# Anaximander: Interactively Running Geospatial Deep Learning Models on Any Compute Backend

arXiv: https://arxiv.org/abs/2610.09085 · HTML: https://mlsanity.com/paper/2610.09085/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 2 of its 23 references that are in the map.
- First posted on arXiv 6 Oct 2026.

## Builds on (most cited first, 2 of 2)

- [The first global agricultural field boundary map at 10m resolution](https://mlsanity.com/paper/2605.11055/) (2026)
- [Evaluating AI-Driven Automated Map Digitization in QGIS](https://mlsanity.com/paper/2504.18777/) (2025)

## Abstract (arXiv)

Applying deep learning models to satellite imagery from within geographic information systems (GIS) remains high-friction for remote sensing practitioners. Models arrive in incompatible formats and target different compute environments, from local workstations to serverless cloud services. As a result, every evaluation demands custom deployment, tiling, and georeferencing code before a single prediction reaches the analyst's map. This friction discourages systematic comparison in a domain where model choice directly affects operational outcomes such as field delineation, crop monitoring, and disaster response. We present Anaximander, an open-source system that unifies model source and compute location choice behind one interactive interface. The system's backend is an inference server that loads models from multiple commonly-used sources and serves them on any accessible compute backend. The server provides session management and model caching, and streams results back per tile. The backend is paired with a QGIS plugin that drives tiling, result reassembly, georeferencing, and real-time per-tile status visualization. An additional user-interface path injects layer legends as prompts into vision-language models. We demonstrate the system in a code-free side-by-side comparison of three heterogeneous models on an agricultural field delineation task: gpt-image-1 via a cloud API, Segment Anything Model 3 (SAM3) on a remote GPU, and DelineateAnything on a local CPU. The inference backend and protocol are open-source and available at https://github.com/microsoft/nxmndr.