Zhaoxu Zhang

Intensive mining over recent decades has caused severe ground subsidence in mining regions, threatening safety and long-term sustainability. High-precision, continuous monitoring and prediction of subsidence are therefore urgently needed. Traditional methods—terrestrial surveying and GPS—offer limited coverage, sparse measurement points, high costs, and poor scalability, making them unsuitable for large-scale, long-term surface deformation monitoring. InSAR is widely used for ground deformation monitoring due to its wide-area coverage, long-term sampling, high spatial resolution, and millimeter-scale precision. However, conventional InSAR often fails in vegetated areas and under steep deformation gradients—common in mining zones. To overcome these limitations, this study applied SBAS-InSAR, a method better suited for large-magnitude, continuous subsidence monitoring in mining areas. This study proposed an enhanced hierarchical spatiotemporal dependency graph neural network (HSDGNN) integrated with a Long Short-Term Memory (LSTM) module to improve temporal feature representation. Using this model, this study predicted surface subsidence at the Dexing Copper Mine under environmental drivers. Key findings are as follows: (1) Surface subsidence exhibited pronounced spatial heterogeneity and strong temporal nonlinearity; major subsidence zones were localized in open-pit excavation areas and waste rock dumps, with peak subsidence rates reaching −126.121 mm/yr. (2) Precipitation and soil moisture emerged as the dominant environmental controls on subsidence, displaying distinct seasonal modulation and quantifiable lagged responses—up to several months—relative to subsidence onset. (3) The HSDGNN model achieved high predictive accuracy for both Mine 1 and Mine 2, attaining R² values of up to 0.9950. This work establishes a robust, scalable, and operationally viable framework for high-precision subsidence monitoring and forecasting in geologically and anthropogenically complex mining environments.

Cropland soil organic carbon (SOC) is a critical soil component governing soil fertility, agricultural productivity, food security, climate change mitigation and ecosystem health via carbon biogeochemical cycling. Conventional soil sampling fea-tures low spatial density and infrequent updates, making it inca-pable of high-resolution, large-scale SOC monitoring. Meanwhile, individual machine learning models show weak generalization across heterogeneous agroecological conditions and limited accu-racy in fine-scale SOC inversion. To tackle these constraints, this study developed a stacked ensemble meta-model framework for Tianjin's croplands to achieve high-precision 10 m resolution surface SOC inversion and mapping. Thirty-six biophysical and spectral covariates including Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI) and Green Normalized Difference Vegetation Index (GNDVI) were derived from Sentinel-2 imagery as predictors. Four base learners, name-ly Random Forest (RF), Support Vector Regression (SVR), eX-treme Gradient Boosting (XGBoost), Elastic Net Regression (ElasticNet) were trained and verified, with Ridge Regression as the meta-learner. SHapley Additive exPlanations (SHAP) analy-sis was used to quantify feature contributions for model inter-pretability. The ensemble model obtained an R² of 0.7816, 0.1069 higher than the best-performing base model SVR (R² = 0.6747), and reduced RMSE by 18.0

As a critical geophysical parameter governing land-atmosphere interactions, soil moisture (SM) plays a pivotal role in regulating global water and energy cycles. Despite the proliferation of satellite-derived SM products, their utility in precision agriculture remains constrained by inherent limitations in spatial resolution and cross-regional generalizability. This study presents a novel machine learning framework that synergistically integrates multisource earth observation data with in-situ measurements from the International Soil Moisture Network (ISMN) to address these limitations. Leveraging the cloud-based computational capabilities of Google Earth Engine (GEE), we developed a high-resolution (60m) SM estimation model through systematically synergistic integration of Sentinel-2 multispectral reflectance, Sentinel-1 C-band SAR backscatter characteristics (VV, VH polarization, incidence angle) and ISMN ground measurements. The microwave-canopy interaction mechanisms were quantitatively characterized using the Michigan Microwave Canopy Scattering (MIMICS) model, informing the selection of optimal predictor variables from Sentinel-2 MSI spectral bands (B1-B8A, B9-B12) and SoilGrids texture parameters. A streamlined machine learning regression architecture was implemented, achieving optimized performance through feature importance analysis that identified clay content (32.98%) and sand content (28.25%) as dominant predictors. Validation across heterogeneous agricultural regions demonstrated robust performance (Bias < 0.05 cm³/cm³) in low-to-moderate moisture regimes (< 0.36 cm³/cm³), with systematic underestimation observed in saturated conditions. The operational pipeline generated monthly composite SM maps for Henan Province croplands (April 2018), establishing a transferable paradigm for global-scale high-resolution SM monitoring, particularly in low-stature crop environments (e.g., winter wheat). This methodology advances the synergistic use of microwave-optical-soil property data fusion and provides critical insights for extending the framework to other vegetation types.

