Urban surface subsidence is primarily induced by intensive above-ground and underground construction activities and excessive groundwater extraction. Integrating InSAR techniques for safety monitoring of urban subway infrastructure is therefore of great significance for urban safety and sustainable development. However, single-track high-spatial-resolution SAR imagery is insufficient to achieve full coverage over large urban areas, and direct mosaicking of inter-track InSAR results may introduce systematic biases, thereby compromising the continuity and consistency of deformation fields at the regional scale. To address this issue, this study proposes an inter-track InSAR correction and mosaicking approach based on the mean vertical deformation difference within overlapping areas, aiming to mitigate the overall offset between deformation results derived from different tracks and to construct a spatially continuous urban surface deformation field. Based on the fused deformation results, subsidence characteristics along subway lines and in key urban infrastructures were further analyzed. The main urban area and the eastern and western new districts of Zhengzhou, a national central city in China, were selected as the study area. A total of 16 Radarsat-2 SAR scenes acquired from two tracks during 2022–2024, with a spatial resolution of 3 m, were processed using the SBAS-InSAR technique to retrieve surface deformation. The results indicate that the mean deformation rate difference in the overlapping areas between the two SAR tracks is approximately −5.54 mm/a. After applying the difference-constrained correction, the coefficient of determination (R2) between the mosaicked InSAR results and leveling observations increased to 0.739, while the MAE and RMSE decreased to 4.706 and 5.538 mm, respectively, demonstrating good stability in achieving inter-track consistency and continuous regional deformation representation. Analysis of the corrected InSAR results reveals that, during 2022–2024, areas exhibiting uplift and subsidence trends accounted for 37.6% and 62.4% of the study area, respectively, while the proportions of cumulative subsidence and uplift areas were 66.45% and 33.55%. In the main urban area, surface deformation rates are generally stable and predominantly within ±5 mm/a, whereas subsidence rates in the eastern new district are significantly higher than those in the main urban area and the western new district. Along subway lines, deformation rates are mainly within ±5 mm/a, with relatively larger deformation observed only in localized sections of the eastern segment of Line 1. Further analysis of typical zones along the subway corridors shows that densely built areas in the western part of the main urban area remain relatively stable, while building-concentrated areas in the eastern region exhibit a persistent relative subsidence trend. Overall, the results demonstrate that the proposed inter-track InSAR mosaicking method based on the mean deformation difference in overlapping areas can effectively support subsidence monitoring and spatial pattern identification along urban subway lines and key regions under relative calibration conditions, providing reliable remote sensing information for refined urban management and infrastructure risk assessment.

Urban vegetation is critical for climate regulation, ecological resilience, public mental health, and sustainable urban development. However, accurate delineation of vegetation within densely built environments remains challenging due to significant spectral confusion with impervious surfaces. To address this limitation, we introduce the Red-Edge Near-Infrared Urban Artificial Interference-Resistant Index (RENIUAI), a geometrically interpretable vegetation index derived from the Red Edge I/II-Near Infrared spectral space of Gaofen-6 (GF-6) imagery. By exploiting red-edge bands and calculating the signed Euclidean distance to an optimized decision boundary, RENIUAI enhances the separability of vegetation from spectrally similar non-vegetation surfaces. When incorporated as an explicit input into a UNet+ + deep learning segmentation framework, RENIUAI facilitates multiscale feature extraction and improves boundary fidelity, particularly for narrow, fragmented, and shadowed vegetation patches. Experiments conducted in the Jinshui District of Zhengzhou City, China, validated against high-resolution Gaofen-2 (GF-2) imagery, demonstrate that the RENIUAI-UNet+ + framework achieves an Overall Accuracy of 92.61 %, an F1-score of 0.8916, a Kappa coefficient of 0.8356, and a vegetation IoU of 0.8200. This performance surpasses traditional indices, such as NDVI, RVI, and DVI, by up to 4.31 % points while reducing false positives in impervious areas by over 60 %. Spatially, the framework generates more coherent vegetation maps, supporting the reliable estimation of key ecological indicators, including green coverage ratio, patch connectivity, and fragmentation metrics. By providing ecologically interpretable, transferable, and policy-relevant vegetation information, this study offers a robust and easily deployable tool for urban greening assessment, ecological planning compliance, and sustainable land-use management in rapidly urbanizing regions.

