Violent event-related fatality patterns in Ethiopia: a Bayesian spatiotemporal perspective

2025-11-15

AI Summary

Systematic, quantitative characterization of the spatiotemporal dynamics of conflict-related fatalities in Ethiopia has long been lacking. This study develops a zero-inflated Bayesian generalized additive mixed model (ZI-BGAMM) using ACLED data, jointly incorporating spatial and temporal random effects with nonlinear covariate effects to enable high-resolution probabilistic modeling and inference of fatality risk. The methodological innovation lies in simultaneously addressing event sparsity (zero inflation) and spatiotemporal heterogeneity, thereby enabling precise identification of high-risk regions and the probability of large-scale lethal events (≥20 fatalities). Results reveal that five regional states—including Oromia and Somali—exhibit fatality probabilities exceeding 70%; Tigray shows the highest peak probability (55.8%) for single-event fatalities ≥20, though this declined significantly during 2020–2022. The framework provides an interpretable, dynamically updatable statistical foundation for conflict monitoring, early warning, and targeted intervention.

Technology Category

• Reasoning under Uncertainty: Relational Probabilistic Models
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Security and Privacy: Large-scale security measurements

Abstract

Fatalities resulting from violence in armed conflict have long been a significant public health issue in Ethiopia. Despite the severity of this problem, more comprehensive quantitative scientific studies need to be conducted to elucidate the sequence and dynamics of these occurrences. In response, this study introduces a spatio-temporal statistical method designed to uncover the patterns of fatalities associated with violent events in Ethiopia. The research employs a two-part zero-inflated Bayesian generalized additive mixed model, which integrates a spatio-temporal component to map the fatality patterns across Ethiopian regions. The dataset utilized originates from the Armed Conflict Location and Event Data Project, covering fatality counts related to violent events from 1997 to 2022. The analysis revealed that nine out of thirteen administrative regions exhibited a probability greater than 0.6 for fatality occurrence due to violent events, with five regions surpassing a 0.7 probability threshold. These five regions include Benishangul Gumz, Gambela, Oromia, Somali, and the South West Ethiopian People's Region. Notably, the Tigray region displayed the highest probability (0.558) of experiencing more than 20 deaths per violent event, followed by the Benishangul Gumz region with a probability of 0.306. Encouragingly, the findings also indicate an average decline in fatalities per violent event over time. Specifically, the probability of more than 20 deaths per event was 0.401 in 2020, which decreased to 0.148 by 2022. These insights are invaluable for the government, policymakers, political leaders, and traditional or religious authorities in Ethiopia, enabling them to make informed, strategic decisions to mitigate and ultimately prevent violence-related fatalities in the country.

Problem

• Analyzing violent conflict fatality patterns across Ethiopian regions
• Developing spatiotemporal statistical methods to map fatality distributions
• Identifying high-risk regions and temporal trends in violence deaths

Innovation

• Bayesian spatiotemporal statistical method for fatality patterns
• Two-part zero-inflated Bayesian generalized additive model
• Spatio-temporal mapping of violent event fatalities