geoai
GeoAI: Artificial Intelligence for Geospatial Data
What is geoai?
GeoAI: Artificial Intelligence for Geospatial Data
Overview of geoai
What it is
GeoAI is a Python package that integrates artificial intelligence with geospatial data analysis and visualization. It provides a unified framework for processing satellite imagery, aerial photographs, and vector data using deep learning models. The package integrates PyTorch, Transformers, PyTorch Segmentation Models, and geospatial libraries like torchange. It offers six core capabilities: search and download of remote sensing imagery, automated dataset preparation, model training for classification/detection/segmentation, inference pipelines, interactive visualization with Leafmap and MapLibre, and QGIS integration via a dedicated plugin. GeoAI supports multiple data formats including GeoTIFF, JPEG2000, GeoJSON, Shapefile, and GeoPackage, and includes automatic GPU acceleration when available.
Key features
- Advanced Geospatial Data Visualization: interactive multi-layer visualization of vector and raster data from local or cloud storage, with customizable styling and time-series support.
- Data Preparation & Processing: streamlined access to satellite and aerial imagery from Sentinel, Landsat, NAIP, and other open datasets; tools for downloading, mosaicking, and preprocessing; automated training dataset generation with image chips and labels; vector-to-raster and raster-to-vector conversion; data augmentation; support for Overture Maps data.
- Image Segmentation: integration with PyTorch Segmentation Models for automatic feature extraction; reproducible k-fold segmentation training with site/scene grouping, loss- or IoU-based checkpoint selection, pooled out-of-fold metrics, and probability-averaged ensemble inference; export to GeoJSON, Shapefile, GeoPackage, GeoParquet.
- Image Classification: pre-trained models for land cover and land use classification; transfer learning utilities; multi-temporal classification for change detection; accuracy assessment tools.
- Remote Sensing Foundation Models: curated catalog of 20 remote sensing foundation models; filter by category, modality, or downstream task; retrieve metadata with
geoai.get_foundation_model_info(); load TerraTorch-supported model backbones withgeoai.load_foundation_model(). - Additional Capabilities: change detection with AI-enhanced feature extraction; object detection in aerial and satellite imagery; georeferencing utilities for AI model outputs.
Use cases
GeoAI is designed for geospatial researchers who need accessible AI workflows without deep machine learning expertise, AI practitioners who want streamlined geospatial preprocessing and domain-specific datasets, and educators seeking reproducible examples and teaching-ready workflows. Example applications include building footprint extraction from satellite imagery, land cover classification, change detection, and environmental monitoring.
Getting started
bashpip install geoai-py``````bashconda install -c conda-forge geoai``````bashmamba install -c conda-forge geoai
License and pricing
GeoAI is free and open source software, licensed under the MIT License. The pricing type is open source.
Based on the project's public README and repository metadata.