1. Irene (2011) and Sandy (2012), are in the training set, the performance of all Bi-LSTM models are satisfactory, with metrics comparable to Bi-LSTM-ATT models (Table S3). Here, the goal is to predict the evolution of EWLs for relevant extreme events such as Hurricane Isabel (2003) and Dorian;contrast, the top-two transferable Bi-LSTM-ATT models achieve high KGE of 0.94 and 0.93 and NSE of 0.97 and 0.97 when predicting EWLs triggered by Hurricane Isabel (Figure 5b),2003
2. Multivariate remotely sensed and in-situ data assimilation for enhancing community WRF-Hydro model forecasting;P Abbaszadeh;Advances in Water Resources,2020
3. Att-BiL-SL: Attention-Based Bi-LSTM and Sequential LSTM for Describing Video in the Textual Formation;S Ahmed;Applied Sciences,2022