Using a regional climate model and a machine learning algorithm for farmer-herder conflict prediction in the Sahel region

Climate variability and environmental stress are increasingly recognized as important factors influencing conflict dynamics in vulnerable regions. This study examines the relationship between climate variability and conflict risk in the Sudano–Sahelian region of northern Nigeria by integrating regional climate modeling and machine learning techniques. High-resolution climate projections were generated using the Weather Research and Forecasting (WRF) regional climate model to simulate key climate variables, including precipitation, temperature, and soil moisture conditions. These climate outputs were used to construct environmental stress indicators such as rainfall anomalies, drought frequency, and the Standardized Precipitation Index (SPI). Historical conflict event data obtained from the Armed Conflict Location and Event Data (ACLED) project and the Uppsala Conflict Data Program (UCDP) were combined with climate variables and socioeconomic indicators to train predictive machine learning models. The results indicate that drought severity, rainfall variability, and soil moisture deficits are among the strongest predictors of conflict risk in the study region. Among the machine learning algorithms tested, the Random Forest model demonstrated the highest predictive accuracy, achieving an Area Under the Curve (AUC) of approximately 0.86, outperforming traditional regression-based approaches. Spatial prediction maps reveal several conflict hotspots across the northern parts of the Sudano–Sahelian region where climate stress and population pressure are particularly high. The findings suggest that climate-induced environmental stress may intensify competition over land and water resources, thereby increasing the likelihood of resource-based conflicts, particularly between farming and pastoral communities. By combining regional climate modeling with machine learning-based predictive analytics, this study provides a novel framework for understanding and forecasting climate-related conflict risks in climate-sensitive regions. The results highlight the potential of integrating climate science and data-driven conflict prediction methods to support climate–conflict early warning systems and inform proactive policy interventions aimed at strengthening resilience and conflict prevention in the Sahel and similar vulnerable regions.