The lockdown of cities in the Yangtze River Delta (YRD) during COVID-19 has provided many natural and typical test sites for estimating the potential of air pollution control and reduction. To evaluate the reduction of PM_2.5 concentration in the YRD region by the epidemic lockdown policy, this study employs big data, including PM_2.5 observations and 29 independent variables regarding Aerosol Optical Depth (AOD), climate, terrain, population, road density, and Gaode map Point of interesting (POI) data, to build regression models and retrieve spatially continuous distributions of PM_2.5 during COVID-19. Simulation accuracy of multiple machine learning regression models, i.e., random forest (RF), support vector regression (SVR), and artificial neural network (ANN) were compared. The results showed that the RF model outperformed the SVR and ANN models in the inversion of PM_2.5 in the YRD region, with the model-fitting and cross-validation coefficients of determination R² reached 0.917 and 0.691, mean absolute error (MAE) values were 1.026 μg m⁻³ and 2.353 μg m⁻³, and root mean square error (RMSE) values were 1.413 μg m⁻³, and 3.144 μg m⁻³, respectively. PM_2.5 concentrations during COVID-19 in 2020 have decreased by 3.61 μg m⁻³ compared to that during the same period of 2019 in the YRD region. The results of this study provide a cost-effective method of air pollution exposure assessment and help provide insight into the atmospheric changes under strong government controlling strategies.

Lakes play a role as the sentinel of climate change. Surrounded by vast expanses of barren land with limited infrastructure, there is also a lack of knowledge about the dynamics of dryland lakes. The change of lake area can be effectively monitored by remote sensing, and multi-source satellite altimetry datasets provide the possibility to obtain long-term lake water level data. Using the Global Surface Water Monthly Historical dataset and altimetry water level dataset (Hydroweb), we reconstructed a time series of lake water storage changes in Xinjiang, Northwestern China, by establishing the empirical models based on the statistical relationship between the surface area and water level of each lake. We further explored lake response to climate change. The results show that the storage of water at Ayakkum Lake, Aqqikkol Lake and Aksayquin Lake have been undergoing an obvious expanding trend from 2000 to 2020, at a rate of $3.59\times {10}^8{\mathrm{m}}^3/\mathrm{a}$, $9.43\times {10}^8{\mathrm{m}}^3/\mathrm{a}$ and $0.44\times {10}^8{\mathrm{m}}^3/\mathrm{a}$, respectively. In the plain and transition zone, Ulungur Lake showed an upward tendency ($0.413\times {10}^8{\mathrm{m}}^3/\mathrm{a}$) in water storage, while Manas Lake and Bosten Lake experienced shrinkage with descending rates of $-0.1\times {10}^8{\mathrm{m}}^3/\mathrm{a}$ and $-0.86\times {10}^8{\mathrm{m}}^3/\mathrm{a}$. Temperature changes significantly affect the lake water storage on plateaus, especially those lakes supplied with a large proportion of glacial meltwater. Precipitation is a key factor for changes of lake storage in the plain and transition zones. Meanwhile, extreme weather and man-made factors also play crucial roles. To reduce the risk of flood and drought disasters, rational regulation of water resources is required, and a large-scale integrated catchment management plan can avoid inadvertent trade-offs. This research provides a new perspective for lake water storage inversion, as well as data support for water resources management in arid areas including Xinjiang.