Ying Yuan

Accurate and timely information on tobacco cultivation is essential for macro-level regulation, tobacco monopoly management, and farmer support in China. Remote sensing offers an efficient means for mapping tobacco, yet most studies focus on mid- to late-season identification, while early-season detection remains underexplored. Therefore, we integrated multi-source remote sensing data with the Google Earth Engine (GEE) platform to quantify separability between tobacco and competing crops, determined the optimal early-season phenological window and discriminative features, and developed an early-season tobacco mapping approach using a stacked generalization ensemble. The results show that January–February period provides the most effective early identification window for Changting County, with near-infrared (NIR) and water-sensitive features contributing most to class discrimination. The stacked ensemble achieved an overall accuracy of 87.17%, with producer and user accuracies of 85.97% and 92.28%, respectively, outperforming individual classifiers. At the township scale, the mapped tobacco area was strongly associated with tobacco purchase volumes (R² = 0.819), supporting the reliability of the derived maps. Spatially, tobacco fields exhibited a pronounced corridor-like pattern, primarily influenced by proximity to water systems and terrain conditions. The proposed workflow provides tobacco management agencies with timely, spatially explicit information to support precise and intelligent tobacco production management.

Gross Domestic Product (GDP) serves as a core indicator for measuring the sustainable economic development of countries and regions. Accurate understanding of its spatio-temporal distribution is crucial for achieving the United Nations Sustainable Development Goals (SDGs). However, current grid-based GDP data for China’s regions predominantly consists of data from specific years, making it difficult to capture fine-grained changes in economic development. To address this, this study proposes a spatial GDP framework integrating cross-scale feature extraction (CSFs) with stacked ensemble learning. Based on China’s county-level GDP statistics and multi-source auxiliary data, it first generates a density-weighted estimation layer. This is then processed through dasymetric mapping to produce China’s Annual High-Resolution Gridded GDP Dataset (CA_GDP) from 2000 to 2021. Evaluation demonstrates the framework’s superior performance in density weight estimation, achieving an R² of 0.82 against statistical data. Compared to traditional single models like Random Forests (RF), it improves R² by 13–54%, reduces mean absolute error (MAE) by 2–26%, and lowers root mean square error (RMSE) by 19–39%, with these advantages remaining stable across time series. The dasymetric mapping of the CA_GDP dataset clearly depicts the economic development patterns and urban agglomeration effects in the southeastern coastal regions, as well as the relatively lagging economic development in western areas. Compared to existing public datasets, CA_GDP offers significant advantages in reflecting the fine-grained economic spatial structure within county-level units, providing a more reliable data foundation for identifying regional economic disparities, policy formulation and evaluation, and related research.

China’s age structure is undergoing profound demographic shifts, making accurate spatial information on age-stratified populations essential for policy-making, resource allocation, and risk assessment. However, census data are primarily aggregated by administrative units, offering coarse spatial resolution that constrains their integration and application with other gridded datasets. Using township-level population counts for four age groups (0–14, 15–59, 60–64, and ≥65 years) from the 2020 Seventh National Population Census across 38,572 townships, we developed an age-stratified downscaling framework. This framework integrates a random forest model with age-filtered Points of Interest (POI) data and other multi-source geospatial covariates to generate a 100 m resolution age-stratified population density weighting layer. Through township-level data dasymetric mapping, we produced the township-based 100 m Age-Stratified Population Grid Data (Township-ASPOP). Since township-level data represent the finest publicly available spatial unit of demographic statistics in China, we further validated the accuracy of Township-ASPOP by generating County-based 100 m Age-Stratified Population Grid Data (County-ASPOP) through dasymetric mapping using county-level age-stratified population data. The results demonstrate that County-ASPOP achieves superior predictive accuracy, with R² values of 0.95, 0.95, 0.85, and 0.86, and Root Mean Square Error (RMSE) values of 1743, 6829, 900, and 2033 persons per township for the four age groups, respectively—significantly outperforming the contemporaneous WorldPop dataset (R² = 0.69, 0.72, 0.64, and 0.60). The accuracy of Township-ASPOP is no less than that of County-ASPOP and effectively captures realistic spatial settlement patterns. This study establishes a reproducible framework for generating age-stratified population grid data and provides critical data support for policy formulation and resource allocation.