Soil moisture is a critical parameter in hydrology, meteorology, and agricultural applications. To address the limitations of low model generalization and difficulties in rapid data acquisition, this study integrated a downscaling soil moisture estimation model with the Google Earth Engine (GEE) platform to develop a technique for automated production of large-scale, medium spatial resolution soil moisture remote sensing products. Using Henan Province as a case study, this research produced monthly average soil moisture data with a spatial resolution of 1 km for 2018. It provided a detailed description of the automated production workflow implemented on the GEE platform and presented the 1 km monthly composite soil moisture results for the agricultural regions of Henan Province. The findings revealed that soil moisture in Henan Province generally exhibited a spatial trend of lower values in the north and higher values in the south across most months. In the east-west direction, soil moisture showed no clear gradient, though values in eastern Henan were consistently lower. Additionally, the spatial variations in soil moisture correlated positively with precipitation and evapotranspiration. This study successfully addressed the challenges of low model generalizability and difficulty in rapid data acquisition, achieving the automated generation of soil moisture remote sensing products. This method will fill the research shortcoming and hold significant importance for regional soil moisture estimation and application studies.

Land-use and land-cover changes constitute pivotal components in global environmental change research. Through an examination of spatiotemporal variations in land cover, we can deepen our understanding of land-cover change dynamics, shape appropriate policy frameworks, and implement targeted environmental conservation strategies. The judicious management of land is a critical determinant in fostering the sustainable growth of urban economies and enhancing quality of life for residents. This study harnessed remote sensing data to analyze land-cover patterns in Tianjin over five distinct time points: 2000, 2005, 2010, 2015, and 2020. It focused on evaluating the evolving dynamics, transition velocities, and transformation processes across various land categories within the region. Utilizing dynamic analysis and a transition matrix, the study traced shifts among different land-use classes. The center-of-gravity migration model was employed to elucidate land-cover pattern evolution. This research also integrated pertinent land-cover statistics to offer a holistic perspective on Tianjin’s land-cover transformations. Employing the CA–Markov model, we projected the prospective spatial layout of land cover for the area. Our findings revealed the following. (1) From 2000 to 2020, Tianjin experienced a significant reduction in cropland, forest, grassland, and water areas, alongside a substantial increase in impervious. (2) The impervious surface’s center of gravity, initially in Beichen District, shifted 4.20 km northwestward at an average rate of 0.84 km per year. (3) Principal component analysis indicated that the growth in the output value of the secondary and forestry industries is a key driver in expanding Tianjin’s impervious-surface area. (4) Predictions for 2025 suggest an increase in Tianjin’s impervious-surface area to 4659.78 km², with a concurrent reduction in cropland to 5656.18 km². The insights gleaned from this study provide a solid theoretical foundation and empirical evidence, aiding in the formulation of informed land-use strategies, the preservation of urban land resources, and guiding principles for sustainable urban development.

