An Improved Prediction of Indian Summer Monsoon Onset From State-of-the-Art Dynamic Model Using Physics-Guided Data-Driven Approach

Abstract

Prediction of Indian Summer Monsoon onset, which marks the beginning of the South Asian monsoon, has significant implications on monsoon characteristics and subsequent nationwide agricultural planning. Here we make the most skillful prediction of monsoon onset with a physics-guided data-driven model integrated with the operational monsoon prediction by Coupled Forecast System version 2. Drivers of the variability of onset, which are well simulated by Coupled Forecast System version 2, viz., tropical Pacific sea surface temperature, reversal of tropospheric temperature gradient and strengthening of westerlies over AS during the early summer are identified as potential predictors. Data-driven method, Least Absolute Shrinkage and Selection Operator, makes the final selection of predictors for the linear regression model of onset. We obtain an improved correlation of 0.6 between simulated and observed onset dates with the proposed integrated statistical dynamical model as compared to 0.44 obtained with the operational dynamic monsoon prediction model.