Sea Surface Temperature (SST) is of great importance to study several major phenomena due to ocean interactions with other earth systems. Previous studies on SST based on statistical inference methods were less accurate for longer prediction lengths. A considerable number of studies in recent years involve machine learning for SST modeling. These models were able to mitigate this problem to some length by modeling SST patterns and trends. Sequence analysis by decomposition is used for SST forecasting in several studies. Ensemble Empirical Mode Decomposition (EEMD) has been proven in previous studies as a useful method for this. The application of EEMD in spatiotemporal modeling has been introduced as Multidimensional EEMD (MEEMD). The aim of this study is to employ fast MEEMD methods to decompose the SST spatiotemporal dataset and apply a Convolutional Long Short-Term Memory (ConvLSTM)-based model to model and forecast SST. The results show that the fast MEEMD method is capable of enhancing spatiotemporal SST modeling compared to the Linear Inverse Model (LIM) and ConvLSTM model without decomposition. The model was further validated by making predictions from April to May 2023 and comparing them to original SST values. There was a high consistency between predicted and real SST values.

The frequency of extreme wave events is increasing with climate change. The temporal and spatial variations of extreme wave height affect both human livelihood and the usage of ocean resources. The South China Sea and northern Indian Ocean both support coastal communities of high population density, with varied terrain structures and extreme wind and wave systems. This study focuses on the temporal and spatial variations of the extreme significant wave height in the South China Sea and northern Indian Ocean. Using nonstationary generalized extreme value analysis, trends for a 100-year return period of significant wave height were obtained for both. The most rapid increase in the 100-year return was found to be 0.015 m yr-1 in the northern South China Sea and in the Arabian Sea; however, the 100-year return significant wave height fell in the mouth of the Bay of Bengal. After analyzing the possible causes and influence factors, we found that the increase in significant wave height in the northern South China Sea was dominated by local wind-waves and similarly, the Arabian Sea was affected by swell. The NINO3.4 index shows good correlation with the significant wave height in the northern South China Sea because typhoons are related to NINO3.4 in this area. The trends of the extreme wave height in the Arabian Sea and southern Bay of Bengal have good correlations with the South Asian summer monsoon index.

The characteristics of local surface wind are closely related to the assessment of wind power resources and the oscillation period of offshore wind turbines. In this research, we analyzed near-surface wind observation data from the southern coast of Sri Lanka, comparing the surface wind variation characteristics across different seasons. Through spectral analysis, we discuss the wind stability and oscillation period, aiming to provide information for the management strategies and oscillation issues of offshore wind turbines in the North Equatorial Indian Ocean to ensure their stable operation. Our findings showed that the Indian summer monsoon dominated the seasonal surface wind variation in the southern coast of Sri Lanka. The local monsoon period began in mid-May and ended in mid-October, during which stable southwest winds prevailed with an average maximum 10 m wind speed exceeding 6.0 m/s. In contrast, surface wind was unstable and weaker during autumn and winter. The surface wind speed exhibited a clear diurnal oscillation throughout the year. The wind speed power spectral density exhibited clear peaks at periods of 24 h, 12 h, and 6 h.

This study addresses the issues of sparse observations from buoys in the tropical Indian Ocean and systematic biases in reanalysis products by proposing a daily-mean wind speed reconstruction framework that integrates multi-source meteorological fields. This study also considers the impact of different source domains on model pre-training, with the goal of providing reliable data support for wind energy assessment. The model was pre-trained using data from the Americas and tropical Pacific buoys as the source domain and then fine-tuned on Indian Ocean buoys as the target domain. Using annual leave-one-out cross-validation, we evaluated the model’s performance against uncorrected ERA5 and CCMP data while comparing three deep reconstruction models. The results demonstrate that deep models significantly reduce reanalysis bias: the RMSE decreases from approximately 1.00 m/s to 0.88 m/s, while R² improves by approximately 8.9% and 7.1% compared to ERA5/CCMP, respectively. The Branch CNN–Transformer outperforms standalone LSTM or CNN models in overall accuracy and interpretability, with transfer learning yielding directional gains for specific wind conditions in complex topography and monsoon zones. The 20-year wind energy data reconstructed using this model indicates wind energy densities 60–150 W/m² higher than in the reanalysis data in open high-wind zones such as the southern Arabian Sea and the Somali coast. This study not only provides a pathway for constructing high-precision wind speed databases for tropical Indian Ocean wind resource assessment but also offers precise quantitative support for delineating priority development zones for offshore wind farms and mitigating near-shore engineering risks.