Urbanization is an important symbol of regional economic development and social progress. Studying the urbanization level is greatly important for the scientific development of towns and cities, and for the efficient decision-making of governments. Nighttime light data, containing information on human activities, economic and social development, compensate for the uncertainty and lag problems of the indicator method. Those data can also provide a more intuitive reflection of the level of urbanization and offer novel insights for research on urbanization. In this study, based on the 2000–2020 EANTLI_Like nighttime light remote sensing data, the characteristics of the spatial and temporal dynamic changes in the land urbanization level in China were measured. Results were analysed at four scales: national, regional, provincial, and municipal. Finally, the main economic indicators affecting urbanization were selected as variables to simply analyze the driving force of land urbanization through spatial autocorrelation and spatio-temporal geographically weighted regression model. Results indicated that China's land urbanization level continued to grow from 2000 to 2020, with an average annual growth rate of 2.51%. The spatial distribution of land urbanization varied significantly across regions. The level of land Urbanization in the eastern coastal region was significantly higher than that in the inland and western provinces, at the agricultural and provincial scales. Hong Kong, Macao, and Shanghai ranked high in terms of land urbanization, and the Pearl River Delta and Yangtze River Delta regions in which they were located also belong to the cluster of high land urbanization levels. Meanwhile, the goodness of fit amongst GDP, the proportion of output of secondary and tertiary industries, freight volume and land urbanization level were higher than 0.86. Among them, GDP and the output of secondary and tertiary industries had a more obvious role in promoting land urbanization. The freight volume exhibited positive effects on land urbanization level in the western region, Heilongjiang and Jilin provinces. This study is great important for understanding the law of urban construction land expansion in China, the regional differences in land urbanization level and the optimisation of land use layout.

Drought is a frequent global phenomenon. Solar-induced chlorophyll fluorescence (SIF), an electromagnetic signal, has been proven to be an efficient tool for monitoring and assessing gross primary productivity (GPP) and drought. To address the issue of the sparse resolution of satellite-based SIF, researchers have developed different downscaling algorithms. Recently, the most frequently used SIF products had a spatial resolution of 0.05 degrees. However, these spatial resolution SIF data are not conducive to regional agricultural drought monitoring. In this study, we utilized the global ‘OCO-2’ solar-induced fluorescence (GOSIF) products along with normalized difference vegetation index (NDVI) and land surface temperature (LST) products. With the powerful advantages offered by Google Earth Engine (GEE), we could conveniently acquire the necessary data. Additionally, employing the random forest (RF) method, we successfully acquired downscaled SIF data at an enhanced spatial resolution of 1 km. Using those downscaled SIF results with 1 km resolution, an SIF anomaly index was established and calculated to monitor drought. Results showed that the RF-based downscaled SIF result followed the same trend as the GOSIF value. Subsequently, correlation coefficients between SIF and GPP were calculated. The downscaled SIF demonstrated a higher correlation with GPP from MODIS compared to 0.05-degree GOSIF, with coefficients of 0.74 and 0.68 in May 2018, respectively. Moreover, the SIF anomaly index showed positive correlations with crop yield; the correlation coefficients were 0.93 for wheat and 0.89 for maize. The drought index had a negative correlation with areas affected by drought, with a correlation coefficient of −0.58. Finally, the SIF anomaly index was used to monitor drought from 2001 to 2020 in Henan Province. The 1 km SIF results obtained through the RF-based downscaled method were deemed reliable, thereby establishing the suitability of the SIF anomaly index for drought monitoring at a regional scale.

