JWJie Wang

Jie Wang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Jie Wang has a total of 109 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Global 30 m annual cropland extent dynamics (2000–2024): a harmonized baseline of structural evolution and regional disparities

    by Yuanhong Liao, Shuang Chen, Yuqi Bai, Jie Wang, Peng Gong

    Accurate annual information on cropland extent is essential for monitoring agricultural change, yet existing global products are often limited to snapshots or multiyear epochs and differ in their cropland definitions. Here we present GACED30, which, to our knowledge, is the first dedicated global 30 m annual cropland-extent dataset covering 2000–2024. The mapping framework combines gap-free SDC30 observations, spectral-semantic alignment of expert-annotated and spatially augmented samples, and rule-based spatial and temporal refinement. Independent classifiers were trained for each year using a common observation, feature, sample-construction, and modeling protocol, and the resulting annual record was used to derive pixel-level Cropping Frequency and 1 km Structural Evolution Indicators. Against independent stable-site FAST-Crop samples, GACED30 achieved an overall accuracy of 0.965 and an F 1 score of 0.844. Multitemporal assessments using GLAD Cropland and LUCAS reference samples showed higher recall and F 1 scores than GLC_FCS30D for both crop gain and crop loss, although the absolute transition scores remained modest. In a matched regional assessment in China, GACED30 achieved OA and F1 scores of 0.946 and 0.840, respectively, showing performance comparable with CACD. At the national scale, GACED30 agreed closely with definition-reconciled FAOSTAT statistics ( R 2 : 0.95; area-weighted direction match rate: 83.1 %). The sample-adjusted global cropland area was estimated at 1488.5 Mha in 2024, approximately 30.0 Mha higher than in 2000. Persistent expansion was concentrated in parts of Africa and South America, whereas stability and reduction were more widespread across much of the Global North. GACED30 provides a harmonized baseline for monitoring global cropland-extent dynamics and is publicly available at https://doi.org/10.5281/zenodo.18199675 (Chen et al., 2026).

  • Open Access

    Democratizing planetary-scale analysis: an ultra-lightweight Earth embedding database for accurate and flexible global land monitoring

    by Shuang Chen, Jie Wang, Shuai Yuan, Jiayang Li, Yu Xia, Yuanhong Liao, Junbo Wei, Jincheng Yuan, Xiaoqing Xu, Xiaolin Zhu, et al.

    The rapid evolution of satellite-borne Earth Observation (EO) systems has fundamentally revolutionized terrestrial monitoring, yielding comprehensive petabyte-scale archives. However, the immense computational resources and storage volumes required for global-scale analysis often preclude widespread use by many research teams, hindering broader scientific adoption and the execution of planetary-scale studies. To address these barriers, we present the Embedded Seamless Data (ESD), an ultra-lightweight, 30 m global Earth embedding database spanning the 25-year period from 2000 to 2024. By transforming high-dimensional, multi-sensor observations from the Landsat series (5, 7, 8, and 9) and MODIS Terra into information-dense, quantized latent vectors, ESD distils essential geophysical and semantic features into a unified latent space. Utilizing the ESDNet architecture and Finite Scalar Quantization (FSQ), the dataset achieves a transformative ∼ 340-fold reduction in data volume compared to raw daily archives. This compression allows the entire global land surface for a single year to be encapsulated within approximately 2.4 TB, enabling decadal-scale global analysis on standard local workstations. Rigorous validation demonstrates that ESD maintains high reconstructive fidelity to the original reflectance values across the spectral dimension, achieving a Mean Absolute Error (MAE) of 0.0130 (averaged over six spectral bands, including Blue, Green, Red, NIR, SWIR1, and SWIR2), a Root Mean Square Error (RMSE) of 0.0179, and a Correlation Coefficient (CC) of 0.8543. By condensing the annual phenological cycle into 12 temporal latent steps, the embeddings provide inherent denoising effects and a semantically organized latent space that outperforms raw reflectance data in downstream land-cover classification tasks, achieving a comparable and even higher overall accuracy of 79.74 % than the 76.92 % obtained using raw sensor fusion data on globally distributed land cover sample sets. With robust few-shot learning capabilities and longitudinal consistency across 25 years, the ESD product provides a versatile foundation for democratizing planetary-scale Earth system research and advancing next-generation geospatial artificial intelligence. The ESD dataset is freely available at https://doi.org/10.12436/iEarth.0000.20251229.000064.v1 (Chen, 2025).