Aiming at the dual dilemma in high-resolution cropland change detection, where CNNs are constrained by limited local receptive fields and Transformers suffer from heavy computational costs, we propose LiteScan-Net, a lightweight and robust network architecture incorporating scanning principles from state-space modeling. The network innovatively introduces the Multi-Directional Global Scanning (MDGS) mechanism as an efficient engineering surrogate, which simulates the selective scanning process using large-kernel 1D convolutions. This achieves global context modeling with linear complexity while avoiding the hardware limitations imposed by recurrent computations. Based on this mechanism, a three-stage collaborative architecture is constructed: the Coordinate-Aware Feature Purification (CAFP) module is designed to mitigate shallow phenological noise via coordinate sensitivity; the Context Difference Verification (CDV) module aims to alleviate pseudo-changes caused by registration errors through global alignment; and the State-Space Guided Refinement (SSGR) module promotes the generation of change masks with precise boundaries and compact interiors. To verify the model generalization, we construct a Massive Specialized Cropland Change Detection dataset named MSCC, which exhibits significant cross-scale characteristics. Experimental results demonstrate that LiteScan-Net achieves state-of-the-art (SOTA) performance across the CLCD, Hi-CNA, and MSCC datasets, with F1-scores of 79.43%, 84.82%, and 89.62%, respectively. With a low computational cost of only 1.78 GFLOPs and a real-time inference speed of 37.9 FPS, LiteScan-Net demonstrates high potential for future deployment on resource-constrained edge devices.

Traditional monitoring of cropland non-agriculturalization heavily relies on land use/cover change data, which is constrained by long update cycles and the difficulty of accurately isolating the unidirectional conversion from cropland to non-agricultural uses. To address these limitations, this study utilizes a semantic change detection network with GaoFen-2 (GF-2) high-resolution time-series remote sensing imagery of Zhengzhou City from 2021 to 2025 as the primary data source. Integrating a land-use transfer matrix, grid cell analysis, spatial autocorrelation analysis, and the Geographic Detector model, we systematically analyze the spatiotemporal evolution dynamics and driving mechanisms of cropland non-agriculturalization in the region. The results demonstrate that: (1) Temporally, the intensity of cropland conversion in Zhengzhou City exhibits an unbalanced fluctuating pattern characterized by "initial intensity, subsequent stabilization, and localized rebound," with construction land being the absolute dominant destination of cropland outflow, resulting in a cumulative converted area exceeding 80 km² over the five-year period. (2) Spatially, cropland non-agriculturalization exhibits a distinct gradient pattern described as "commencing in the central urban core, highly aggregating in near suburbs, and dispersedly distributing with low intensity in far suburbs." Hot spot zones are heavily clustered in the near-suburb plains (e.g., Zhongmu County and Xinzheng City), whereas cold spot zones remain long-term stable in the western and southern hilly and mountainous regions (e.g., Dengfeng and Xinmi). The Global Moran's I indices are consistently positive and statistically significant, revealing pronounced spatial polarization and clustering features. (3) Regarding the driving mechanisms, cropland non-agriculturalization in Zhengzhou City is generally characterized by "transportation location dominance, industrial economic support, and topographical constraints."

