We investigated coastal low‐level jets (CLLJs) over Beibu Gulf, China, during the warm season (May to July) using hourly model simulations from a mesoscale weather research and forecasting model with a 9‐km horizontal resolution. Two high‐incidence CLLJ areas were identified over Beibu Gulf: one located on the leeward side of the Annamite Range that prevailed after sunset and the second off the northwestern coast of Hainan Island that reached its maximum intensity at midnight. The upstream wind of the Annamite Range was too weak to pass over the range during the daytime due to strong turbulent mixing near the land surface of Indochina; however, due to the suppression of the turbulent mixing after sunset, the flow intensified and crossed over the Annamite Range and further formed a hydraulic jump jet downstream. In addition to advection effect from upstream, topographic blocking effect of Hainan Island contributed to the CLLJ off the northwestern coast of Hainan Island, which persisted during the day but became more prevalent at midnight. Further momentum budget analysis and sensitivity experiments indicated that the upstream inertial oscillation due to the diurnal variation in turbulence over land was the primary source of the CLLJ over the ocean. These findings reveal the primary mechanism of CLLJs over Beibu Gulf, providing insight into CLLJ formation in other coastal regions with complex mountain ranges.

We investigate coastal low‐level jets (CLLJs) in the early warm season during 2006–2011 over the Bohai Sea using a 9‐km horizontal resolution output data from the Weather Research and Forecasting model. CLLJs mainly occur in May when large‐scale low is located over land to the north and the Pacific high is located to the southeast of the study area. The occurrence of the CLLJs exhibits an obvious diurnal cycle with two different peaks: one at night, located mainly in the central region, and the other in the afternoon, located in the northern region with mountains at both eastern and western sides. A momentum budget analysis shows that inertial oscillations, triggered by land‐sea thermal contrast, results in the formation of nocturnal CLLJs in the Bohai Sea. In addition, sensitivity experiments show that the enhanced atmospheric baroclinicity, caused by unbalanced solar radiation over the western mountain of the northern region, dominates the occurrence of afternoon CLLJs in the northern area of the Bohai Sea. Besides that, the eastern topography plays a main role as barrier and, therefore, traps CLLJs by topography blocking to its western side.

Air pollution, particularly particulate matter such as PM2.5 and PM10, has become a focal point of global concern due to its significant impact on air quality and human health. Macau, as one of the most densely populated cities in the world, faces severe air quality challenges. We leveraged daily pollution data from 2015 to 2023 and hourly meteorological pollution monitoring data from 2020 to 2022 in Macau to conduct an in-depth analysis of the temporal trends of and seasonal variations in PM2.5 and PM10, as well as their relationships with meteorological factors. The findings reveal that PM10 concentrations peak during dawn and early morning, whereas PM2.5 distributions are comparatively uniform. PM concentrations significantly increase in winter and decrease in summer, with relative humidity, temperature, and sea-level atmospheric pressure identified as key meteorological determinants. To enhance prediction accuracy, a Stacking-based ensemble learning model was developed, employing LSTM and XGBoost as base learners and LightGBM as the meta-learner for predicting PM2.5 concentrations. This model outperforms traditional methods such as LSTM, CNN, RF, and XGB across multiple performance metrics.

Clouds are a significant factor in regional climates and play a crucial role in regulating the Earth’s water cycle through the interaction of sunlight and wind. Meteorological agencies around the world must regularly observe and record cloud data. Unfortunately, the current methods for collecting cloud data mainly rely on manual observation. This paper presents a novel approach to identifying ground-based cloud images to aid in the collection of cloud data. However, there is currently no publicly available dataset that is suitable for this research. To solve this, we built a dataset of surface-shot images of clouds called the SSC, which was overseen by the Macao Meteorological Society. Compared to previous datasets, the SSC dataset offers a more balanced distribution of data samples across various cloud genera and provides a more precise classification of cloud genera. This paper presents a method for identifying cloud genera based on cloud texture, using convolutional neural networks. To extract cloud texture effectively, we apply Gamma Correction to the images. The experiments were conducted on the SSC dataset. The results show that the proposed model performs well in identifying 10 cloud genera, achieving an accuracy rate of 80% for the top three possibilities.

The atmosphere exhibits variability across different time scales. Currently, in the field of atmospheric science, statistical filtering is one of the most widely used methods for extracting signals on certain time scales. However, signal extraction based on traditional statistical filters may be sensitive to missing data points, which are particularly common in meteorological data. To address this issue, this study applies a new type of temporal filters based on a one-dimensional convolution neural network (1D-CNN) and examines its performance on reducing such uncertainties. As an example, we investigate the advantages of a 1D-CNN bandpass filter in extracting quasi-biweekly-to-intraseasonal signals (10–60 days) from temperature data provided by the Hong Kong Observatory. The results show that the 1D-CNN achieves accuracies similar to a 121-point Lanczos filter. In addition, the 1D-CNN filter allows a maximum of 10 missing data points within the 60-point window length, while keeping its accuracy higher than 80% (R² > 0.8). This indicates that the 1D-CNN model works well even when missing data points exist in the time series. This study highlights another potential for applying machine learning algorithms in atmospheric and climate research, which will be useful for future research involving incomplete time series and real-time filtering.