AI & ML New Capability

GeoNDC introduces a queryable neural data cube that compresses 20 years of planetary satellite data by 95x while allowing on-demand continuous-time reconstruction.

March 27, 2026

Original Paper

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

Jianbo Qi, Mengyao Li, Baogui Jiang, Yidan Chen, Qiao Wang

arXiv · 2603.25037

The Takeaway

By moving away from discrete raster files to implicit neural fields, it enables direct spatiotemporal queries on consumer hardware. This represents a shift for Earth Observation data, making petabyte-scale archives analysis-ready and accessible without massive decompression.

From the 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 globa