The unchecked expansion of tea plantations onto steep, forest-adjacent slopes in subtropical mountains engenders a conflict between agricultural productivity and ecosystem integrity, particularly by exacerbating habitat fragmentation and soil erosion. While precise monitoring is essential to navigate this trade-off for sustainable management, accurate inventorying remains a challenge due to the plantations’ strong phenological variability, heterogeneous canopy structures, and high spectral confusion with surrounding vegetation. This study proposes a feature-optimized deep learning framework for mapping and characterizing tea plantations in complex landscapes, using Xinyang City, China, as a study area. The framework integrates multi-temporal Sentinel-1/2 observations with a sequential Jeffries-Matusita (JM)-Pearson feature filtering strategy. This approach effectively condenses a 132-variable high-dimensional pool (including optical spectra, vegetation indices, textures, and SAR polarimetry) into a compact 28-feature subset (a 78.8% reduction), preserving critical phenological and structural cues while minimizing redundancy. These optimized predictors drive a hybrid VGG16–UNet++ segmentation network, which couples transfer-learning-based semantic encoding with detail-preserving dense skip fusion. Extensive experiments across 18 model–feature configurations demonstrate that the optimal setting achieves an Overall Accuracy of 97.82%, an F1-score of 0.9093, and a mean IoU of 0.7968. Notably, the method significantly reduces misclassification in rugged, cloud-prone terrain, yielding a User’s Accuracy of 91.14% for tea. Based on the generated wall-to-wall map, we derived two decision-support indicators: multi-threshold steep-slope exposure and a normalized tea–forest interface density. This framework provides actionable, high-precision spatial products to support slope-based zoning, ecological restoration, and sustainable management in fragile mountain agroforestry systems.

Semantic Change Detection (SCD) in high-resolution remote sensing imagery is a core technology for quantifying land-cover transitions and supporting refined territorial management. Most existing SCD methods explicitly decouple the task into Semantic Segmentation (SS) and Change Detection (CD). However, this paradigm overlooks the inherent synergy between the two tasks in feature representation and optimization objectives, leading to ambiguous boundary localization and weak task interactions. To address these issues, we propose the Boundary-Task Collaborative Refinement Network (CoRe-SCD). First, a Boundary Refinement Module (BRM) is designed to explicitly inject edge priors into the CD branch, enabling precise dual refinement of spatial structures and semantic contours in changed regions. Second, a Cross-Task Interaction (CTI) module is proposed to model spatiotemporal dependencies via a cross-attention mechanism, achieving bidirectional feature enhancement and strict decoupling of semantic representations from change cues. Finally, a unified multi-task loss function is constructed to prevent over-optimization and maintain a strict equilibrium among the sub-tasks. Comprehensive experiments on two public datasets confirm that CoRe-SCD significantly outperforms other state-of-the-art (SOTA) methods, achieving an optimal balance between predictive accuracy and computational efficiency.

Accurate winter wheat mapping from satellite data is essential for food-security assessment and regional agricultural management, but is hampered by single-source imagery, feature redundancy and limited generalization. We propose a compact deep-learning framework that fuses multi-temporal Sentinel-1/2 data with JM-guided feature selection for county-scale winter wheat mapping. In Taikang County, Henan Province, a phenology-aware 124-dimensional feature set integrating spectral, index, texture and polarization descriptors is constructed, and the Jeffreys-Matusita distance is used to retain 46 discriminative features, reducing dimensionality by 62.9% while preserving class separability. Three segmentation networks-VGG16, UNet++ and a lightweight hybrid VGG16-UNet++-are evaluated; the hybrid model with JM-selected features performs best, achieving PA 90.53%, UA 90.90%, OA 96.99%, Kappa 0.9525, IoU 0.7883 and F1 0.9071 with moderate complexity. When directly transferred to neighbouring Biyang County without retraining, the hybrid network still yields accurate and spatially coherent winter wheat maps, providing initial evidence of cross-county transferability for regional monitoring.

