A novel framework for high resolution air quality index prediction with interpretable artificial intelligence and uncertainties estimation.

Accurate air quality index (AQI) prediction is essential in environmental monitoring and management. Given that previous studies neglect the importance of uncertainty estimation and the necessity of constraining the output during prediction, we proposed a new hybrid model, namely TMSSICX, to forecast the AQI of multiple cities. Firstly, time-varying filtered based empirical mode decomposition (TVFEMD) was adopted to decompose the AQI sequence into multiple internal mode functions (IMF) components. Secondly, multi-scale fuzzy entropy (MFE) was applied to evaluate the complexity of each IMF component and clustered them into high and low-frequency portions. In addition, the high-frequency portion was secondarily decomposed by successive variational mode decomposition (SVMD) to reduce volatility. Then, six air pollutant concentrations, namely CO, SO2, PM2.5, PM10, O3, and NO2, were used as inputs. The secondary decomposition and preliminary portion were employed as the outputs for the bidirectional long short-term memory network optimized by the snake optimization algorithm (SOABiLSTM) and improved Catboost (ICatboost), respectively. Furthermore, extreme gradient boosting (XGBoost) was applied to ensemble each predicted sub-model to acquire the consequence. Ultimately, we introduced adaptive kernel density estimation (AKDE) for interval estimation. The empirical outcome indicated the TMSSICX model achieved the best performance among the other 23 models across all datasets. Moreover, implementing the XGBoost to ensemble each predicted sub-model led to an 8.73%, 8.94%, and 0.19% reduction in RMSE, compared to SVM. Additionally, by utilizing SHapley Additive exPlanations (SHAP) to assess the impact of the six pollutant concentrations on AQI, the results reveal that PM2.5 and PM10 had the most notable positive effects on the long-term trend of AQI. We hope this model can provide guidance for air quality management.

Assessment of bridge scour in the lower, middle, and upper Yangtze River estuary with riverbed sonar profiling techniques.

Riverbed scour of bridge piers can cause rapid loss in foundation strength, leading to sudden bridge collapse. This study used multi-beam echo sounders (Seabat 7125) to map riverbed surrounding the foundations of four major bridges in the lower, middle, and upper reaches of the 700-km Yangtze River Estuary (YRE) during June 2015 and September 2016. The high-resolution data were utilized to analyze the morphology of the bridge scour and the deformation of the wide-area riverbed (i.e., 5-18 km long and 1.3-8.3 km wide). In addition, previous bathymetric measurements collected in 1998, 2009, and 2013 were used to determine riverbed erosion and deposition at the bridge reaches. Our study shows that the scour depth surrounding the bridge foundations progressed up to 4.4-19.0 m in the YRE. Over the past 5-15 years, the total channel erosion in some river reaches was up to 15-17 m, possessing a threat to the bridge safety in the YRE. Tide cycles seemed to have resulted in significant variation in the scour morphology in the lower and middle YRE. In the lower YRE, the riverbed morphology displayed one long erosional ditch on both sides of the bridge foundations and a long-strip siltation area distributed upstream and downstream of the bridge foundations; in the middle YRE, the riverbed morphology only showed erosional morphology surrounding the bridge foundations. Large dunes caused deep cuts and steeper contours in the bridge scour. Furthermore, this study demonstrates that the high-resolution grid model formed by point cloud data of multi-beam echo sounders can clearly display the morphology of the bridge scour in terms of wide areas and that the sonar technique is a very useful tool in the assessment of bridge scours.

Riverbed erosion of the final 565 kilometers of the Yangtze River (Changjiang) following construction of the Three Gorges Dam.

The world's largest hydropower dam, the Three Gorges Dam (TGD), spans the upper Yangtze River in China, creating a 660-km long and 1.1-km wide reservoir upstream. Several recent studies reported a considerable decline in sediment load of the Lowermost Yangtze River (LmYR) and a rapid erosion in the subaqueous delta of the river mouth after the closure of the TGD in 2003. However, it is unknown if the TGD construction has also affected river channel and bed formation of the LmYR. In this study, we compared bathymetric data of the last 565 kilometers of the Yangtze River's channel between 1998 and 2013. We found severe channel erosion following the TGD closure, with local riverbed erosion up to 10 m deep. The total volume of net erosion from the 565-km channel amounted to 1.85 billion m3, an equivalent of 2.59 billion metric tons of sediment, assuming a bulk density of 1.4 t/m3 for the riverbed material. The largest erosion occurred in a 100-km reach close to the Yangtze River mouth, contributing up to 73% of the total net eroded channel volume.