Rainfall is a critical determinant of agricultural productivity and water resource management in India, where approximately 60% of cultivated land relies on monsoon rains. In 2024, India recorded an average annual rainfall of 1190 mm. However, Andhra Pradesh experienced slightly below-average precipitation, receiving only 920 mm. The situation was particularly concerning in the Anantapuramu District a semi-arid and drought-prone region where the annual rainfall was limited to just 470 mm. In such vulnerable areas, timely and accurate rainfall forecasting is essential for strategic planning and sustainable agricultural practices.
This study aims to forecast monthly rainfall in the Anantapuramu district using historical data from 1988 to 2024. Three models were employed for comparison: the ARIMA (Autoregressive Integrated Moving Average) model, suitable for linear time series forecasting; the Artificial Neural Network (ANN), capable of modeling non-linear dependencies; and the Wavelet-ANN model, which combines wavelet decomposition with ANN to capture both time-frequency and non-linear patterns in the data. Model performance was evaluated using Root Mean Squared Error (RMSE) as the key metric. Among the three, the ANN model exhibited the lowest RMSE value, indicating superior prediction accuracy. These results highlight the effectiveness of ANN in improving rainfall forecasting, which is crucial for enhancing agricultural resilience and mitigating climate-related risks in drought-prone regions like Anantapuramu.
International Journal of Statistics and Applied Mathematics
