Home /Processing/Processes

Upsampling (Sentinel-2)

An algorithm that improves the spatial resolution of RGB bands in Sentinel-2 imagery.

Overview

The process upsamples the spatial resolution of the red, green, and blue (RGB) spectral bands in Sentinel‑2 imagery using convolutional neural networks.

The result is a GeoTIFF file with an upsampled spatial resolution of 3.20 m.

Upsampling can be used as a preprocessing step before change detection, vegetation detection, infrastructure detection, fire risk estimation, and land use management.

An input Sentinel-2 image of California (USA)
An upsampled output image

General

Specification Description
Provider Nara Space
Process type

Enhancement from 3 credits per km2

Requirements for input imagery

Input data items must be added to storage in 2023 or later.

CollectionData product

Sentinel‑2

Catalog: Level 2A

Input parameters

Use the upsampling-ns-sentinel name ID for the processing API.

JSON
{
  "inputs": {
    "title": "Processing imagery over Berlin",
    "item": "https://api.up42.com/v2/assets/stac/collections/21c0b14e-3434-4675-98d1-f225507ded99/items/23e4567-e89b-12d3-a456-426614174000"
  }
}
Parameter Overview
inputs.title string | required

The title of the output data item.
inputs.item string | required

The absolute API path to the input data item.

Learn more