paper-with-me

홈 › Papers

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

2026-01-16 · Shuang Chen, Jie Wang, Shuai Yuan, Jiayang Li, Yu Xia, Yuanhong Liao, Junbo Wei, Jincheng Yuan, Xiaoqing Xu, Xiaolin Zhu, Peng Zhu, Hongsheng Zhang, Yuyu Zhou, Haohuan Fu, Huabing Huang, Bin Chen, Fan Dai, Peng Gong arxiv

The rapid evolution of satellite-borne Earth Observation (EO) systems has revolutionized terrestrial monitoring, yielding petabyte-scale archives. However, the immense computational and storage requirements for global-scale analysis often preclude widespread use, hindering planetary-scale studies. To address these barriers, we present 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 distills 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 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 high reconstructive fidelity (MAE: 0.0130; RMSE: 0.0179; CC: 0.8543). By condensing the annual phenological cycle into 12 temporal steps, the embeddings provide inherent denoising and a semantically organized space that outperforms raw reflectance in land-cover classification, achieving 79.74% accuracy (vs. 76.92% for raw fusion). With robust few-shot learning capabilities and longitudinal consistency, ESD provides a versatile foundation for democratizing planetary-scale research and advancing next-generation geospatial artificial intelligence.

📄 PDF Abstract BibTeX arXiv:2601.11183

Code (0)

등록된 구현이 없습니다.

Tasks

Few-Shot Learning

Similar Papers 제목 키워드 기반

The Economics of Interstellar Flight

2021-12-27 · Philip Lubin, Alexander N. Cohen

Large scale directed energy offers the possibility of radical transformation in a variety of areas, including the ability to achieve relativistic flight that will enable the first interstellar missions, as well as rapid …

Natural Language-Driven Global Mapping of Martian Landforms

2026-01-22 · Yiran Wang, Shuoyuan Wang, Zhaoran Wei, Jiannan Zhao 외 arxiv

Planetary surfaces are typically analyzed using high-level semantic concepts in natural language, yet vast orbital image archives remain organized at the pixel level. This mismatch limits scalable, open-ended exploration…

Semantic Retrieval

MVSegNet: A Lightweight Boundary-Aware Network for Fetal Lateral Ventricle Segmentation and Atrial Width Estimation in Prenatal Ultrasound

2026-06-05 · Arafat Hossain Sayem arxiv

Fetal ventriculomegaly is assessed by measuring the atrial width of the lateral ventricle in prenatal ultrasound. Accurate segmentation is essential for this measurement, but acoustic shadowing, speckle noise, and poor c…

The Solar System: Nature and Mechanics

2021-10-16 · Anonymous

Origin, mechanics and properties of the Solar System are analyzed in the framework of Complete Relativity. The analysis confirms the postulates and hypotheses of the theory with a high degree of confidence. During the …

Democratizing GraphRAG: Linear, CPU-Only Graph Retrieval for Multi-Hop QA

2025-12-27 · Qizhi Wang arxiv

GraphRAG systems improve multi-hop retrieval by modeling structure, but many approaches rely on expensive LLM-based graph construction and GPU-heavy inference. We present SPRIG (Seeded Propagation for Retrieval In Graphs…