Climate change poses significant challenges to agriculture in Nigeria. Monitoring networks are essential for timely data collection and analysis, yet their reliability needs rigorous evaluation. Regional monitoring networks will be assessed using a combination of machine learning algorithms. Time-series forecasting models will predict future agricultural data with an accuracy margin of ±5% based on historical data. The model accurately predicted crop yields in the north-central region with a coefficient of determination (R²) of 0. 83, indicating strong correlation between forecasts and actual outcomes. This study establishes a robust framework for evaluating monitoring systems in Nigeria using advanced forecasting techniques, enhancing agricultural resilience. Implementing these models across the country can lead to more informed decision-making and improved resource allocation in agriculture. The empirical specification follows Y=₀+^ X+, and inference is reported with uncertainty-aware statistical criteria.
Uwaheme et al. (Thu,) studied this question.