As the most abundant greenhouse gas in the atmosphere, CO₂ has a significant impact on climate change. Therefore, the determination of the temporal and spatial distribution of CO₂ is of great significance in climate research. However, existing CO₂ monitoring methods have great limitations, and it is difficult to obtain large-scale monitoring data with high spatial resolution, thus limiting the effective monitoring of carbon sources and sinks. To obtain complete Chinese daily-scale CO₂ information, we used OCO-2 XCO₂ data, Carbon Tracker XCO₂ data, and multivariate geographic data to build a model training data set, which was then combined with various machine learning models including Random Forest, Extreme Random Forest, XGBoost, LightGBM, and CatBoost. The results indicated that the Random Forest model presented the best performance, with a cross-validation R² of 0.878 and RMSE of 1.123 ppm. According to the final estimation results, in terms of spatial distribution, the highest multi-year average RF XCO₂ value was in East China (406.94 ± 0.65 ppm), while the lowest was in Northwest China (405.56 ± 1.43 ppm). In terms of time, from 2016 to 2018, the annual XCO₂ in China continued to increase, but the growth rate showed a downward trend. In terms of seasonal effects, the multi-year average XCO₂ was highest in spring (407.76 ± 1.72 ppm) and lowest in summer (403.15 ± 3.36ppm). Compared with the Carbon-Tracker data, the XCO₂ data set constructed in this study showed more detailed spatial changes, thus, can be effectively used to identify potentially important carbon sources and sinks.

NO₂ (nitrogen dioxide) is a common pollutant in the atmosphere that can have serious adverse effects on the health of residents. However, the existing satellite and ground observation methods are not enough to effectively monitor the spatiotemporal heterogeneity of near-surface NO₂ concentrations, which limits the development of pollutant remediation work and medical health research. Based on TROPOMI-NO₂ tropospheric column concentration data, supplemented by meteorological data, atmospheric condition reanalysis data and other geographic parameters, combined with classic machine learning models and deep learning networks, we constructed an ensemble model that achieved a daily average near-surface NO₂ of 0.03° exposure. In this article, a meteorological hysteretic effects term and a spatiotemporal term were designed, which considerably improved the performance of the model. Overall, our ensemble model performed better, with a 10-fold CV R² of 0.89, an RMSE of 5.62 µg/m³, and an MAE of 4.04 µg/m³. The model also had good temporal and spatial generalization capability, with a temporal prediction R² and a spatial prediction R² of 0.71 and 0.81, respectively, which can be applied to a wider range of time and space. Finally, we used an ensemble model to estimate the spatiotemporal distribution of NO₂ in a coastal region of southeastern China from May 2018 to December 2020. Compared with satellite observations, the model output results showed richer details of the spatiotemporal heterogeneity of NO₂ concentrations. Due to the advantages of using multi-source data, this model framework has the potential to output products with a higher spatial resolution and can provide a reference for downscaling work on other pollutants.

Groundwater depletion has emerged as a pressing global challenge, yet the low spatial resolution (0.25°) of Gravity Recovery and Climate Experiment (GRACE) satellite data limits its application in regional groundwater monitoring. In this study, based on 0.25° spatial resolution groundwater storage anomalies (GWSAs) data derived from GRACE satellite observations and GLDAS hydrological model outputs, supplemented with hydrological data, humanities data, and other geographic parameters, we constructed a Stacking-based ensemble machine learning model that achieved a 1 km spatial resolution of GWSAs distribution data across the contiguous United States (CONUS) from 2010 to 2020. The ensemble model integrates eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Categorical Boosting (CatBoost) models using an Attention-Based Dynamic Weight Allocation (ADWA) approach, along with a ridge regression model. The results indicate that our ensemble model outperforms individual machine learning (ML) models, achieving a coefficient of determination (R²) of 0.929, root mean square error (RMSE) of 25.232 mm, mean absolute error (MAE) of 19.125 mm, and Nash–Sutcliffe efficiency (NSE) of 0.936, validated by 10-fold cross-validation. In situ measurements indicate that, compared with the original data, approximately 61.7% of the monitoring wells (266 out of 431) exhibit a higher correlation after downscaling, with the overall correlation coefficient increasing by about 18.7%, which suggests that the downscaled product exhibits an appreciable improvement in accuracy. The ensemble model proposed in this study, by integrating the advantages of various ML algorithms, is better able to address the complexity and uncertainty of groundwater storage variations, thus providing scientific support for the sustainable management of groundwater resources.