Soil moisture is a key indicator of the global water cycle and terrestrial ecosystems, which is critical for drought monitoring and agricultural management for stronger scientific tone. Currently, soil moisture products obtained from remote sensing satellites have low spatial resolution, and soil moisture data derived using vegetation indices as downscaling factors exhibit significant temporal lag. Solar-induced chlorophyll fluorescence (SIF) provides direct information on vegetation physiology. Therefore, this paper reconstructs spatial-temporal SIF products. It proposes a downscaling method using multi-source remote sensing data that integrates vegetation physiological and structural characteristics. This method compares the downscaling performance of five machine learning approaches, including Support Vector Regression (SVR), XGBoost, Random Forest (RF), Deep Neural Networks (DNN), and a stacking ensemble. Multimodal data such as SIF, digital elevation models, soil properties, and albedo are used as predictor variables to select the optimal model for generating monthly Soil Moisture Active Passive (SMAP) soil moisture estimates at 1 km resolution. The downscaling results are validated against high-resolution soil moisture datasets (SSM and SMCI1.0), with their temporal consistency assessed against CHIRPS precipitation data. As a result, the RF model with SIF performs optimally, with an R² of 0.92. The downscaled product achieved a superior accuracy (R= 0.864), outperforming both the non-SIF downscaling result and the SSM product. Across all sites, correlations with collocated high-resolution values ranged from 0.6 to 1.0, with a minimum ubRMSE of 0.015 m³/m³. The downscaled SMAP soil moisture product exhibits enhanced spatial detail. The temporal correlation improved from 0.686 to 0.713 relative to vegetation index-based downscaling, indicating that SIF demonstrates superior applicability in SMAP soil moisture downscaling. This supports precise decision-making in agricultural drought monitoring and water resource management. This study proposes an SMAP soil moisture downscaling method based on Solar-induced chlorophyll fluorescence (SIF) and multi-source data fusion, aiming to downscale the coarse-resolution (9 km) SMAP soil moisture data to a 1 km spatial resolution monthly product. First, a Random Forest model was used to reconstruct the SIF data to both 1 km and 9 km resolutions, and the reconstructed SIF data were used as driving factors for soil moisture downscaling. The downscaling framework integrates multiple data sources, including Land Cover (LC), Normalized Difference Water Index (NDWI), Normalized Shortwave-Infrared Difference Soil Moisture Index (NSDSI), Apparent Thermal Inertia (ATI), Evapotranspiration (ET), Land Surface Temperature (LST), Albedo, soil properties (sand, silt, clay), Digital Elevation Model (DEM), slope, and precipitation data. During model training and evaluation, several machine learning algorithms, including Support Vector Regression (SVR), XGBoost, Random Forest (RF), Deep Neural Network (DNN), and Stacking ensemble model, were used. The results indicate that the RF model combined with SIF data performed the best, with an R² of 0.92, significantly outperforming the traditional vegetation index method (R² = 0.90). The high-resolution SMAP soil moisture product derived from the RF model showed significant improvements in spatial distribution and temporal dynamics capture.The innovation of this study lies in the introduction of SIF data to replace traditional vegetation indices, solving the time lag issue commonly associated with vegetation index methods. SIF provides a more direct and sensitive reflection of vegetation photosynthetic activity, enabling more accurate capture of soil moisture changes in dynamic processes. By integrating SIF with multi-source data, the study enhances the accuracy and timeliness of the soil moisture downscaling model, significantly improving the spatial resolution and temporal correlation of soil moisture products, providing more reliable monitoring tools for agricultural and water resource management. Introducing SIF as a physiological vegetation factor for soil moisture downscaling. SIF-based downscaling outperforms traditional vegetation index-based methods. A random forest model integrating SIF achieved superior performance. Generated a high-resolution (1 km) monthly SMAP soil moisture product. Fusing SIF with Random Forest effectively captures fine-scale soil moisture heterogeneity.

