Location Is All You Need: Continuous Spatiotemporal Neural Representations of Earth Observation Data

TL;DR

LIANet is a coordinate-based neural model that represents multi-temporal Earth observation data as a continuous spatiotemporal field, enabling efficient downstream task adaptation without needing original satellite data.

Contribution

This work introduces LIANet, a neural representation that models EO data continuously and can be fine-tuned for various tasks without access to raw satellite imagery.

Findings

Pretrained LIANet can be adapted for downstream tasks with competitive performance.

Fine-tuning LIANet requires less data and computational resources than training from scratch.

The source code and datasets are publicly available at the provided GitHub URL.

Abstract

In this work, we present LIANet (Location Is All You Need Network), a coordinate-based neural representation that models multi-temporal spaceborne Earth observation (EO) data for a given region of interest as a continuous spatiotemporal neural field. Given only spatial and temporal coordinates, LIANet reconstructs the corresponding satellite imagery. Once pretrained, this neural representation can be adapted to various EO downstream tasks, such as semantic segmentation or pixel-wise regression, importantly, without requiring access to the original satellite data. LIANet intends to serve as a user-friendly alternative to Geospatial Foundation Models (GFMs) by eliminating the overhead of data access and preprocessing for end-users and enabling fine-tuning solely based on labels. We demonstrate the pretraining of LIANet across target areas of varying sizes and show that fine-tuning it for downstream tasks achieves competitive performance compared to training from scratch or using established GFMs. The source code and datasets are publicly available at https://github.com/mojganmadadi/LIANet/tree/v1.0.1.