  • Open Access

    Bridging Extreme Data Gaps: SAR-Optical Fusion Guided by Dual-Temporal SAR Differences

    by Zheng Ge, Xiaoqing Wang, Jie Wang, Ming Tao, Peng Qin, Xiaopeng Chao, Tianwu Lin, Yuting Zhu

    Continuous and complete optical observations are essential for agricultural monitoring, phenology analysis, and land-surface assessment. In subtropical and tropical regions, persistent large-scale thick cloud cover frequently causes extended periods with few available optical image pixels, making traditional cloud removal and optical reconstruction methods that depend on spatially and temporally adjacent cloud-free data inapplicable. Similarly, existing SAR-optical fusion and multi-temporal optical approaches require partially cloud-free target imagery. As a result, they become ineffective in scenarios with extreme cloud coverage ($\geq$80%) or during prolonged periods of optical data absence. To address this challenge, we propose TDSAR-DR, a dual-temporal SAR-difference-guided optical data reconstruction framework for reconstructing complete optical imagery at the target time without requiring any usable target-time optical observation as model input. Modulated Fusion (TV-SMF) module integrates reference optical information with time labels and temporal change cues extracted by a Time Difference Enhancement Module (TDEM). These dual-temporal SAR derived cues explicitly encode the direction and magnitude of land-surface dynamics, providing physically grounded guidance for a directionally informed and quantitatively consistent transformation toward the target time. Then, a SAR Guided Structural Refinement Module (SGR-M) exploits detailed SAR spatial cues to improve the structural fidelity and spectral consistency of the reconstructed target-time optical image, thereby producing robust results even when optical observations are missing for extended periods. Extensive experiments on subtropical farmland datasets show that TDSAR-DR achieves better qualitative and quantitative results under extreme cloud coverage, outperforming current SOTA SAR-optical fusion models. TDSAR-DR achieves a PSNR of 27.134 and SSIM of 0.947, surpassing other the state-of-the-art methods. More importantly, the framework enables reconstruct continuous cloud free time series, producing temporally consistent optical imagery when optical data are fully missing for long periods.

  • Open Access

    Wetland mapping from sparse annotations with satellite image time series and temporal-aware segment anything model

    by Shuai Yuan, Tianwu Lin, Shuang Chen, Yu Xia, Peng Qin, Xiangyu Liu, Xiaoqing Xu, Nan Xu, Hongsheng Zhang, Jie Wang, et al.


  • Make more pixels usable: A data-driven framework for customizable cloud and shadow processing in satellite imagery

    by Yu Xia, Tianwu Lin, Xiangyu Liu, Shuang Chen, Shuai Yuan, Geng Tian, Yang Xu, Wei Zhang, Wei He, Jie Wang, et al.

  • Open Access

    Detecting hidden plantations for future forestation potential on the Tibetan Plateau

    by Xiaoyi Wang, Xiaoyu Ding, Zhengchao Chen, Yongqing Bai, Xiaokai Qie, Zeqing Wang, Jie Wang, Qiang Liu, Shuang Chen, Siyu Li, et al.

    Accurate tree plantation mapping is crucial for optimizing limited land resources and informing future forestation efforts. However, detecting sparse plantations in mountain regions, such as the Tibetan Plateau, remains challenging due to spectral confusion with natural vegetation and terrain fragmentation. To address this, we propose PlantationNet, a multimodal deep learning framework that implements a coarse-to-fine classification strategy, fusing vertical structural signals (Sentinel-1 and GEDI), phenological features (Sentinel-2), and multi-decadal spectral dynamics (Landsat and MODIS), and refining spatial boundaries with high-resolution GaoFen-2 images. PlantationNet introduces three advances: an adaptive multi‐scale attention mechanism optimised for fragmented plantations in rugged terrain; a Real‐ESRGAN–based super‐resolution pipeline that captures subtle landcover change; and a pyramid‐fusion algorithm that downscales plantation boundaries from 30 m to 2 m. Applied across the Tibetan Plateau, PlantationNet maps 16,812 km² of planted forests (0.67% of the region) at 2 m resolution, with an F1 score of 0.93, outperforming state‐of‐the‐art models by 5–13% while improving computational efficiency. By integrating our plantation map with climate projections, we projected an additional 48,175 km² of climatically suitable land for future (~2100) plantations. Our framework offers a robust and scalable solution for detecting ecological restoration in remote mountain systems and guiding climate-resilient forestation in a changing climate.

