Zhiyao Song

The integration of multi-source sensors based AIoT (Artificial Intelligence of Things) technologies into air quality measurement and forecasting is becoming increasingly critical in the fields of sustainable and smart environmental design, urban development, and pollution control. This study focuses on enhancing the prediction of emission, with a special emphasis on pollutants, utilizing advanced deep learning (DL) techniques. Recurrent neural networks (RNNs) and long short-term memory (LSTM) neural networks have shown promise in predicting air quality trends in time series data. However, challenges persist due to the unpredictability of air quality data and the scarcity of long-term historical data for training. To address these challenges, this study introduces the AIoT-enhanced EEMD-CEEMDAN-GCN model. This innovative approach involves decomposing the input signal using EEMD (Ensemble Empirical Mode Decomposition) and CEEMDAN (Complete Ensemble Empirical Mode Decomposition with Adaptive Noise) to extract intrinsic mode functions. These functions are then processed through a GCN (Graph Convolutional Network) model, enabling precise prediction of air quality trends. The model’s effectiveness is validated using air pollution datasets from four provinces in China, demonstrating its superiority over various deep learning models (GCN, EMD-GCN) and series decomposition models (EEMD-GCN, CEEMDAN-GCN). It achieves higher accuracy and better data fitting, outperforming other models in key metrics such as MAE (Mean Absolute Error), MSE (Mean Squared Error), MAPE (Mean Absolute Percentage Error), and R² (Coefficient of Determination). The implementation of this AIoT-enhanced model in air pollution prediction allows decision-makers to more accurately anticipate changes in air quality, particularly concerning carbon emissions. This facilitates more effective planning of mitigation measures, improvement of public health, and optimization of resource allocation. Moreover, the model adeptly addresses the complexities of air quality data, contributing significantly to enhanced monitoring and management strategies in the context of sustainable urban development and environmental conservation.

In this study, we propose a two-parameter symmetric tropical cyclone (TC) pressure model, derived from the fundamental equations of the TC wind field. This model rectifies the deficits of the traditional TC pressure model mathematically. It incorporates a new parameter into the Holland pressure model and establishes relationship equations between the new parameter, Holland parameter B, and TC attributes such as pressure difference, maximum wind speed radius, geographical latitude, and inflow angle. This derivation is achieved theoretically. Our model not only tackles the limitations of the traditional pressure model by meeting the gradient wind equations, but it also resolves the uncertainty issue of parameter B arising from varied factor selection, data time frames, and research maritime areas. As practical applications, we apply both this model and the corresponding wind field model to five TC profiles. Further, we juxtapose them with primary pressure and wind field models and conduct error and statistical significance analyses. Our findings reveal that the two-parameter model produces results on par with the Holland model and superior to Fujita and Takahashi models. Notably, reanalysis of the wind field consistently underestimates the wind field near the maximum wind speed. Hence, a hybrid wind field, synthesized from the modeled and reanalyzed wind fields, appears to be one of the most effective methodologies for reconstructing a tropical cyclone’s wind field.

Several countries implemented prevention and control measures in response to the 2019 new coronavirus virus (COVID-19) pandemic. To study the impact of the lockdown due to COVID-19 on multiple cities, this study utilized data from 18 cities of Henan to understand the air quality pattern change during COVID-19 from 2019 to 2021. It examined the temporal and spatial distribution impact. This study firstly utilized a deep learning bi-directional long-term short-term (Bi-LSTM) model to predict air quality patterns during 3 periods, i.e., COVID-A (before COVID-19, i.e., 2019), COVID-B (during COVID-19, i.e., 2020), COVID-C (after COVID-19 cases, i.e., 2021) and obtained the R² value of more than 72% average in each year and decreased MAE value, which was better than other studies’ deep learning methods. This study secondly focused on the change of pollutants and observed an increase in Air Quality Index by 10%, a decrease in PM_2.5 by 14%, PM₁₀ by 18%, NO₂ by 14%, and SO₂ by 16% during the COVID-B period. This study found an increase in O₃ by 31% during the COVID-C period and observed a significant decrease in pollutants during the COVID-C period (PM₁₀ by 42%, PM_2.5 by 97%, NO₂ by 89%, SO₂ by 36%, CO by 58%, O₃ by 31%). Lastly, the impact of lockdown policies was studied during the COVID-B period and the results showed that Henan achieved the Grade I standards of air quality standards after lockdown was implemented. Although there were many severe effects of the COVID-19 pandemic on human health and the global economy, lockdowns likely resulted in significant short-term health advantages owing to reduced air pollution and significantly improved ambient air quality. Following COVID-19, the government must take action to address the environmental problems that contributed to the deteriorating air quality.

In order to ensure the safety of bridges and ships, non-navigable channel arresting facilities for ships have become an important part of cross-sea bridges, and the diffusion of suspended sediment caused by their implementation has an impact on seawater quality. Taking the Jintang bridge as an example, a two-dimensional tidal current and sediment numerical model was applied to predict the distribution of suspended sediment diffusion caused by the implementation of arresting facilities, in order to analyze seawater quality. We adopted a new formula for the equivalent roughness method, to generalize the bridge piers, and obtained good results. The results showed that the zone where the SSC (suspended sediment concentration) reached 10 mg/L was concentrated in the area from 4.5 km north to 6.5 km south of the arresting facility, when it was implemented near the western channel. The sea area by the main channel was concentrated within 500 m of the arresting facility. The impact of the implementation of the arresting facility on seawater quality was relatively limited. Only the protected marine area in the Zhenhai Section of the Hangzhou Bay Estuary Coastal Wetland was affected by the suspended sediment from the construction of the western channel.

This study presents an incorporation and application of a two-dimensional, unstructured-grid hydrodynamic model with a suspended sediment transport module in Daishan, China. The model is verified with field measurement data from 2017: water level, flow velocities and suspended sediment concentration (SSC). In the application on the Daishan, the performance of the hydrodynamic model has been satisfactorily validated against observed variations of available measurement stations. Coupled with the hydrodynamic model, a sediment transport model has been developed and tested. The simulations agreed quantitatively with the observations. The validated model was applied to the construction of breakwaters and docks under a different plan. The model can calculate the flow field and siltation situation under different breakwater settings. After we have analyzed the impact of existing breakwater layout schemes and sediment transport, a reasonable plan will be selected. The results show that the sea area near the north of Yanwo Shan and Dongken Shan has a large flow velocity exceeding 2.0 m/s and the flow velocity within the isobath of 5 m is small, within 0.6 m/s. According to the sediment calculation, the dock project is feasible. However, the designed width of the fairway should be increased to ensure the navigation safety of the ship according to variation characteristics of cross flow velocity in channel.