GeoNDC: A Queryable Neural Data Cube for Planetary-Scale Earth Observation

2026-03-26

AI Summary

This work proposes the first queryable neural data cube for planetary-scale remote sensing, addressing the high storage, transmission, and querying costs of traditional Earth observation data stored as discrete raster grids, which hinder continuous spatiotemporal analysis. By encoding global observations into a continuous spatiotemporal implicit neural field, the method unifies highly efficient compression, on-demand querying, and lossless temporal reconstruction. Integrating implicit neural representations, continuous spatiotemporal parameterization, and spectral reflectance modeling, it achieves a 95:1 compression ratio (0.44 GB) on two decades of MODIS data with spectral R² > 0.98, cloud-gap-filled Sentinel-2 reconstruction with R² > 0.85, and HiGLASS product fidelity with R² > 0.98, establishing a new AI-native paradigm for remote sensing data representation.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Data Mining & Knowledge Management: Data Compression

Application Category

• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Satellite Earth observation has accumulated massive spatiotemporal archives essential for monitoring environmental change, yet these remain organized as discrete raster files, making them costly to store, transmit, and query. We present GeoNDC, a queryable neural data cube that encodes planetary-scale Earth observation data as a continuous spatiotemporal implicit neural field, enabling on-demand queries and continuous-time reconstruction without full decompression. Experiments on a 20-year global MODIS MCD43A4 reflectance record (7 bands, 5\,km, 8-day sampling) show that the learned representation supports direct spatiotemporal queries on consumer hardware. On Sentinel-2 imagery (10\,m), continuous temporal parameterization recovers cloud-free dynamics with high fidelity ($R^2 > 0.85$) under simulated 2-km cloud occlusion. On HiGLASS biophysical products (LAI and FPAR), GeoNDC attains near-perfect accuracy ($R^2 > 0.98$). The representation compresses the 20-year MODIS archive to 0.44\,GB -- approximately 95:1 relative to an optimized Int16 baseline -- with high spectral fidelity (mean $R^2 > 0.98$, mean RMSE $= 0.021$). These results suggest GeoNDC offers a unified AI-native representation for planetary-scale Earth observation, complementing raw archives with a compact, analysis-ready data layer integrating query, reconstruction, and compression in a single framework.

Problem

• Earth observation
• spatiotemporal data
• data cube
• query efficiency
• data compression

Innovation

• neural data cube
• implicit neural field
• spatiotemporal query
• planetary-scale Earth observation
• neural compression