Accurate soybean mapping is critical for food–oil security and cropping assessment, yet spatiotemporal heterogeneity arising from fragmented parcels and phenological variability reduces class separability and robustness. This study aims to deliver a high-resolution, reusable pipeline and quantify the marginal benefits of feature selection and architecture design. We built a full-season multi-temporal Sentinel-1/2 stack and derived candidate optical/SAR features (raw bands, vegetation indices, textures, and polarimetric terms). Jeffries–Matusita (JM) distance was used for feature–phase joint selection, producing four comparable feature sets. We propose a lightweight APM-UNet: an Attention Sandglass Layer (ASL) in the shallow path to enhance texture/boundary details, and a Parallel Vision Mamba layer (PVML with Mamba-SSM) in the middle/bottleneck to model long-range/global context with near-linear complexity. Under a unified preprocessing and training/evaluation protocol, the four feature sets were paired with U-Net, SegFormer, Vision-Mamba, and APM-UNet, yielding 16 controlled configurations. Results showed consistent gains from JM-guided selection across architectures; given the same features, APM-UNet systematically outperformed all baselines. The best setup (JM-selected composite features + APM-UNet) achieved PA 92.81%, OA 97.95, Kappa 0.9649, Recall 91.42%, IoU 0.7986, and F1 0.9324, improving PA and OA by ~7.5 and 6.2 percentage points over the corresponding full-feature counterpart. These findings demonstrate that JM-guided, phenology-aware features coupled with a lightweight local–global hybrid network effectively mitigate heterogeneity-induced uncertainty, improving boundary fidelity and overall consistency while maintaining efficiency, offering a potentially transferable framework for soybean mapping in complex agricultural landscapes.

Solar-induced chlorophyll fluorescence (SIF), as a direct indicator of vegetation photosynthesis, offers a more accurate measure of plant photosynthetic dynamics than traditional vegetation indices. However, the current SIF satellite products have low spatial resolution, limiting their application in fine-scale agricultural research. To address this, we leveraged MODIS data at a 1 km resolution, including bands b1, b2, b3, and b4, alongside indices such as the NDVI, EVI, NIRv, OSAVI, SAVI, LAI, FPAR, and LST, covering October 2018 to May 2020 for Shandong Province, China. Using the Random Forest (RF) model, we downscaled SIF data from 0.05° to 1 km based on invariant spatial scaling theory, focusing on the winter wheat growth cycle. Various machine learning models, including CNN, Stacking, Extreme Random Trees, AdaBoost, and GBDT, were compared, with Random Forest yielding the best performance, achieving R2 = 0.931, RMSE = 0.052 mW/m2/nm/sr, and MAE = 0.031 mW/m2/nm/sr for 2018–2019 and R2 = 0.926, RMSE = 0.058 mW/m2/nm/sr, and MAE = 0.034 mW/m2/nm/sr for 2019–2020. The downscaled SIF products showed a strong correlation with TanSIF and GOSIF products (R2 > 0.8), and consistent trends with GPP further confirmed the reliability of the 1 km SIF product. Additionally, a time series analysis of Shandong Province’s wheat-growing areas revealed a strong correlation (R2 > 0.8) between SIF and multiple vegetation indices, underscoring its utility for regional crop monitoring.

This article proposes a multi-channel complementary change detection network (MCC-Net) integrating Convolutional Neural Network (CNN) and Transformer architectures. Firstly, a three-channel feature extraction module is designed for fully extracting the spatio-temporal features of the two-phase images. Then, a pyramid spatio-temporal cross-attention module is constructed to enhance the spatio-temporal features extracted with the CNN and Transformer by leveraging the interpolated features of the two-phase images to highlight the information of the changes. Finally, a multi-layered feature fusion module is proposed to further enhance the augmented features from the perspectives of both layers and channels. On the Henan Cultivated Land Change Dataset (HCLCD) and control change detection datasets (PX-CLCD, LuojiaSET-CLCD), the F1-score/Intersection over Union (IoU) values of MCC-Net reached 80.15%/65.02%, 95.50%/90.95%, and 72.50%/56.83%, respectively, which were significantly better than those of six state-of-the-art comparison methods. These results demonstrate that MCC-Net possesses a superior ability to identify within-class difference scenarios of cropland non-agriculturalization.