With burgeoning economic development, a surging influx of greenhouse gases, notably carbon dioxide (CO₂), has precipitated global warming, thus accentuating the critical imperatives of monitoring and predicting carbon emissions. Conventional approaches employed in the examination of carbon emissions predominantly rely on energy statistics procured from the National Bureau of Statistics and local statistical bureaus. However, these conventional data sources, often encapsulated in statistical yearbooks, exclusively furnish insights into energy consumption at the national and provincial levels, so the assessment at a more granular scale, such as the municipal and county levels, poses a formidable challenge. This study, using nighttime light data and statistics records spanning from 2000 to 2019, undertook a comparative analysis, scrutinizing various modeling methodologies, encompassing linear, exponential, and logarithmic models, with the aim of assessing carbon emissions across diverse spatial scales. A multifaceted analysis unfolded, delving into the key attributes of China’s carbon emissions, spanning total carbon emissions, per capita carbon emissions, and carbon emission intensity. Spatial considerations were also paramount, encompassing an examination of carbon emissions across provincial, municipal, and county scales, as well as an intricate exploration of spatial patterns, including the displacement of the center of gravity and the application of trend analyses. These multifaceted analyses collectively contributed to the endeavor of predicting China’s future carbon emission trajectory. The findings of the study revealed that at the national scale, total carbon emissions exhibited an annual increment throughout the period spanning 2000 to 2019. Secondly, upon an in-depth evaluation of model fitting, it was evident that the logarithmic model emerged as the most adept in terms of fitting, presenting a mean R² value of 0.83. Thirdly, the gravity center of carbon emissions in China was situated within Henan Province, and there was a discernible overall shift towards the southwest. In 2025 and 2030, it is anticipated that the average quantum of China’s carbon emissions will reach 7.82 × 10² million and 25.61 × 10² million metric tons, with Shandong Province emerging as the foremost contributor. In summary, this research serves as a robust factual underpinning and an indispensable reference point for advancing the scientific underpinnings of China’s transition to a low-carbon economy and the judicious formulation of policies governing carbon emissions.

The successful launch of Landsat-9 marks a significant achievement in preserving the data legacy and ensuring the continuity of Landsat’s calibrated Earth observations. This study comprehensively assesses the continuity of reflectance and the Normalized Difference Vegetation Index (NDVI) between Landsat-8 and Landsat-9 Operational Land Imagers (OLIs) over diverse Chinese landscapes. It reveals that sensor discrepancies minimally impact reflectance and NDVI consistency. Although Landsat-9’s top-of-atmosphere (TOA) reflectance is slightly lower than that of Landsat-8, small root-mean-square errors (RMSEs) ranging from 0.0102 to 0.0248 for VNIR and SWIR bands (and larger RMSE for NDVI at 0.0422) fall within acceptable ranges for Earth observation applications. Applying atmospheric corrections markedly enhances reflectance uniformity and brings regression slopes closer to unity. Further, Bidirectional Reflectance Distribution Function (BRDF) adjustments improve comparability, ensuring measurement reliability, and the NDVI maintains robust consistency across various reflectance types, time series, and land cover classes. These findings affirm Landsat-9’s success in achieving data continuity within the Landsat program, allowing interchangeable use of Landsat-8 and Landsat-9 OLI data for diverse Earth observation purposes. Future research may explore specific sensor correlations across different vegetation types and seasons while integrating data from complementary platforms, such as Sentinel-2, to enhance the understanding of data continuity factors.

Drought is a frequent global phenomenon. The occurrence of drought can affect the production of industry, agriculture and economic growth. Solar-induced chlorophyll fluorescence is a by-product of photosynthesis that can be used to monitor vegetation growth and drought. Traditional drought monitoring generally used solar-induced chlorophyll fluorescence anomalies and rarely used solar-induced chlorophyll fluorescence to establish an index. This study integrated solar-induced chlorophyll fluorescence and land surface temperature to establish a new solar-induced chlorophyll fluorescence drought index (SIF_DI). The new SIF_DI was subsequently used for monitoring drought in Huang-Huai-Hai plain from 2000 to 2018. Results showed that SIF_DI had negative correlation with areas affected by drought. In Hebei, Henan and Shandong provinces, the correlation coefficients were − 0.79, -0.54 and − 0.76 respectively. SIF_DI had positive correlation with crop yields (wheat and maize). The correlation coefficients were 0.47, 0.61, 0.32 (wheat) and 0.69, 0.49, 0.36 (maize) respectively. All correlation coefficients surpassed those calculated using vegetation health index. Subsequently, the SIF_DI was applied to long-term drought monitoring during the crop growing season in Huang-Huai-Hai plain. This investigation proved that the new index calculated using solar-induced chlorophyll fluorescence is a reliable and effective indicator for monitoring and assessing drought.