Modelling the Influence of Climate Variability on Vegetation Dynamics in Northern Nigeria

Northern Nigeria faces increasing vegetation stress due to changing climate extremes, yet the spatial and temporal dynamics of this relationship remain underexplored. This study aimed at modelling climate influence on vegetation dynamics in Northern Nigeria, focusing on detecting patterns and identifying key climatic drivers of vegetation change. The research utilized Normalized Difference Vegetation Index (NDVI) datasets from GIMMS AVHRR (1981 to 2015) and MODIS Terra (2000 to 2021). Climate data comprising daily precipitation and temperature (Tmin and Tmax) from 1980 to 2021 were obtained from the Nigerian Meteorological Agency (NiMet), covering ten synoptic stations across major ecological zones. NDVI data were harmonized and geo-referenced using ENVI and ArcGIS, while climate extremes were computed using RClimDex software following ETCCDI guidelines. Trend analysis was performed using the Mann–Kendall test and Coefficient of Variation (CV) to evaluate variability and direction. Machine learning models, Random Forest (RF) and Support Vector Regression (SVR), were applied to simulate NDVI responses to selected climate indices. Model performance was assessed using Root Mean Square Error (RMSE), R², and Mean Absolute Error (MAE). Findings revealed significant vegetation degradation in the Sudan and Guinea Savanna zones, particularly in years of high climate extremes (1984, 1994, 2020), while slight greening trends were noted in the Sahel. RF models achieved high accuracy (R² >0.83), with dry spells and heatwaves emerging as the most influential climate drivers of NDVI variability. In conclusion, climate extremes play a substantial role in shaping vegetation dynamics, underlining the need for targeted climate adaptation and sustainable land-use strategies in Northern Nigeria.