Quantifying the aggregation patterns of urban population, economic activities, and land use are essential for understanding compact development, but little is known about the difference among the distribution characteristics and how the built environment influences urban aggregation. In this study, five elements are collected in Wuhan, China, namely population density, floor area ratio, business POIs, road network and built-up area as the representative of urban population, economic activities and land use. An inverse S-shape function is employed to fit the elements’ macro distribution. An aggregation degree index is proposed to measure the aggregation level of urban elements. The kernel density estimation is used to identify the aggregation patterns. The spatial regression model is used to identify the built environment factors influencing the spatial distribution of urban elements. Results indicates that all urban elements decay outward from the city center in an inverse S-shape manner. The business Point-of-Interest (POI) density and population density are highly aggregated; floor area ratio and road density are moderately aggregated, whereas the built-up density is poorly aggregated. Three types of spatial aggregation patterns are identified: a point-shaped pattern, an axial pattern and a planar pattern. The spatial regression modeling shows that the built environment is associated with the distribution of the urban population, economic activities and land use. Destination accessibility factors, transit accessibility factors and land use diversity factors shape the distribution of the business POI density, floor area ratio and road density. Design factors are positively associated with population density, floor area ratio and built-up density. Future planning should consider the varying spatial concentration of urban population, economic activities and land use as well as their relationships with built environment attributes. Results of this study will provide a systematic understanding of aggregation of urban land use, population, and economic activities in megacities as well as some suggestions for planning and compact development.

Methods for estimating the spatial distribution of PM_2.5 concentrations have been developed but have not yet been able to effectively include spatial correlation. We report on the development of a spatial back-propagation neural network (S-BPNN) model designed specifically to make such correlations implicit by incorporating a spatial lag variable (SLV) as a virtual input variable. The S-BPNN fits the nonlinear relationship between ground-based air quality monitoring station measurements of PM_2.5, satellite observations of aerosol optical depth, meteorological synoptic conditions data and emissions data that include auxiliary geographical parameters such as land use, normalized difference vegetation index, elevation, and population density. We trained and validated the S-BPNN for both yearly and seasonal mean PM_2.5 concentrations. In addition, principal components analysis was employed to reduce the dimensionality of the data and a grid of neural network models was run to optimize the model design. The S-BPNN was cross-validated against an analogous but SLV-free BPNN model using the coefficient of determination (R²) and root mean squared error (RMSE) as statistical measures of goodness of fit. The inclusion of the SLV led to demonstrably superior performance of the S-BPNN over the BPNN with R² values increasing from 0.80 to 0.89 and with the RMSE decreasing from 8.1 to 5.8 μg/m³. The yearly mean PM_2.5 concentration in China during the study period was found to be 41.8 μg/m³ and the model estimated spatial distribution was found to exceed Level 2 of the China Ambient Air Quality Standards (CAAQS) enacted in 2012 (>35 μg/m³) in more than 70% of the Chinese territory. The inclusion of spatial correlation upgrades the performance of conventional BPNN models and provides a more accurate estimation of PM_2.5 concentrations for air quality monitoring.

While the influence of compound extreme events is gaining attention with advancing extreme climate research, the variations in their impacts on regional crop production require further exploration. Here, we primarily analyze the changes in compound hot‐dry events and compound hot‐wet events in China from 1985 to 2019, based on meteorological observations from 686 stations. Then, their contributions to losses in cropland net primary productivity (CNPP) are identified using the extreme gradient boosting and Shapley additive explanations models. Results indicate that compound extreme events have become increasingly frequent, persistent, and severe over the past 35 years. With the increasing risks of compound extreme events, greater CNPP losses are observed in the northern regions compared to the southern regions. Throughout the growing season, CNPP losses caused by compound extreme events initially increase, peak in summer, and then gradually decrease. CNPP losses in China are primarily influenced by compound hot‐dry events. From north to south, the events dominating CNPP losses shift sequentially from compound daytime hot and dry events to compound day‐night hot and dry events, and finally to compound nighttime hot and dry events. This study explores the threats posed by compound extreme events to regional crop production and provides new insights into extreme climate risks in China, supporting climate‐adaptive agricultural development.

Air pollution is a significant urban issue, with practical applications for pollution control, urban environmental management planning, and urban construction. However, owing to the complexity and differences in spatiotemporal changes for various types of pollution, it is challenging to establish a framework that can capture the spatiotemporal correlations of different types of air pollution and obtain high prediction accuracy. In this paper, we proposed a deep learning framework suitable for predicting various air pollutants: a graph convolutional temporal sliding long short-term memory (GT-LSTM) model. The hybrid integrated model combines graph convolutional networks and long short-term networks based on a strategy with temporal sliding. Herein, the graph convolution networks gather neighbor information for spatial dependency modeling based on the spatial adjacency matrices of different pollutants and the graph convolution operator with parameter sharing. LSTM networks with a temporal sliding strategy are used to learn dynamic air pollution changes for temporal dependency modeling. The framework was applied to predict the average concentrations of PM_2.5, PM₁₀, O₃, CO, SO₂, and NO₂ in the Bejing-Tianjin-Hebei (BTH) region for the next 24 hours. Experiments demonstrated that the proposed GT-LSTM model could extract high-level spatiotemporal features and achieve higher accuracy and stability than state-of-the-art baselines. Advancement in this methodology can assist in providing decision support capabilities to mitigate air quality issues.