Water functional zoning plays a crucial role in water resource allocation, pollution prevention, and ecological protection. With the increasing intensity of human activities, there is a significant mismatch between current water functional zoning and the economic, social development needs and ecological protection goals. Existing water functional zoning methods mainly rely on expert experience for qualitative judgment, which is highly subjective and inefficient. In response, this paper presents a transferable quantitative feature system and introduces a machine learning-based progressive zoning framework for water functions, validated through a case study of the Yangtze River Basin. The results show that the overall accuracy of the framework is 0.78, which is 4–7% higher compared to traditional single models. In terms of spatial distribution, the transformation of protection and reserved zones in 2020 mainly occurred in the middle and lower reaches, where human activities are frequent, particularly in Sichuan and Jiangxi provinces. The development zones are highly concentrated in the downstream areas, with some regions transitioning into protection or reserved zones, mainly in Hubei and Chongqing provinces. Adjustments to buffer zones are primarily concentrated along inter-provincial boundary areas, such as the junction between Hubei and Anhui provinces. This framework helps managers quickly identify key areas for optimizing water functional zones, providing valuable reference for the precise management of water resources and the formulation of ecological protection strategies in the basin.

Accurate assessment of cropland maps is crucial for ensuring food security, effective agricultural management, and environmental monitoring. With the widespread application of high-resolution (≤10 m) remote sensing imagery and the advancement of machine learning techniques, numerous high-resolution cropland maps have been developed. However, comprehensive evaluations of their accuracy remain limited. We utilized 163,861 validation samples and national land survey statistical data to conduct a multi-scale comparison of the accuracy of seven cropland maps (one 1 m and six 10 m maps) in China. Additionally, five synergistic strategies were employed to generate more accurate fused cropland maps. Validation results showed that the overall accuracy (OA) of the seven maps ranged from 0.79 to 0.91, with ESA-WorldCover (ESA-WC) exhibiting the highest OA, followed by AI Earth China land cover classification dataset (AIEC), ESRI Land Cover (ESRI-LC), and Cropland Use Intensity in China (China-CUI), while Sino-LC1 showed the lowest performance. Spatially, ESA-WC achieved the highest accuracy in nearly 60% of provinces, followed by AIEC and ESRI-LC, each accounting for approximately 20%. AIEC performed best in western provinces, whereas ESRI-LC dominated in the middle and lower reaches of the Yangtze River. Area consistency assessments revealed that, on average, the seven maps overestimated cropland areas by 20% compared to statistical data. Among these, ESA-WC showed the highest proportion of provinces with relative errors within ±20%, but this proportion was only 50%. Moreover, the OA of the fused maps exceeded 0.92, with county-level R² values compared to statistical data reaching 0.98, significantly improving the reliability of cropland products in over 60% of provincial administrative regions. Based on these results, effective synergistic strategies for high-resolution cropland mapping are proposed.

Accurate prediction of water quality involves early identification of future pollutant concentrations and water quality indicators, which is an important prerequisite for optimizing water environment management. Although deep learning algorithms have demonstrated considerable potential in predicting water quality parameters, their broader adoption remains hindered by limited interpretability. This study proposes an interpretable deep learning framework integrating an artificial neural network (ANN) model with Shapley additive explanations (SHAP) analysis to predict spatiotemporal variations in water quality and identify key influencing factors. A case study was conducted in the Poyang Lake Basin, utilizing multi-dimensional datasets encompassing topographic, meteorological, socioeconomic, and land use variables. Results indicated that the ANN model exhibited strong predictive performance for dissolved oxygen (DO), total nitrogen (TN), total phosphorus (TP), permanganate index (CODMn), ammonia nitrogen (NH₃N), and turbidity (Turb), achieving R² values ranging from 0.47 to 0.77. Incorporating land use and socioeconomic factors enhanced prediction accuracy by 37.8–246.7% compared to models using only meteorological data. SHAP analysis revealed differences in the dominant factors influencing various water quality parameters. Specifically, cropland area, forest cover, air temperature, and slope in each sub-basin were identified as the most important variables affecting water quality parameters in the case area. These findings provide scientific support for the intelligent management of the regional water environment.

Water quality evaluation usually relies on limited state-controlled monitoring data, making it challenging to fully capture variations across an entire basin over time and space. The fine estimation of water quality in a spatial context presents a promising solution to this issue; however, traditional analyses often ignore spatial non-stationarity between variables. To solve the above-mentioned problems in water quality mapping research, we took the Yangtze River as our study subject and attempted to use a geographically weighted random forest regression (GWRFR) model to couple massive station observation data and auxiliary data to carry out a fine estimation of water quality. Specifically, we first utilized state-controlled sections’ water quality monitoring data as input for the GWRFR model to train and map six water quality indicators at a 30 m spatial resolution. We then assessed various geographical and environmental factors contributing to water quality and identified spatial differences. Our results show accurate predictions for all indicators: ammonia nitrogen (NH₃-N) had the lowest accuracy (R² = 0.61, RMSE = 0.13), and total nitrogen (TN) had the highest (R² = 0.74, RMSE = 0.48). The mapping results reveal total nitrogen as the primary pollutant in the Yangtze River basin. Chemical oxygen demand and the permanganate index were mainly influenced by natural factors, while total nitrogen and total phosphorus were impacted by human activities. The spatial distribution of critical influencing factors shows significant clustering. Overall, this study demonstrates the fine spatial distribution of water quality and provides insights into the influencing factors that are crucial for the comprehensive management of water environments.

