Accurate wind speed and direction data are vital for coastal engineering, renewable energy, and climate resilience, particularly in regions with sparse observational datasets. This study evaluates the ERA5 reanalysis model’s performance in predicting wind speeds and directions at ten coastal and offshore stations in Kuwait from 2010 to 2017. This analysis reveals that ERA5 effectively captures general wind speed patterns, with offshore stations demonstrating stronger correlations (up to 0.85) and higher Perkins Skill Score (PSS) values (up to 0.94). However, the model consistently underestimates wind variability and extreme wind events, especially at coastal stations, where correlation coefficients dropped to 0.35. Wind direction analysis highlighted ERA5’s ability to replicate dominant northwest wind patterns. However, it reveals notable biases and underrepresented variability during transitional seasons. Taylor diagrams and error metrics further emphasize ERA5’s challenges in capturing localized dynamics influenced by land-sea interactions. Enhancements such as localized calibration using high-resolution datasets, hybrid models incorporating machine learning techniques, and long-term monitoring networks are recommended to improve accuracy. By addressing these limitations, ERA5 can more effectively support engineering applications, including coastal infrastructure design and renewable energy development, while advancing Kuwait’s sustainable development goals. This study provides valuable insights into refining reanalysis model performance in complex coastal environments.

Marine pollution in shallow embayments is hazardous to human and marine health. This research investigates the environmental impact of sewage discharge from coastal outfalls on the semi-enclosed-shallow Doha Bay. Such a study highlights the impact of environmental stressors on the health of such bays. Also, the study assesses the spreading of the pollutant relative to the location of the pollution source. The bay is susceptible to sewage discharge as it is featured slow tidal currents leading to increased pollution concentrations within its basin. The concentrations and distributions of microbial water quality indicators (E. coli, fecal coliform, and fecal streptococci) were investigated parallel with physical and chemical water quality parameters. Water samples were collected from the outfalls and within Doha Bay for four months. The results show that the concentrations of discharged Biological Oxygen Demand (BOD), Total Suspended Solids (TSS), Total Dissolved Solids (TDS), Total Organic Carbon (COD), Nitrites (NO2−) and ammonia (NH₃) has exceeded Kuwait Environment Public Authority (KEPA) maximum limits, specifically from the outfalls J3 and J4. In addition, the microbiological parameters were significantly breaching KEPA’s guidelines. The maximum fecal coliform concentration was 3.5 × 10⁵, 2.4 × 10⁴, and 5.4 × 10³ CFU/100 ml, E. coli concentration was 2.2 × 10⁵, 1.2 × 10⁴, and 2.6 × 10³ CFU/100 ml, fecal streptococci concentration was 7.25 × 10², 4.4 × 10², and 44 CFU/100 ml, at outfalls J3, J4, and J5, respectively, indicating high microbial pollution. The fecal coliform near J3 exceeds the allowable limits of KEPA by more than 600 times. Laboratory results were mapped to assess the microbial indicators within the bay. Spatially, the concentration of pollutants varies and correlates proportionally with the locations of the outfalls. The highly affected area is near outfall J3: a shallow, closed area with minimal water circulation and maximum sewage discharge. Offshore locations show lower pollution concentrations, and the pollutant concentrations were highest in January 2019 and February 2019. Continuing to discharge pollutants through coastal outfalls to regions such as Doha Bay will lead to long-term consequences, including eco-social, ecological, and adverse health impacts that are complex to be treated. Therefore, the bay needs an independent, comprehensive, and reliable monitoring program to measure the environmental indicators continuously.

Creating an efficient model for predicting sea level fluctuations is essential for climate change research. This study examined the effectiveness of utilizing Artificial Neural Networks (ANNs), particularly the recurrent network approach. ANNs were chosen for their capacity to learn from extensive and intricate data and their ability to handle nonlinear correlations. The Long Short-Term Memory (LSTM) algorithm was employed to fill data gaps and predict future sea level records in the Arabian Gulf, especially in Mina Salman. The results were promising, with LSTM successfully filling a 6-year data gap while maintaining low Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE) values. The first phase of the model yielded a RMSE value of 63.4 mm and a MAPE value of 3.14%. The same approach was used to retrain the model with a mix of real and predicted values, preserving historical patterns and yearly rates with an RMSE of 66.5 mm and a MAPE of 3.07%. These findings highlight LSTM’s advantages when considering only historical information for predicting the future sea level changes. The research provides valuable insights into predicting sea level changes in regions with limited field data, such as the Arabian Gulf, and emphasizes the potential for further research to enhance sea level prediction models through improved optimization techniques.