Leaf area index (LAI) assessment methods relying on physical and empirical models are considered to be the most commonly used method at present, but their estimation efficiency and accuracy are deficient. Although the hybrid model of these two methods can address these issues, a poor coupling mechanism can easily occur. Given that, a PROSAIL model coupling particle swarm optimization (PSO) neural network (NN) algorithm (PSO-NN-PROSAIL model) was introduced to invert the winter wheat LAI (WWLAI) at five distinct growth stages. The Xiangfu District in the east of Kaifeng City, Henan Province was served as the study region. Based on the measured WWLAI data at varying stages and GF-1 WFV satellite images, the initial analysis focused on assessing the PROSAIL model's sensitivity in simulating vegetation canopy reflectance. It then calculated six vegetation index models according to the wavelength reflectance of GF-1 WFV and analysed their correlation with LAI to select the input parameters that could be used in the model. Normalized differential vegetation Index (NDVI) and ratio vegetation Index (RVI) as well as vegetation canopy reflectance were employed as input parameters to invert the WWLAI by adopting the PSO-NN-PROSAIL model. The experimental results showed the following: (1) In the vegetation index model, the determination coefficient (R2) of NDVI and RVI was greater than 0.68, implying that NDVI and RVI might serve as input factors for the proposed model in this paper; (2) LAI and chlorophyll a + b content (Cab) were most sensitive to the PROSAIL model in near-infrared and visible light bands; and (3) the PSO-NN-PROSAIL model possessed better LAI inversion accuracy. In summary, the model proposed in this paper provided a technical reference for rapid and accurate remote sensing monitoring of WWLAI. The optimization technology of particle swarm optimization algorithm is integrated into the neural network, and the weight of the neural network is adjusted by its fitness function transformation and inertia weight.By integrating prior knowledge into the inversion of crop leaf area index constructed by machine learning and radiative transfer model, the ill-posed problem of physical model inversion has been improved.

Accurate monitoring of the leaf area index (LAI) and aboveground biomass (AGB) using remote sensing at a fine scale is crucial for understanding the spatial heterogeneity of vegetation structure in mountainous ecosystems. Understanding discrepancies in various retrieval strategies considering topographic effects or not is necessary to improve LAI and AGB estimations over mountainous areas. In this study, the performances of the look-up table method (LUT) using radiative transfer model (RTM), machine learning algorithms (MLAs), and hybrid RTM integrating RTM and MLAs based on Landsat surface reflectance (SR) before and after topographic correction were compared and analyzed. The results show that topographic correction improves the accuracies of retrieval methods involving RTM more significantly than the MLAs, meanwhile, it reduces the performance variability of different MLAs. Based on the topographically corrected Landsat SR, the random forest (RF) combined with RTM improves the retrieval accuracy of RTM-based LUT by 7.7% for LAI and 13.8% for AGB, and reduces the simulation error of MLA by 15.1% for LAI and 20.1% for AGB. Compared with available remote sensing products, the hybrid RTM based on Landsat SR with topographic correction has better feasibility to capture LAI and AGB variation at 30 m scale over mountainous areas.

Cities with sloping terrain are more susceptible to flooding during heavy rains. Traditional hydraulic models struggle to meet computational demands when addressing such emergencies. This study presented an integration of the one-dimensional Storm Water Management Model (SWMM) and the two-dimensional LISFLOOD-FP model, where the head difference at coupled manholes between the two models functioned as the connection. Based on its calculation results, this study extracted the characteristic parameters of the rainfall data, simplified the SVR calculation method and developed a high-efficiency solution for determining the maximum ponding depth. The cost time of this model was stable at approximately 1.0 min, 95% faster compared to the one from the mechanism model for 5 h simulation under the same working conditions. By conducting this case study in Jiujiang, China, the feasibility of this algorithm was well demonstrated.

