Despite the great significance of precisely forecasting the wind speed for development of the new and clean energy technology and stable grid operators, the stochasticity of wind speed makes the prediction a complex and challenging task. For improving the security and economic performance of power grids, accurate short-term wind power forecasting is crucial. In this paper, a deep learning model (Long Short-term Memory (LSTM)) has been proposed for wind speed prediction. Knowing that wind speed time series is nonlinear stochastic, the mutual information (MI) approach was used to find the best subset from the data by maximizing the joint MI between subset and target output. To enhance the accuracy and reduce input characteristics and data uncertainties, rough set and interval type-2 fuzzy set theory are combined in the proposed deep learning model. Wind speed data from an international airport station in the southern coast of Iran Bandar-Abbas City was used as the original input dataset for the optimized deep learning model. Based on the statistical results, the rough set LSTM (RST-LSTM) model showed better prediction accuracy than fuzzy and original LSTM, as well as traditional neural networks, with the lowest error for training and testing datasets in different time horizons. The suggested model can support the optimization of the control approach and the smooth procedure of power system. The results confirm the superior capabilities of deep learning techniques for wind speed forecasting, which could also inspire new applications in meteorology assessment.

The Pacific island countries are particularly vulnerable to the effects of global warming including more frequent and intense natural disasters. Seawater inundation, one of the most serious disasters, could damage human property and life. Regional sea level rise, highest astronomic tide, vertical land motions, and extreme sea level could result in episodic, recurrent, or permanent coastal inundation. Therefore, assessing potential flooding areas is a critical task for coastal management plans. In this study, a simulation of the static flooding situation in the southwest coast of Taiwan (Tainan city) at the end of this century was conducted by using a combination of the Taiwan Digital Elevation Model (DEM), regional sea level changes reconstructed by tide gauge and altimetry data, vertical land deformation derived from leveling and GPS data, and ocean tide models. In addition, the extreme sea level situation, which typically results from high water on a spring tide and a storm surge, was also evaluated by the joint probability method using tide gauge records. To analyze the possible static flood risk and avoid overestimation of inundation areas, a region-based image segmentation method was employed in the estimated future topographic data to generate the flood risk map. In addition, an extreme sea level situation, which typically results from high water on a spring tide and a storm surge, was also evaluated by the joint probability method using tide gauge records. Results showed that the range of inundation depth around the Tainan area is 0–8 m with a mean value of 4 m. In addition, most of the inundation areas are agricultural land use (60% of total inundation area of Tainan), and two important international wetlands, 88.5% of Zengwun Estuary Wetlands and 99.5% of Sihcao Wetlands (the important Black-faced Spoonbills Refuge) will disappear under the combined situation. The risk assessment of flooding areas is potentially useful for coastal ocean and land management to develop appropriate adaptation policies for preventing disasters resulting from global climate change.

The regional sea level budget and interannual sea level changes around Taiwan and Philippines are studied using altimetry, GRACE, and in-situ hydrographic data during 1993‒2021. Results show that the average sea level trend around Taiwan and Philippines during 1993–2021 derived from the altimetric data is 3.6 ± 0.2 mm/yr. Over 2002–2021, the study shows closure of sea level budget in the eastern ocean of Taiwan and Philippines within the observed data uncertainties, and the ocean mass accounts for 88%–100% of the observed sea level rise. In contrast, the sea level budget is not closed in the western ocean of Taiwan and Philippines, probably due to the lack of complete coverage by in-situ ocean observing systems. In addition, both regional sea level anomalies and their steric component around Taiwan and Philippines exhibit pronounced interannual and decadal variabilities. The trade wind stress associated with El Niño–Southern Oscillation and Pacific Decadal Oscillation offers a compelling explanation for the interannual and decadal signals of sea level anomalies in the southern ocean of Taiwan, with negative correlations of − 0.78 to − 0.64, indicating that trade wind stress makes a negative contribution to interannual-to-decadal sea level variability. In the northwestern ocean of Taiwan, the sea level variation is strongly influenced by the local monsoon system and shallow bathymetry with an annual amplitude of 90.3 ± 2.9 mm, larger than those in other regions around Taiwan and Philippines, where ocean mass is dominant with a high correlation with the sea level (+ 0.75 to + 0.78).

This study evaluates the potential of GNSS/IMU buoys for sea surface height observations and depth datum verification. GNSS/IMU buoys were deployed alongside 34 tide gauges around Taiwan for synchronous sea surface height measurements. The collected GNSS data were processed through relative positioning and loosely coupled GNSS/IMU integration methods. Analysis revealed that the average of the means of the differences was −2.5 cm across all stations, indicating that most tide gauge datums agreed well with the GNSS/IMU buoy measurements. Significant discrepancies were observed at only a few stations, likely due to local subsidence. Notably, the Shuitou station showed a mean difference of 63.4 cm, resulting from its remarkable deviation from tidal zero since 2019, suggesting a potential datum issue. The mean of the standard deviation (STD) of the differences across the stations was 3.8 cm, with the highest STD observed at the Shuitou station (9.4 cm). These findings demonstrate that GNSS/IMU buoys can effectively complement tide gauge measurements for observing sea surface heights and defining the depth datum, particularly in areas where local vertical land movements affect tide gauge data accuracy.

Rapid sea level rise, a severe consequence of global warming, could significantly damage the lives and properties of numerous human beings living in low-lying coastal areas. Therefore, realizing and monitoring coastal sea level variations are of great importance for human society. Conventionally, sea level heights are measured by using tide gauges; however, the records are contaminated by vertical land motions which are difficult to be separated. Recently, Global Navigation Satellite System Reflectometry (GNSS-R) technology has been proved to effectively monitor the coastal sea level changes from GNSS signal-to-noise ratio (SNR) data. However, the generation of detrended SNR ( SNR) depending on different satellite elevation angle intervals via a quadratic fitting, considerably influences the accuracy of sea level retrievals. Moreover, the quadratic fitting cannot perfectly describe the trend of SNR data. Therefore, we proposed a method combining ensemble empirical mode decomposition (EEMD) and ocean tide model to compute SLHs. EEMD can decompose the original SNR data into several intrinsic mode functions (IMFs) corresponding to specific frequencies. Then, Lomb-Scargle Periodogram (LSP) is applied to calculate the dominant frequency of the IMF with maximum spectral power. EEMD is not only suitable for dealing with nonlinear and nonstationary data but also eliminates the mode mixing problem of empirical mode decomposition (EMD) by adding white noises. In addition, we set an empirical SLH interval from ocean tide model as a quality control. In this study, the existing GNSS stations at the coasts of Taiwan are used to examine the proposed approach and then compare the results with those from the traditional quadratic fitting. Finally, the measurements from co-located or nearby traditional tide gauges are served as ground truth to evaluate the accuracy and stability of the mentioned methods.