Skillful prediction of Meiyu onset using diabatic heating over Southeast Asian low-latitude highlands

Advancing oceanographic forecasts in the Bay of Bengal: an AI-based spatiotemporal prediction for SST and MLD

A deep-learning model based on ConvLSTM to forecast SST and MLD in the Bay of Bengal for up to four weeks ahead contributes to improved ocean variable forecasting and demonstrates potential for ISMR prediction and disaster management.

Subseasonal predictability of the Bay of Bengal summer monsoon onset tied to three-ocean sea surface temperature anomalies

Multi-model assessment of East Asian Winter Monsoon predictions: upper- and lower-tropospheric pathways of ENSO impacts

Capturing Typhoon Rapid Intensification and Abrupt Recurvature Using an IAU‐Based 4DVar Scheme

Dynamic imbalances in model initialization severely constrain the predictability of the rapid intensification (RI) and abrupt track recurvature of tropical cyclones (TCs). In this study, the effectiveness of an incremental analysis update (IAU)‐based four‐dimensional variational (4DVar) data assimilation scheme in fore...

Assessing Physics-Informed Neural Networks in Streamflow Predictions for Tropical Monsoonal Basins in Sri Lanka

Globally, escalating floods and droughts demand accurate streamflow prediction for effective water management and early warning. Yet, this remains challenging in tropical monsoon regions. Traditional process-based models (e.g., HEC-HMS) underperform given extensive data needs, while purely data-driven models (e.g., LST...

How ocean thermal structure and atmospheric steering govern typhoon evolution: evidence from interpretable machine learning

This study develops a tree-based framework for simultaneous multi-step prediction of typhoon trajectory and intensity in Western North Pacific (WNP), and applies SHapley additive explanations (SHAP) to quantify the contribution of individual environmental drivers to each forecast.