Sharing your GeoSpatial Models , MLOps Architecture in fAIr
2026-09-01 , Conference Management Room1

We'll discuss recent advancements in fAIr. Specifically, we'll explore our approach to enabling developers to share their GeoAI models for humanitarian mapping purposes. We'll also dive into the development of our MLOps architecture, which leverages STAC, MLM, Zenml, and Kubernetes to run models independently in the cloud.


fAIr is a humanitarian Geo-AI platform by HOT that enables feature extraction from very high resolution aerial imagery (buildings, roads, trees) for OpenStreetMap mapping. This talk provides information about the ML infrastructure layer & recent developments in the platform . We will cover the STAC collections avilable , advantages of using standards while describing the model and integrating it to k8s


Level of technical complexity: 2 - intermediate Give indication of resources (video, web pages, papers, etc.) to read in advance, that will help get up to speed on advanced topics.:

https://hotosm.github.io/fAIr-models/

I make my conference contribution available under the CC BY 4.0 license. The conference contribution comprises the abstract, the text contribution for the conference proceedings, the presentation materials as well as the video recording and live transmission of the presentation:

Tech Lead @ HOTOSM. Working in the nexus of open geospatial and humantiarian action / global development.

This speaker also appears in:

Kshitij is a OpenSource GeoSpatial Developer , AI Engineer at HOTOSM & Active OSGeo member from OSGeo Nepal !