Research
SPEAR NeXT Causal Latent Forecasting Across Multiple Horizons for Spectral Temporal Earth Representation Learning
arXiv:2609.16871v1 Announce Type: new Abstract: Earth observation is inherently dynamic, yet temporal information in many foundation models is learned through reconstruction, invariance, or retrospect
arXiv:2609.16871v1 Announce Type: new Abstract: Earth observation is inherently dynamic, yet temporal information in many foundation models is learned through reconstruction, invariance, or retrospective sequence summarization. SPEAR NeXT is introduced as a compact pixel-wise multimodal spectral temporal foundation model in which temporal self supervision is formulated as past only, multi horizon latent Earth state prediction. Instantaneous states are first encoded by the pretrained SPEAR model from optical, radar, and environmental observations into compact 32 dimensional embeddings. Their temporal evolution is then modeled by a causally masked Trans former that predicts multiple future latent states from pre ceding observations. Relative temporal order is represented using Rotary Position Embeddings, while month and year embeddings encode seasonal phase and interannual con text.
Related
- Densification and forecasting of Sentinel-2 time series from multimodal SAR and Optical satellite data using deep generative models
- Location Is All You Need: Continuous Spatiotemporal Neural Representations of Earth Observation Data
- Temporal Sensitivity Analysis of Tessera Embeddings
Source: arXiv cs.CV | 2026-09-16