024, aiming to support risk identification and targeted resource allocation for vulnerable communities. We propose an innovative two-level Bayesian spatiotemporal model: the first level models conflict occurrence (binary), while the second models fatality counts (count), jointly incorporating identifiable heterogeneous spatiotemporal random effects, nonlinear covariates, and Matérn Gaussian process priors. Inference is performed efficiently via Integrated Nested Laplace Approximation (INLA). Results reveal that airstrikes, shelling, and attacks exhibit the highest fatality rates; ethnic and rebel-group-led conflicts drive large-scale fatalities; multi-fatality events are more prevalent during summer months; border-proximate regions show significantly elevated violence intensity, whereas remote urban areas exhibit lower risk. The model substantially improves both predictive accuracy and mechanistic interpretability of conflict risk across space and time.

Technology Category

• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Security and Privacy: Large-scale security measurements

Abstract

This study presents a spatiotemporal dual Bayesian model that examines both the occurrence and number of conflict fatalities using event-level data from Ethiopia (1997-2024), sourced from the Armed Conflict Location and Event Data (ACLED) project. Fatalities are treated as two linked outcomes: the binary occurrence of deaths and the count of deaths when they occur. The model combines additive fixed effects for covariates with random effects capturing spatiotemporal influences, allowing for outcome-specific effects. Covariates include event type and season as categorical variables, proximity to cities and borders as nonlinear effects, and population as an offset term in the count model. A latent spatiotemporal process accounts for shared spatial and temporal dependence, with the spatial structure modeled using a Matérn field prior and inference via Integrated Nested Laplace Approximation (INLA). Results show strong spatial clustering and temporal variation in fatality risk, emphasizing the importance of modeling both dimensions for better understanding and prediction. Airstrikes, shelling, and attacks show the highest fatality likelihood and counts, while communal and rebel actors cause the most deaths. Multiple fatalities are more likely in summer, and proximity to borders drives intense violence, whereas remoteness from urban centers is linked to lower-intensity events. These results provide insight for planning, policy, and resource allocation to protect vulnerable communities.

Problem

• Modeling conflict occurrence and fatalities in Ethiopia
• Analyzing spatiotemporal patterns using Bayesian methods
• Identifying high-risk factors for violence and casualties

Innovation

• Bayesian model analyzes conflict occurrence and fatalities
• Spatiotemporal random effects capture geographical and temporal influences
• INLA inference enables efficient latent process estimation