Over the past decades, benefiting from the development of computing capacity and the free access to Landsat and Sentinel imagery, several fine-resolution global land cover (GLC) products (with a resolution of 10 m or 30 m) have been developed (GlobeLand30, FROM-GLC30, GLC_FCS30, FROM-GLC10, European Space Agency (ESA) WorldCover and ESRI Land Cover). However, there is still a lack of consistency analysis or comprehensive accuracy assessment using a common validation dataset for these GLC products. In this study, a novel stratified random sampling GLC validation dataset (SRS_Val) containing 79,112 validation samples was developed using a visual interpretation method, significantly increasing the number of samples of heterogeneous regions and rare land-cover types. Then, we quantitatively assessed the accuracy of these six GLC products using the developed SRS_Val dataset at global and regional scales. The results reveal that ESA WorldCover achieved the highest overall accuracy (of 70.54% ± 9%) among the global 10 m land cover products, followed by FROM-GLC10 (68.95% ± 8%) and ESRI Land Cover (58.90% ± 7%) and that GLC_FCS30 had the best overall accuracy (of 72.55% ± 9%) among the global 30 m land cover datasets, followed by GlobeLand30 (69.96% ± 9%) and FROM-GLC30 (66.30% ± 8%). The mapping accuracy of the GLC products decreased significantly with the increased heterogeneity of landscapes, and all GLC products had poor mapping accuracies in countries with heterogeneous landscapes, such as some countries in Central and Southern Africa. Finally, we investigated the consistency of six GLC products from the perspective of area distributions and spatial patterns. It was found that the area consistencies between the five GLC products (except ESRI Land Cover) were greater than 85% and that the six GLC products showed large discrepancies in area consistency for grassland, shrubland, wetlands and bare land. In terms of spatial patterns, the totally inconsistent pixel proportions of the 10 m and 30 m GLC products were 23.58% and 14.12%, respectively, and these inconsistent pixels were mainly distributed in transition zones, complex terrains regions, heterogeneous landscapes, or mixed land-cover types. Therefore, the SRS_Val dataset well supports the quantitative evaluation of fine-resolution GLC products, and the assessment results provide users with quantitative metrics to select GLC products suitable for their needs.

Accurate irrigated cropland mapping is critical for agricultural water management and food security. Existing image-based irrigation mapping workflows primarily rely on vegetation indices and synthetic aperture radar (SAR) backscatter features, which have limited capacity to characterize the temporal evolution of irrigation processes and crop growth conditions. The AlphaEarth Foundation (AEF) model developed by Google DeepMind provides compact embeddings with temporal semantic information learned via self-supervision, yet their utility for irrigation mapping has not been systematically assessed. In this study, a comprehensive assessment of AEF embeddings for irrigated cropland mapping was performed in terms of feature separability, classification performance, and spatiotemporal transferability. Experiments were conducted in two representative irrigated regions: the Guanzhong Plain in China and Kansas in the USA. Class separability of the 64 embedding dimensions was quantified using the Jeffries–Matusita (JM) distance. Then, the AEF embeddings were compared with the Sentinel feature set (Sentinel-2 bands, normalized difference vegetation index(NDVI), enhanced vegetation index(EVI), normalized difference water index(NDWI) and Sentinel-1 vertical transmit vertical receive(VV), vertical transmit horizontal receive(VH)) using K-means clustering and supervised classifiers, including Decision Tree (DT), Random Forest (RF), Gradient Boosting Decision Trees (GBDT), Support Vector Machine (SVM), and Multi-layer Perceptron (MLP). Finally, transfer experiments across 2022 and 2024 in the Guanzhong Plain and Kansas were conducted to examine cross-year and cross-region performance. The results showed that AEF embeddings consistently provide stronger class separability in both study areas, with a maximum JM distance of 1.58 (A29). Using AEF embeddings, RF achieved overall accuracies (OA) of 0.95 in the Guanzhong Plain and 0.93 in Kansas, outperforming models based on Sentinel-1/2 bands and indices. Notably, unsupervised K-means clustering on AEF embeddings yielded OA > 0.85, indicating high intrinsic separability between irrigated and rainfed croplands. Transfer experiments further demonstrate stable temporal transfer (cross-year OA > 0.87), whereas cross-region transfer is constrained by differences in irrigation regimes, crop phenology and management practices, resulting in limited spatial generalization (OA~0.3). Overall, this study demonstrates the potential of high-information-density representations from geospatial foundation models for irrigated cropland mapping and provides methodological and technical insights to support transfer learning and operational mapping over large areas.

Frequent climate changes and intense human activities increase the risk of vegetation destruction. Spectral index-based change detection can identify vegetation destruction from multi-temporal images, providing valuable insights for vegetation management and post-disaster recovery efforts. However, we still face the challenge of the spectral diversity of vegetation destruction and the complexity of the background environment. Existing spectral indices (VIs) often struggle to accurately detect vegetation destruction in complex scenarios. These VIs focus on specific aspects of vegetation, such as leaf, canopy or water content, limiting their effectiveness in capturing vegetation dynamics. In addition, they are susceptible to background environment changes. To overcome these challenges, this study proposes a new metric called Slope Vegetation Index (SVI) using bands that are sensitive vegetation leaf, canopy, and water content (i.e., green, near-infrared (NIR), and short-wave infrared (SWIR) bands). The performance of SVI was verified by the dual time-phase difference method, and five widely used VIs were selected for detailed comparison. In addition, the performance of SVI was evaluated using PROSAIL simulation data, various vegetation change scenarios, and real vegetation destruction cases. Moreover, we assessed the applicability of SVI to other multispectral sensors. The results showed that compared with existing VIs, SVI exhibited the highest sensitivity to vegetation changes under different chlorophyll and water content conditions. In various vegetation change scenarios and vegetation destruction cases, SVI consistently had the best performance, with Producer’s Accuracy (PA), User’s Accuracy (UA), and F1 scores all exceeding 0.90. In complex scenarios, SVI could better highlight vegetation changes while suppressing background environment changes. Additionally, SVI performed well on other Landsat-8/9 images, with an F1 score exceeding 0.89. This study confirms that SVI is valid for vegetation destruction detection and has potential for large-scale and high-frequency vegetation monitoring.

Maize cultivation significantly contributes to global food security and sustains human livelihoods. Efficient early-season maize mapping is pivotal for forecasting production and informed pre-harvest decisions. Existing approaches rely on prolonged phenological data or available crop labels, limiting their applicability in areas lacking comprehensive data. Thus, an automated, dynamic, and accurate maize identification method for the early growing season is crucial. This study explores spectral bands to distinguish maize early in terms of water content and chlorophyll levels. A novel composite index for dynamic maize identification independent of labels was proposed. Utilizing this index with a multi-temporal Gaussian Mixture Model facilitated early-season maize mapping and identification. Assessments across diverse global regions revealed the method's robustness, consistently achieving 90% accuracy and F1-score. NDCI outperformed other indices, enhancing F1-score by up to 30%. NDCI-mGMM accurately generated maize maps two months pre-harvest, promising an F1 score of at least 77%. Operating autonomously from labels, this framework offers swift and precise maize identification in data-deficient regions, revolutionizing global food security and trade forecasts.