Recent advances in machine learning have been supported by the emergence of domain-specific software libraries, enabling streamlined workflows and increased reproducibility. For geospatial machine learning (GeoML), the availability of Earth observation data has outpaced the development of domain libraries to handle its unique challenges, such as varying spatial resolutions, spectral properties, temporal cadence, data coverage, coordinate systems, and file formats. This chapter presents a comprehensive overview of GeoML libraries, analyzing their evolution, core functionalities, and the current ecosystem. It also introduces popular GeoML libraries such as TorchGeo, eo-learn, and Raster Vision, detailing their architecture, supported data types, and integration with ML frameworks. Additionally, it discusses common methodologies for data preprocessing, spatial--temporal joins, benchmarking, and the use of pretrained models. Through a case study in crop type mapping, it demonstrates practical applications of these tools. Best practices in software design, licensing, and testing are highlighted, along with open challenges and future directions, particularly the rise of foundation models and the need for governance in open-source geospatial software. Our aim is to guide practitioners, developers, and researchers in navigating and contributing to the rapidly evolving GeoML landscape.

This blog is accompanied by a Colab notebook which provides an in-depth look at how Raster Vision works and allows you to run each experiment discussed in this post yourself. Change detection is the computer-vision equivalent of the spot-the-difference game. Given two images, the model must detect all the points at which they differ. In the context of remote sensing, these images are usually satellite or aerial images of the same geographical location at two different points in time. Change detection has been an active research area for a long time and the literature is rich with algorithms that perform the task automatically, ranging from basic image processing techniques to present-day deep neural networks.

A satellite image is more than its pixels -- it is also its location. Typically encoded as a GeoTiff, such an image will also have georeferencing metadata -- such as coordinates, a coordinate system, and a projection transform -- that defines a mapping from pixel-based coordinates (ie. The same holds true for any annotations we might create for such an image -- these might take the form of GeoJSON files with vector annotations (eg. With the right tools, we can extract from these files a correctly transformed raster image and a corresponding label that we can happily feed into our computer vision models; but ultimately, to be useful in the real world, any insights gained from these models must also be mapped back to geographical locations. What use is detecting a wildfire if we don't know where it is?

In terms of raw data, the earth observation industry is undeniably exploding. Investments in freely available data from satellite constellations like MODIS, Landsat, and Sentinel have democratized access to timely satellite imagery of the entire globe (albeit at a lower resolution than you're accustomed to seeing on Google Maps). Meanwhile, cloud providers like AWS and Google Cloud have gone so far as to store satellite data for free, further accelerating global usage of these images. The trouble, naturally, is that interpreting the content of satellite imagery is not an easy task. In the field of remote sensing, researchers have been applying algorithmic techniques to the challenge of earth imagery interpretation for over 70 years.

We partnered with Driven Data and the World Bank to develop the Open Cities AI Challenge. This competition asks contestants to build semantic segmentation models that identify buildings in aerial imagery from several African cities. In other words, the goal is to automatically extract building footprints from each image. Contestants will be judged on the quality of their predictions and will be competing for a share of a combined $15,000 cash prize. Disaster relief efforts rely on accurate and up-to-date infrastructure maps.

This blog was coauthored by Lewis Fishgold and Rob Emanuele. Aerial and satellite imagery gives us the unique ability to look down and see the earth from above. It is being used to measure deforestation, map damaged areas after natural disasters, spot looted archaeological sites, and has many more current and untapped use cases. At Azavea, we understand the potential impact that imagery can have on our understanding of the world. We also understand that the enormous and ever-growing amount of imagery presents a significant challenge: how can we derive value and insights from all of this data? There are not enough people to look at all of the images all of the time.