Anaximander: Interactively Running Geospatial Deep Learning Models on Any Compute Backend
Applying deep learning models to satellite imagery from within geographic information systems (GIS) remains high-friction for remote sensing practitioners.
ProofPaper ↗
Key points
- 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.
- 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.
Sources (1)
- [1]Anaximander: Interactively Running Geospatial Deep Learning Models on Any Compute BackendarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 08:31 PM
Applying deep learning models to satellite imagery from within geographic information systems (GIS) remains high-friction for remote sensing practitioners.
We present Anaximander, an open-source system that unifies model source and compute location choice behind one interactive interface.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 6, 2026What AI gets wrong and what failure teaches us
- Oct 3, 2026The Agent Said It Was Done. The Database Disagreed.
- Sep 30, 2026Forecasting space weather risks on power grids
- Sep 29, 2026Introducing Quine: An AI research system designed for the complexity of biology
- Sep 29, 2026microsoft/AesCode-32B
- Sep 28, 2026One year in: How Microsoft Research Asia – Singapore is advancing research, partnership and talent for real-world impact