Prediction of Multi-Scalar Standardized Precipitation Index by Using Artificial Intelligence and Regression Models

Accurate monitoring and forecasting of drought are crucial. They play a vital role in the optimal functioning irrigation systems, risk management, readiness, alleviation. In this work, Artificial Intelligence (AI) models, comprising Multi-layer Perceptron Neural Network (MLPNN) Co-Active Neuro-Fuzzy Inference System (CANFIS), regression, model including Multiple Linear Regression (MLR), were investigated for multi-scalar Standardized Precipitation Index (SPI) prediction Garhwal region Uttarakhand State, India. The SPI was computed on six different scales, i.e., 1-, 3-, 6-, 9-, 12-, 24-month, by deploying monthly rainfall information available years. significant lags as inputs MLPNN, CANFIS, MLR models obtained utilizing Partial Autocorrelation Function (PACF) with level equal to 5% SPI-1, SPI-3, SPI-6, SPI-9, SPI-12, SPI-24. predicted values compared calculated multi-time scales through performance evaluation indicators visual interpretation. appraisals results indicated that CANFIS more reliable at Dehradun (3-, 12-month scales), Chamoli Tehri (1-, Haridwar Pauri 9-month Rudraprayag 6-month Uttarkashi (3-month scale) stations. MLPNN best (1- 24- month (24-month scale), (12- 24-month (12-month (9-, 24-month), scales) stations, while found be Furthermore, modeling approach can foster straightforward trustworthy expert intelligent mechanism projecting decision making remedial arrangements tackle meteorological stations under study.