This study aimed at alleviating the problems of unsatisfactory inversion accuracy and weak model stability in LAI remote sensing quantitative inversion. The properties and complex scattering mechanism of SAR data specify the polarization combinations and frequencies. This paper proposes an improved water cloud model combined with a deep neural network (MWCMLAI-Net) for high-precision inversion. The polarized GF-3 (C-band) and Lutan (L-band) were used to investigate the potential of SAR images to estimate LAI, a strong indicator of crop productivity. The study selected xiangfu district in the eastern part of Kaifeng City, Henan Province, as the test area and investigated the LAI of maize and rice. The $RVI_{Freeman}$RVIFreeman Model, backward scattering coefficient extracted by the modified cloud and water model (MWCM), and LAI obtained by the inversion of the MWCM were used as the inputs, and the MWCMLAI-Net inversion of the LAI was constructed. The results showed that the model's inverted LAI fitting accuracies of maize and rice for the three fertility periods were better than the other models, with R2 above 0.8516 and RMSE below 0.3999 m2/m2. The addition of noise did not affect the results.

Solar-induced chlorophyll fluorescence (SIF) is the release of plant energy during photosynthesis, which is significantly superior to the vegetation index in the characterization of vegetation growth. However, the existing satellite retrieved SIF data have the problems of low spatial resolution and spatial discontinuity. To solve these problems, this paper proposes multiple parameters downscaling method that considers the structural and physiological characteristics of SIF. Multiple linear regression (MLR), random forest (RF), and convolutional neural network (CNN) models were used to construct a downscaling model for the TROPOspheric Monitoring Instrument (TROPOMI) Enhanced SIF (eSIF) data. The theory of spatial scale invariance was applied to invert the 500 m spatial resolution SIF data products for Henan Province from 2012 to 2021 using Moderate-resolution Imaging Spectroradiometer (MODIS) data. The evaluation metrics for assessing downscaling accuracy include the determination coefficient (R2), mean absolute error (MAE), and root mean squared error (RMSE). The experimental results demonstrate that the RF model outperforms others, achieving R2, MAE, and RMSE values of 0.935, 0.041 mW/m2/nm2/sr, and 0.061 mW/m2/nm2/sr, respectively. These results successfully meet the downscaling requirements. The downscaling data products have better fitting effect with eSIF and new Global 'OCO-2 ' SIF (GOSIF) data both in time and space. The correlation between downscaling SIF data and winter wheat yield is significantly better than that of GOSIF data products and shows strong correlation with Gross Primary Productivity (GPP). By considering the structural and physiological characteristics of SIF, the RF algorithm can effectively retrieve reliable 500 m spatial resolution SIF data, this provides methodological support for the application of SIF data at higher spatial scales.

Declining cultivated land poses a serious threat to food security. However, existing Change Detection (CD) methods are insufficient for overcoming intra-class differences in cropland, and the accumulation of irrelevant features and loss of key features leads to poor detection results. To effectively identify changes in agricultural land, we propose a Difference-Directed Multi-scale Attention Mechanism Network (DDAM-Net). Specifically, we use a feature extraction module to effectively extract the cropland’s multi-scale features from dual-temporal images, and we introduce a Difference Enhancement Fusion Module (DEFM) and a Cross-scale Aggregation Module (CAM) to pass and fuse the multi-scale and difference features layer by layer. In addition, we introduce the Attention Refinement Module (ARM) to optimize the edge and detail features of changing objects. In the experiments, we evaluated the applicability of DDAM-Net on the HN-CLCD dataset for cropland CD and non-agricultural identification, with F1 and precision of 79.27% and 80.70%, respectively. In addition, generalization experiments using the publicly accessible PX-CLCD and SET-CLCD datasets revealed F1 and precision values of 95.12% and 95.47%, and 72.40% and 77.59%, respectively. The relevant comparative and ablation experiments suggested that DDAM-Net has greater performance and reliability in detecting cropland changes.

