# Combining Sentinel-1 and Sentinel-2 Time Series via RNN for object-based land cover classification

## TL;DR

This paper introduces a neural network architecture that effectively combines Sentinel-1 radar and Sentinel-2 optical satellite time series data at the object level for improved land cover classification, demonstrating its effectiveness on real-world data.

## Contribution

A novel neural architecture for integrating radar and optical satellite time series data at object level for land cover classification.

## Key findings

- Significant improvement in land cover classification accuracy.
- Effective integration of radar and optical data enhances results.
- Validated on Reunion Island dataset.

## Abstract

Radar and Optical Satellite Image Time Series (SITS) are sources of information that are commonly employed to monitor earth surfaces for tasks related to ecology, agriculture, mobility, land management planning and land cover monitoring. Many studies have been conducted using one of the two sources, but how to smartly combine the complementary information provided by radar and optical SITS is still an open challenge. In this context, we propose a new neural architecture for the combination of Sentinel-1 (S1) and Sentinel-2 (S2) imagery at object level, applied to a real-world land cover classification task. Experiments carried out on the Reunion Island, a overseas department of France in the Indian Ocean, demonstrate the significance of our proposal.