Using machine learning to forecast conflict events for use in forced migration models

Abstract Forecasting the movement of populations during conflict outbreaks remains a significant challenge in contemporary humanitarian efforts. Accurate predictions of displacement patterns are crucial for improving the delivery of aid to refugees and other forcibly displaced individuals. Over the...

Full description

Saved in:
Bibliographic Details
Main Authors: Yani Xue, Thomas Schincariol, Thomas Chadefaux, Derek Groen
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-11812-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849763426594717696
author Yani Xue
Thomas Schincariol
Thomas Chadefaux
Derek Groen
author_facet Yani Xue
Thomas Schincariol
Thomas Chadefaux
Derek Groen
author_sort Yani Xue
collection DOAJ
description Abstract Forecasting the movement of populations during conflict outbreaks remains a significant challenge in contemporary humanitarian efforts. Accurate predictions of displacement patterns are crucial for improving the delivery of aid to refugees and other forcibly displaced individuals. Over the past decade, generalized modeling approaches have demonstrated their ability to effectively predict such movements, provided that accurate estimations of conflict dynamics during the forecasting period are available. However, deriving precise conflict forecasts remains difficult, as many existing methods for conflict prediction are overly coarse in their spatial and temporal resolution, rendering them inadequate for integration with displacement models. In this paper, we propose a hybrid methodology to enhance the accuracy of conflict-driven population displacement forecasts by combining machine learning-based conflict prediction with agent-based modeling (ABM). Our approach uses a coupled model that combines a Random Forest classifier for conflict forecasting with the Flee ABM—a model of the movements of refugees and internally displaced persons (IDPs). The coupled model is validated using case studies from historical conflicts in Mali, Burundi, South Sudan, and the Central African Republic. Our results demonstrate comparable predictive accuracy over traditional methods without the need for manual conflict estimations in advance, thus reducing the effort and expertise needed for humanitarian professionals to provide urgent displacement forecasts.
format Article
id doaj-art-a448a674e39d4a1599dfe95af5e650e3
institution DOAJ
issn 2045-2322
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-a448a674e39d4a1599dfe95af5e650e32025-08-20T03:05:25ZengNature PortfolioScientific Reports2045-23222025-08-0115111410.1038/s41598-025-11812-2Using machine learning to forecast conflict events for use in forced migration modelsYani Xue0Thomas Schincariol1Thomas Chadefaux2Derek Groen3Department of Computer Science, Brunel University LondonPolitical Science, Trinity College DublinPolitical Science, Trinity College DublinDepartment of Computer Science, Brunel University LondonAbstract Forecasting the movement of populations during conflict outbreaks remains a significant challenge in contemporary humanitarian efforts. Accurate predictions of displacement patterns are crucial for improving the delivery of aid to refugees and other forcibly displaced individuals. Over the past decade, generalized modeling approaches have demonstrated their ability to effectively predict such movements, provided that accurate estimations of conflict dynamics during the forecasting period are available. However, deriving precise conflict forecasts remains difficult, as many existing methods for conflict prediction are overly coarse in their spatial and temporal resolution, rendering them inadequate for integration with displacement models. In this paper, we propose a hybrid methodology to enhance the accuracy of conflict-driven population displacement forecasts by combining machine learning-based conflict prediction with agent-based modeling (ABM). Our approach uses a coupled model that combines a Random Forest classifier for conflict forecasting with the Flee ABM—a model of the movements of refugees and internally displaced persons (IDPs). The coupled model is validated using case studies from historical conflicts in Mali, Burundi, South Sudan, and the Central African Republic. Our results demonstrate comparable predictive accuracy over traditional methods without the need for manual conflict estimations in advance, thus reducing the effort and expertise needed for humanitarian professionals to provide urgent displacement forecasts.https://doi.org/10.1038/s41598-025-11812-2Agent-based modelingMachine learningRandom forestMigrationSimulation
spellingShingle Yani Xue
Thomas Schincariol
Thomas Chadefaux
Derek Groen
Using machine learning to forecast conflict events for use in forced migration models
Scientific Reports
Agent-based modeling
Machine learning
Random forest
Migration
Simulation
title Using machine learning to forecast conflict events for use in forced migration models
title_full Using machine learning to forecast conflict events for use in forced migration models
title_fullStr Using machine learning to forecast conflict events for use in forced migration models
title_full_unstemmed Using machine learning to forecast conflict events for use in forced migration models
title_short Using machine learning to forecast conflict events for use in forced migration models
title_sort using machine learning to forecast conflict events for use in forced migration models
topic Agent-based modeling
Machine learning
Random forest
Migration
Simulation
url https://doi.org/10.1038/s41598-025-11812-2
work_keys_str_mv AT yanixue usingmachinelearningtoforecastconflicteventsforuseinforcedmigrationmodels
AT thomasschincariol usingmachinelearningtoforecastconflicteventsforuseinforcedmigrationmodels
AT thomaschadefaux usingmachinelearningtoforecastconflicteventsforuseinforcedmigrationmodels
AT derekgroen usingmachinelearningtoforecastconflicteventsforuseinforcedmigrationmodels