This study proposes a new method for integrating active and passive remote sensing data during critical reproductive periods in order to extract maize areas early and to address the problem of low accuracy in the classification of maize-growing areas affected by climate change. Focusing on Jiaozuo City, this study utilized active–passive remote sensing images to determine the optimal time for maize identification. The relative importance of features was assessed using a feature selection method combined with a machine learning algorithm, the impact of both single-source and multi-source features on accuracy was analyzed to generate the optimal feature subset, and the classification accuracies of different machine learning classification methods for maize at the tasseling stage were compared. Ultimately, this study identified the most effective remote sensing features and methods for maize detection during the optimal fertility period. The experimental results show that the feature set optimized for the tasseling stage significantly enhanced maize recognition accuracy. Specifically, the random forest (RF) method, when applied to the multi-source data fusion feature set, yielded the highest accuracy, improving classification accuracy by 24.6% and 4.86% over single-source features, and achieving an overall accuracy of 93.38% with a Kappa coefficient of 0.91. Data on the study area’s maize area were also extracted for the years 2018–2022, with accuracy values of 93.83%, 98.77%, 97%, and 98.05%, respectively.

The uneven distribution of global navigation satellite system (GNSS) continuous stations in the Yellow River Basin, combined with the sparse distribution of GNSS continuous stations in some regions and the weak far-field load signals, poses challenges in using GNSS vertical displacement data to invert terrestrial water storage changes (TWSCs). To achieve the inversion of water reserves in the Yellow River Basin using unevenly distributed GNSS continuous station data, in this study, we employed the Tikhonov regularization method to invert the terrestrial water storage (TWS) in the Yellow River Basin using vertical displacement data from network engineering and the Crustal Movement Observation Network of China (CMONOC) GNSS continuous stations from 2011 to 2022. In addition, we applied an inverse distance weighting smoothing factor, which was designed to account for the GNSS station distribution density, to smooth the inversion results. Consequently, a gridded product of the TWS in the Yellow River Basin with a spatial resolution of 0.5 degrees on a daily scale was obtained. To validate the effectiveness of the proposed method, a correlation analysis was conducted between the inversion results and the daily TWS from the Global Land Data Assimilation System (GLDAS), yielding a correlation coefficient of 0.68, indicating a strong correlation, which verifies the effectiveness of the method proposed in this paper. Based on the inversion results, we analyzed the spatial–temporal distribution trends and patterns in the Yellow River Basin and found that the average TWS decreased at a rate of 0.027 mm/d from 2011 to 2017, and then increased at a rate of 0.010 mm/d from 2017 to 2022. The TWS decreased from the lower-middle to lower reaches, while it increased from the upper-middle to upper reaches. Furthermore, an attribution analysis of the terrestrial water storage changes in the Yellow River Basin was conducted, and the correlation coefficients between the monthly average water storage changes inverted from the results and the monthly average precipitation, evapotranspiration, and surface temperature (AvgSurfT) from the GLDAS were 0.63, −0.65, and −0.69, respectively. This indicates that precipitation, evapotranspiration, and surface temperature were significant factors affecting the TWSCs in the Yellow River Basin.

Accurate and timely prediction of crop yields is crucial for ensuring food security and promoting sustainable agricultural practices. This study developed a winter wheat yield prediction model using machine learning techniques, incorporating remote sensing data and statistical yield records from Henan Province, China. The core of the model is an ensemble voting regressor, which integrates ridge regression, gradient boosting, and random forest algorithms. This study optimized the hyperparameters of the ensemble voting regressor and conducted an in-depth comparison of its yield prediction performance with that of other mainstream machine learning models, assessing the impact of key hyperparameters on model accuracy. This study also explored the potential of yield prediction at different growth stages and its application in yield spatialization. The results demonstrate that the ensemble voting regressor performed exceptionally well throughout the entire growth period, with an R2 of 0.90, an RMSE of 439.21 kg/ha, and an MAE of 351.28 kg/ha. Notably, during the heading stage, the model's prediction performance was particularly impressive, with an R2 of 0.81, an RMSE of 590.04 kg/ha, and an MAE of 478.38 kg/ha, surpassing models developed for other growth stages. Additionally, by establishing a yield spatialization model, this study mapped county-level yield predictions to the pixel level, visually illustrating the spatial differences in land productivity. These findings provide reliable technical support for winter wheat yield prediction and valuable references for crop yield estimation in precision agriculture.