Regional monitoring networks in Senegal are crucial for agricultural yield measurement and policy development. However, their effectiveness varies due to methodological challenges. A time-series forecasting model was applied to historical agricultural yield data from the region. The model incorporates autoregressive integrated moving average (ARIMA) methodology, accounting for potential seasonality and autocorrelation in yields. Uncertainty around model predictions is quantified using standard error estimates. The ARIMA model demonstrated a significant improvement in forecasting accuracy compared to simple trend-line regression models, particularly evident in the consistent prediction of yield fluctuations over multiple seasons (-). The evaluation highlights the importance of robust time-series analysis for enhancing agricultural monitoring systems. Further research should focus on validating model assumptions and expanding coverage to include more regions within Senegal. Agricultural Monitoring, Yield Improvement, Time-Series Forecasting, ARIMA Model The empirical specification follows Y=₀+^ X+, and inference is reported with uncertainty-aware statistical criteria.
Sow et al. (Sat,) studied this question.