Assessment and Prediction of Sea Level Trend in the South Pacific Region

Sea level rise is an important and topical issue in the South Pacific region needs urgent assessment of trends for informed decision making. This paper presents mean sea trend using harmonic analysis a hybrid deep learning (DL) model based on Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) technique, Convolutional Neural Network (CNN), Gated Recurrent Unit (GRU) Neighbourhood Component Analysis (NCA) to build highly accurate forecasting three small islands (Fiji, Marshall Island Papua New Guinea (PNG)) Pacific. For 20-year period, estimated per year from computation obtained: 112 mm PNG, 98 52 Fiji. The DL procedure uses climate environment-based remote sensing satellite (MODIS, GLDAS-2.0, MODIS TERRA, MERRA-2) predictor variables tide gauge base (MSL) data training development forecasting. developed CEEMDAN-CNN-GRU as objective benchmarked by comparison without decomposition, CNN-GRU standalone models, Decision Trees (DT) Support Vector Regression (SVR). All performances are evaluated reliable statistical metrics. shows superior accuracy when compared other models. It >96% correlation coefficient error <1% all study sites.