# Multi-sensor spatiotemporal fusion - gap-filling
*analysis . methodologies*

Reconstructs dense time-series by blending high-frequency coarse-resolution and low-frequency fine-resolution observations; good for crop phenology tracking and cloud-gap filling.

## Specifications
- **family**: Fusion
- **requirements envelope**: {"kind":"fusion","integration_pattern":"spatiotemporal-blending"}
- **entity type**: methodology
- **last verified date**: 2026-05-22
- **verified by**: sw
- **claim status**: unclaimed
- **subtype**: analysis
- **attributes**: {"family":"Fusion","summary":"Reconstructs dense time-series by blending high-frequency coarse-resolution and low-frequency fine-resolution observations; good for crop phenology tracking and cloud-gap filling.","requirements_envelope":"{\"kind\":\"fusion\",\"integration_pattern\":\"spatiotemporal-blending\"}","kind":"analysis"}

## Editorial
Algorithms such as STARFM or ESTARFM predict fine-resolution reflectance at unobserved dates by learning spatial-temporal relationships from paired image sets. [Wikipedia: Remote sensing](https://en.wikipedia.org/wiki/Remote_sensing)

## Sources
- [wikipedia] | Wikipedia: Remote sensing | https://en.wikipedia.org/wiki/Remote_sensing | tier=community | accessed=2026-05-22

---
Source: https://eo-atlas.org/methodologies/multisensor-spatiotemporal-fusion
Maintainer: SpectraWorks B.V. (CC-BY 4.0)