# opengeos/geoai

GeoAI: Artificial Intelligence for Geospatial Data

Repository: https://github.com/opengeos/geoai
Canonical: https://ross.abutalabs.com/products/geoai
Homepage: https://opengeoai.org
Language: Python
License: MIT
License Family: permissive
Topics: ai, data-science, geoai, geopython, geospatial, jupyter, python, deep-learning, earth-observation, pytorch, remote-sensing, segmentation
Last push: 2026-08-24T03:04:38+00:00

## Health v2 (maintenance only)
Score: 89/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 83, longevity 79
- inputs: {"age_days": 1118, "days_push": 9, "days_rel": 39, "gap_med": 2.0, "n_releases_24m": 89}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3327, forks 472 (observed 2026-08-28T04:07:56.481504+00:00)

## What it is
GeoAI is a Python package that integrates artificial intelligence with geospatial data analysis, built on PyTorch, Transformers, and segmentation models. It provides end-to-end workflows for downloading imagery, preparing training data, training and running inference on geospatial models, and visualizing results in maps or QGIS.

## Use cases
- train a segmentation model on satellite imagery
- classify land cover from aerial photos
- download remote sensing data for analysis
- run object detection on geospatial rasters
- apply deep learning models to GeoTIFF imagery
- use AI workflows inside QGIS without coding
- zero-shot classify vector polygons with CLIP

## When to choose
- you need deep learning on satellite or aerial imagery in Python
- you want an end-to-end pipeline from data download to model inference
- you want interactive map visualization of AI results
- you prefer high-level APIs over writing raw PyTorch geospatial code

## When to avoid
- you only need classical GIS operations without machine learning
- you need a production web service for geospatial inference
- you work outside the Python ecosystem
- you lack a GPU and need large-scale training

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, image-processing, data-visualization, computer-vision
- domain: machine-learning, deep-learning, data-science
- platform: python, cross-platform
- tags: geospatial-ai, satellite-imagery, segmentation, remote-sensing, qgis-plugin, jupyter, pytorch, land-cover-classification, geospatial, gpu

## Member repositories
- opengeos/geoai (main) score 89

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:56.481504+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 2026-08-29T18:41:45.952893+00:00, confidence not recorded.
  - readme: https://github.com/opengeos/geoai (fetched 2026-08-28T04:07:56.481504+00:00, sha 717b07ea3f36)
  - homepage: https://opengeoai.org (fetched 2026-08-29T09:34:47.714586+00:00, sha 900d82c04c70)
  - site_page: https://opengeoai.org/installation (fetched 2026-08-29T09:34:47.724452+00:00, sha 70b68032a5f5)
  - site_page: https://opengeoai.org/examples/clip_classify_vector (fetched 2026-08-29T09:34:47.726570+00:00, sha 1e0f1edfe51b)
- Data as of 2026-08-30T08:39:29.467469+00:00.