Ambient exposure to fine particulate matter (PM_2.5) in eastern China, a densely populated region with very high-level PM_2.5 pollution, has attracted great concern from the public, government, and scientific community. By taking advantage of advanced statistical methods and a high-resolution PM_2.5 dataset, this study explicitly investigated the spatiotemporal changes in PM_2.5 in eastern China from 2001 to 2018 at multiple spatial and temporal scales and examined its links with natural and socioeconomic factors to explore their effects on PM_2.5 changes. This study found that the PM_2.5 concentration in most of eastern China declined recently, while most of the discernable decreasing trends occurred in the southern and western areas of the study domain, and the statistically significant increasing trends were primarily in the North China Plain. The influencing factors analysis found that, among the selected four natural and five anthropogenic factors, temperature, and population density exerted more potent effects than the other influencing factors, and all the influencing factors were found to impose complex effects on the PM_2.5 concentration over space and time. Our study draws a complete picture of the changes in PM_2.5 and its possible influences, which could guide future actions to mitigate PM_2.5 pollution in eastern China.

As a vital part of the geo-environment and water cycle, ecosystem health and human development are dependent on water resources. Water supply and demand are influenced significantly by land use and cover change (LUCC) which shapes the surface ecosystems by altering their structure and function. Under future climate change scenarios, LUCC may greatly impact regional water balance, yet the impact is still not well understood. Therefore, examining the spatial relationship between LUCC and water yield services is crucial for optimizing land resources and informing sustainable development policies. In this study, we focused on the Hanjiang River Basin and used the patch-generating land use simulation (PLUS) model, coupled with the Integrated Valuation of Ecosystem Services and Tradeoffs (InVEST) model, to assess water yield services under three Shared Socioeconomic Pathway and Representative Concentration Pathway (SSP-RCP) scenarios. For the first time, we considered the impact of future changes in socio-economic and water use indicators on water demand using correction factors and ARIMA projections. The relationship between water supply and demand was explored using this approach, and LUCC’s effects on this balance are also discussed. Results indicate that: (1) The patterns of LUCC are similar for the three scenarios from 2030 to 2050, with varying levels of decrease for cropland and significant growth of built-up areas, with increases of 6.77% to 19.65% (SSP119), 7.66% to 22.65% (SSP245), and 15.88% to 46.69% (SSP585), respectively, in the three scenarios relative to 2020; (2) The future supply and demand trends for the three scenarios of produced water services are similar, and the overall supply and demand risks are all on a downward trend. Water demand continues to decline, and by 2050, the water demand of the 3 scenarios will decrease by $96.275\times {10}^8\mathrm{t}$, $81.210\times {10}^8\mathrm{t}$, and $84.13\times {10}^8\mathrm{t}$ relative to 2020, respectively; while supply decreases from 2030 to 2040 and rises from 2040 to 2050; (3) Both water supply and demand distributions exhibit spatial correlation, and the distribution of hotspots is similar. The water supply and demand are well-matched, with an overall supply-demand ratio greater than 1.5; (4) LUCC can either increase or decrease water yield. Built-up land provides more water supply compared to other land types, while forest land has the lowest average water supply. Limiting land use type conversions can enhance the water supply.

To address the critical demand for high-precision forecasts in flood management, real-time error correction techniques are increasingly implemented to improve the accuracy and operational reliability of the hydrological prediction framework. However, developing a robust error correction scheme remains a significant challenge due to the compounded errors inherent in hydrological modeling frameworks. In this study, a Bayesian ensemble learning-based correction (BELC) scheme is proposed which integrates hydrological modeling with multiple machine learning methods to enhance real-time error correction for flood forecasting. The Xin’anjiang (XAJ) model is selected as the hydrological model for this study, given its proven effectiveness in flood forecasting across humid and semi-humid regions, combining structural simplicity with demonstrated predictive accuracy. The BELC scheme straightforwardly post-processes the output of the XAJ model under the Bayesian ensemble learning framework. Four machine learning methods are implemented as base learners: long short-term memory (LSTM) networks, a light gradient-boosting machine (LGBM), temporal convolutional networks (TCN), and random forest (RF). Optimal weights for all base learners are determined by the K-means clustering technique and Bayesian optimization in the BELC scheme. Four baseline schemes constructed by base learners and three ensemble learning-based schemes are also built for comparison purposes. The performance of the BELC scheme is systematically evaluated in the Hengshan Reservoir watershed (Fenghua City, China). Results indicate the following: (1) The BELC scheme achieves better performance in both accuracy and robustness compared to the four baseline schemes and three ensemble learning-based schemes. The average performance metrics for 1–3 h lead times are 0.95 (NSE), 0.92 (KGE), 24.25 ${\mathrm{m}}^3/\mathrm{s}$ (RMSE), and 8.71% (RPE), with a PTE consistently below 1 h in advance. (2) The K-means clustering technique proves particularly effective with the ensemble learning framework for high flow ranges, where the correction performance exhibits an increment of 62%, 100%, and 100% for 1 h, 2 h, and 3 h lead hours, respectively. Overall, the BELC scheme demonstrates the potential of a Bayesian ensemble learning framework in improving real-time error correction of flood forecasting systems.