Investigating forced transient chaos in monsoon using Echo State Networks.

Forecasting Indian Summer Monsoon Rainfall (ISMR) is a formidable task due to its intricate variability. This study harnesses the power of machine learning (ML) to decipher the chaotic trajectory within ISMR, drawing inspiration from ML's success in predicting analogous systems. By utilizing ERA-interim data, the method dissects ISMR's chaotic nature through correlation dimension-based techniques. Employing the Lorenz-96 model on daily rainfall data, trained with an Echo State Network (ESN), the technique discerns patterns within a span of 1 model time slightly trailing its performance in other systems. This discrepancy could stem from the intricacies of observational data and the training process involving 500 initial conditions. Notably, this method achieves accuracy in slightly over 50% of cases. Despite its current limitations, this approach exhibits promise in shedding light on the chaotic behaviour enforced in ISMR. As a result, it contributes to the advancement of monsoon forecasting techniques. Plain language summary: Predicting Indian Summer Monsoon Rainfall is a challenging task because it is highly variable. This study uses machine learning to better recognize the complex chaotic patterns in ISMR, using a type of data called ERA-interim. Apply a mathematical model called the Lorenz-96 model to daily rainfall data and train it using a neural network called an Echo State Network. This method can identify patterns in ISMR with up to about 1 model time unit, which is slightly less accurate compared to its performance in predicting other systems. This difference may be due to the complexities of the data used and the training process, which involves 500 initial conditions. Importantly, this approach is successful in predicting ISMR accurately in slightly over 50% of cases. While it has some limitations, this method shows promise in helping us recognize the chaotic behaviour of ISMR and may be used in improving monsoon forecasting techniques in future. [ABSTRACT FROM AUTHOR]