Accurately assessing the impact of land use patterns on total phosphorus (TP) concentration in surface water is crucial for protecting the water environment of the Yangtze River Basin (YRB). However, due to the heterogeneity of land use patterns, the regional differences in the intensity and direction of their impacts on TP concentrations in the YRB remain insufficiently understood. This study utilizes water quality monitoring data from state-controlled sections in 2021 and employs spatial autocorrelation analysis, geographic detectors, and Pearson correlation models to identify the impacts of land use on TP concentrations at multiple scales across the YRB. The results indicate that TP concentrations at 98.8% of the monitoring stations in the YRB exceed the Class III standard, with high concentrations of TP concentrated in the Pudu River Basin, Chengdu Plain, Jianghan Plain, and Yangtze River Delta regions. At the YRB scale, the spatial pattern of built-up land, cropland, and industrial and mining land significantly increases TP concentrations, while the pattern of forest and grassland areas exert mitigating effects. At the sub-basin scale, the impact of land use patterns on TP concentrations varies regionally. Specifically, TP concentrations in the Pudu River Basin are primarily attributed to the spatial pattern of industrial and mining land, in the Chengdu Plain to the spatial pattern of cropland and industrial and mining land, and in the Jianghan Plain to the spatial pattern of cropland, built-up land, and industrial and mining land. These results provided decision support for TP concentration control strategies and effective mitigation measures.

The accuracy assessment of cropland products is a critical prerequisite for agricultural planning and food security evaluations. Current accuracy assessments of remote sensing-based cropland products focused on the consistency of spatial patterns for specific years, yet the reliability of these cropland products in time-series analysis remains unclear. Using cropland area data from the second and third national land surveys of China (referred to as NLSCD) as a benchmark, we evaluate the area-based and spatial-based consistency of cropland changes in five 30 m time-series land cover products covering 2010 and 2020, including the annual cropland dataset of China (CACD), the annual China Land Cover Dataset (CLCD), China’s Land-use/cover dataset (CLUD), the Global Land-Cover product with Fine Classification System (GLC_FCS30), and GlobeLand30. We also employed the GeoDetector model to explore the relationships between the consistency in cropland change and the environmental factors (e.g., cropland fragmentation, topographic features, frequency of cloud cover, and management practices). The area-based consistency analysis showed that all five cropland products indicate a declining trend in cropland areas in China over the past decade, while the amount of cropland loss ranges from 5.59% to 57.85% of that reported by the NLSCD. At the prefecture-level city scale, the correlation coefficients between the cropland area changes detected by five cropland products and the NLSCD are low, with GlobeLand30 having the highest coefficient at 0.67. The proportion of prefecture-level cities where the change direction of cropland area in each cropland product is inconsistent with the NLSCD ranges from 13.27% to 39.23%, with CLCD showing the highest proportion and CLUD the lowest. At the pixel scale, the spatial-based consistency analysis reveals that 79.51% of cropland expansion pixels and 77.79% of cropland loss pixels are completely inconsistent across five cropland products, with the southern part of China exhibiting greater inconsistency compared to Northwest China. Besides, the frequency of cloud cover and management practices (e.g., irrigation) are the primary environmental factors influencing consistency in cropland expansion and loss, respectively. These results suggest low consistency in cropland change across five cropland products, emphasizing the need to address these inconsistencies when generating time-series cropland datasets via remote sensing.

In order to meet the needs of the control-unit-based water pollution prevention problem in China, we proposed a comprehensive control unit zoning method with the combined basic administrative region and objective watershed management. The method can effectively connect the natural characteristics of watershed water sources, three-level zoning of water resources, and comprehensively consider the pollution distribution, socio-economics and many other factors. The zoning process includes four steps: (1) Generate the multi-level hydrological unit; (2) Identify the multi-element water catchment units; (3) Obtain the control unit with the administrative boundary as the boundary; (4) Check and adjust the results to meet the actual needs. Based on this method, the Yangtze River Basin was divided into 568 control units with a total area of 1.91 million km². These control units were used as the basic unit to analyze the water quality status and the results show that the upper reaches have good water quality, while the lower reaches have poor water quality and more serious water pollution. Our study helps the Ministry of Environmental Protection of China develop the list of control units that are needed to improve water quality during the “13th Five-Year Plan”, with a goal to provide technical support for control-unit-based water pollution prevention and control in the future.