  • Open Access

    Global 30-m annual cropland extent dynamics (2000–2024): A consistent baseline of structural evolution and regional disparities

    by Yuanhong Liao, Shuang Chen, Yuqi Bai, Jie Wang, Peng Gong

    Accurate quantification of the structural evolution of global agricultural systems is critical for assessing food security and monitoring planetary boundaries. However, current agricultural monitoring is hindered by a baseline that reflects the continuous, annual nature of agricultural management and distinguishes active cultivation cycles from permanent structural changes. Existing products typically rely on fragmented snapshots, multi-year aggregation, or generalized and inconsistent definitions (introducing systematic bias and noise into trend analysis). To bridge this gap, we generated the first Global 30-m Annual Cropland Extent Dynamics (GACED30) dataset (2000–2024). Our continuous mapping framework integrates the gap-free SDC30 to capture the intra-annual phenological transitions distinctive of active cultivation, employs a spectral-semantic sample alignment strategy to resolve the inconsistencies across different cropland sample sets, and applies a rule-based processing to mitigate the spectral ambiguity between active fallow and natural bareland. Furthermore, we derived grid-based Structural Evolution Indicators via continuous statistical trend analysis, utilizing the full 25-year time-series density to rigorously quantify expansion and abandonment trajectories. Comprehensive assessment demonstrates the reliability of GACED30, which achieves a high overall accuracy of 96.5 % and significantly outperforms existing global products (e.g., GLAD Cropland, ESA World Cover and GLC_FCS30D) in capturing temporal stability. Crucially, GACED30 exhibits strong agreement with FAO national statistics, achieving a high correlation in cropland area (R2:0.95) and an 81.1 % consistency in production trends. Based on this consistent baseline, we analyzed the structural evolution of global agriculture, estimating the 2024 cropland area at 1488.5 Mha with a net change rate of 1.2 Mha/year. Our trend analysis reveals a distinct global divergence: structural expansion is heavily concentrated in the Global South (e.g., Africa and South America), driven by commodity frontiers, whereas the Global North is characterized by widespread stability or policy-driven contraction. GACED30 thus provides a reliable evidence base for monitoring the changing footprint of global agriculture. The dataset is publicly available at https://doi.org/10.5281/zenodo.18199675 (Chen et al., 2025).


  • Open Access

    Democratizing planetary-scale analysis: An ultra-lightweight Earth embedding database for accurate and flexible global land monitoring

    by Shuang Chen, Jie Wang, Shuai Yuan, Jiayang Li, Yu Xia, Yuanhong Liao, Junbo Wei, Jincheng Yuan, Xiaoqing Xu, Xiaolin Zhu, et al.

    The rapid evolution of satellite-borne Earth Observation (EO) systems has fundamentally revolutionized terrestrial monitoring, yielding comprehensive petabyte-scale archives. However, the immense computational resources and storage volumes required for global-scale analysis often preclude widespread use by many research teams, hindering broader scientific adoption and the execution of planetary-scale studies. To address these barriers, we present the Embedded Seamless Data (ESD), an ultra-lightweight, 30-m global Earth embedding database spanning the 25-year period from 2000 to 2024. By transforming high-dimensional, multi-sensor observations from the Landsat series (5, 7, 8, and 9) and MODIS Terra into information-dense, quantized latent vectors, ESD distils essential geophysical and semantic features into a unified latent space. Utilizing the ESDNet architecture and Finite Scalar Quantization (FSQ), the dataset achieves a transformative ~340-fold reduction in data volume compared to raw daily archives. This compression allows the entire global land surface for a single year to be encapsulated within approximately 2.4 TB, enabling decadal-scale global analysis on standard local workstations. Rigorous validation demonstrates that ESD maintains high reconstructive fidelity to the original reflectance values across the spectral dimension, achieving a Mean Absolute Error (MAE) of 0.0130 (averaged over six spectral bands, including Blue, Green, Red, NIR, SWIR1, and SWIR2), a Root Mean Square Error (RMSE) of 0.0179, and a Correlation Coefficient (CC) of 0.8543. By condensing the annual phenological cycle into 12 temporal latent steps, the embeddings provide inherent denoising effects and a semantically organized latent space that outperforms raw reflectance data in downstream land-cover classification tasks, achieving a comparable and even higher overall accuracy of 79.74 % than the 76.92 % obtained using raw sensor fusion data on globally distributed land cover sample sets. With robust few-shot learning capabilities and longitudinal consistency across 25 years, the ESD product provides a versatile foundation for democratizing planetary-scale Earth system research and advancing next-generation geospatial artificial intelligence.


  • Surface reflectance in homogeneous regions follows a Gamma distribution: principles, validation and applications

    by Yuanhong Liao, Yuqi Bai, Yanping You, Jie Wang, Shuang Chen, Ming Lin, Jin Chen, Jing M. Chen, Bing Xu, Peng Gong