Northwestern Nigeria, a semi-arid Sahelian environment, is highly vulnerable to rainfall variability due to its strong dependence on rain-fed agriculture. This study evaluated the predictive capability of Artificial Neural Network (ANN) and Random Forest (RF) machine learning models in forecasting annual rainfall variability and aggregate cereal crop yields using some large-scale climate oscillation indices, specifically the El Niño-Southern Oscillation (ENSO), North Atlantic Oscillation (NAO), and the Atlantic Multi-decadal Oscillation (AMO). Historical data (2000-2024) were sourced from the National Aeronautics and Space Administration (NASA) Prediction of Worldwide Energy Resource (POWER) database for rainfall, the National Agricultural Extension and Research Liaison Services (NAERLS) for crop yields, and the National Oceanic and Atmospheric Administration (NOAA) for climate indices. Data preprocessing included temporal aggregation, normalisation, and quality control procedures before model development. The models were trained and validated using a chronological 80:20 data split, while predictive performance was evaluated using the coefficient of determination (R2), Mean Squared Error (MSE), and Mean Absolute Error (MAE). Results showed that the ANN model achieved slightly superior rainfall prediction performance (R² = 0.811; MAE = 101.82 mm), while the RF model produced higher predictive accuracy for aggregate cereal crop yields (R² = 0.893; MAE = 0.04375 T/Ha). The findings demonstrate the effectiveness of machine learning approaches in modelling complex climate-crop interactions across northwestern Nigeria. However, limitations associated with the relatively short temporal dataset and the exclusion of agronomic variables are acknowledged. The study highlights the potential application of machine learning models in climate-informed agricultural forecasting, early warning systems, and climate adaptation planning within vulnerable semi-arid regions.
I. A. Tanko, T. Yahaya, Aishetu Abdulkadir et al.· Kaduna Journal of Geography· 0 citations
The savanna ecological zones of Nigeria are vulnerable to eco-climatic anomalies driven by climate change and land degradation. Despite previous studies on individual climate stressors, few have developed sub-national spatial Eco-Climatic Resilience Indices (ECRI) that integrate both biophysical and socio-economic dimensions across the region, thereby limiting targeted climate adaptation planning. This study applied Mann–Kendall rainfall trend analysis and the Sen slope test to rainfall data acquired from the Nigeria Meteorological Agency (NIMET) across 19 stations from 1971 to 2023. A four-stage cluster sampling design was employed to sample 2400 farming households from 48 communities in the study regions. A Principal Component Analysis (PCA) was applied to reduce the dimensionality of the data from 46 variables across climatic anomalies, ecological anomalies, exposure, sensitivity, adaptation capacity, and transformative adaptation capacity. Community PCA scores were interpolated and integrated into the composite ECRI, which was then classified into five resilience zones. The findings revealed a spatial mixed trend in rainfall as stations in the Sudan-Sahelian savanna showed both significant and insignificant upward trends, with the highest rate of change recorded in Kano (+17.89 mm/year), while stations in the Guinea Savanna indicated a significant and insignificant downward trend, with the highest rate of change recorded in Makurdi (−26.43 mm/year). Although the stations in the Sudan-Sahelian showed upward rainfall trends, the ECRI map depicted a north–south resilience gradient, with very low resilience across the Sahelian savanna to the north and very high resilience across the Guinea Savanna to the south. Overall, the climate and ecological stressors were strongly related (r = 0.82). These findings imply that increased rainfall does not necessarily translate into improved climate resilience. The varying resilience levels depicted by ECRI signal the need for state and location-specific transformation/adaptation strategies to build individual, community, and state capacity for more resilient livelihoods across the study region and similar regions with comparable socio-economic and climate characteristics.
Aishetu Abdulkadir, A. Jibrin, I. Ibrahim et al.· Discover Environment· 0 citations