2025, Vol. 10, Issue 11, Part A

The ARIMA (Autoregressive Integrated Moving Average) model is employed in this study to examine the production trends of black gram, green gram, and red gram in Tamil Nadu for the period spanning from 1991 to 2024. A comparative assessment of these three pulse crops was carried out to understand their production patterns and forecast future trends. Time series modeling was carried out using the Box-Jenkins methodology, with ACF and PACF plots applied to determine appropriate ARIMA models. To ensure the suitability for ARIMA modeling, the stationarity of the series was examined using the Augmented Dickey-Fuller test. After identifying the appropriate models, their performance was assessed and validated using the Akaike Information Criterion (AIC) and the Schwarz Bayesian Information Criterion (SBIC). The residuals from the selected models were examined using the Box-Ljung test to confirm the absence of autocorrelation. Furthermore, the Mean Absolute Percentage Error (MAPE) was calculated to evaluate the forecasting accuracy of the models.

Based on the best-fit ARIMA models, production forecasts were generated up to the year 2029. The results demonstrate that ARIMA is a reliable and effective tool for modeling agricultural time series data, providing accurate forecasts and valuable insights into the future production trends of black gram, green gram, and red gram in Tamil Nadu.