# satellite-image-deep-learning/techniques

Techniques for deep learning with satellite & aerial imagery

Repository: https://github.com/satellite-image-deep-learning/techniques
Canonical: https://ross.abutalabs.com/products/techniques
License: Apache-2.0
License Family: permissive
Topics: deep-learning, deep-neural-networks, satellite-imagery, pytorch, python, machine-learning, sentinel, satellite-images, dataset, remote-sensing, datasets, convolutional-neural-networks, image-classification, satellite-data, earth-observation, object-detection
Last push: 2026-08-02T12:18:31+00:00

## Health v2 (maintenance only)
Score: 66/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 95, release rhythm 8, longevity 100
- inputs: {"age_days": 3061, "days_push": 31, "days_rel": 424, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 10242, forks 1643 (observed 2026-08-28T04:10:41.225576+00:00)

## What it is
A curated reference repository cataloguing deep learning techniques, models, and datasets for satellite and aerial imagery analysis. It organizes resources by task such as classification, segmentation, object detection, change detection, and crop monitoring.

## Use cases
- find deep learning models for satellite image segmentation
- learn techniques for object detection in aerial imagery
- discover datasets for remote sensing research
- find approaches for cloud detection and removal in satellite images
- explore crop classification and yield forecasting methods
- find self-supervised learning resources for earth observation
- learn about SAR image analysis with deep learning

## When to choose
- you are starting a remote sensing or earth observation ML project and need an overview of available techniques
- you want curated links to models, papers, and datasets for satellite imagery tasks
- you need to compare approaches for tasks like change detection or image classification on aerial data

## When to avoid
- you need runnable production code rather than a curated list of links
- you are working with non-imagery data or general computer vision unrelated to aerial/satellite imagery

## Facets
- artifact type: learning-resource
- maturity: active
- function: deep-learning, machine-learning, image-processing, computer-vision, data-science
- domain: deep-learning, machine-learning, computer-vision, image-processing
- platform: python, cross-platform
- tags: satellite-imagery, remote-sensing, awesome-list, earth-observation, segmentation, object-detection, sentinel, aerial-imagery, pytorch, geospatial

## Member repositories
- satellite-image-deep-learning/techniques (main) score 66

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:41.225576+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:19:28.301362+00:00, confidence not recorded.
  - readme: https://github.com/satellite-image-deep-learning/techniques (fetched 2026-08-28T04:10:41.225576+00:00, sha ad721c0230c0)
- Data as of 2026-08-30T08:39:29.467469+00:00.