# BetaEarth: Open Embeddings of Sentinel-2 and Sentinel-1 with a Little Help of AlphaEarth

Page: https://stenobird.com/podcast/satellite-image-deep-learning-5989248/betaearth-open-embeddings-of-sentinel-2-and-sentinel-1-with-a-little-help-of-alphaearth
Text version: https://stenobird.com/podcast/satellite-image-deep-learning-5989248/betaearth-open-embeddings-of-sentinel-2-and-sentinel-1-with-a-little-help-of-alphaearth.md
Podcast: [Satellite image deep learning](https://stenobird.com/podcast/satellite-image-deep-learning-5989248)
Published: 2026-04-29T09:14:01+00:00
Episode link: https://www.satellite-image-deep-learning.com/p/betaearth-open-embeddings-of-sentinel
Audio file: https://api.substack.com/feed/podcast/195348103/9c791ca00ab396e1a48912c1acc0ff17.mp3
Processing state: not_requested
JSON: https://stenobird.com/v1/public/podcasts/satellite-image-deep-learning-5989248/episodes/betaearth-open-embeddings-of-sentinel-2-and-sentinel-1-with-a-little-help-of-alphaearth
Duration seconds: 1575

## Resource

In this episode I sat down with Mikolaj (Miko) Czerkawski from Asterisk Labs to explore BetaEarth, an experimental open-source emulator trained on AlphaEarth Foundations' public embedding archive. AEF — released by Google and Google DeepMind as a global 10 m embedding product derived from a wide range of Earth-observation modalities — is what makes BetaEarth possible: its openness lets the community build lightweight independent emulators that approximate AEF's pixelwise outputs from standard Sentinel inputs, and use them to probe how much of a model's behaviour is captured in its public embeddings. Miko walks through BetaEarth's design — compact architectures based on SegFormer-B2 with separate per-modality encoders, and a shared DINOv3 backbone over 3-band spectral primitives — and the surprising finding that reasonably strong approximations can be achieved even from simple RGB inputs.We then dive into a live demo: generating BetaEarth embeddings for arbitrary regions and time ranges using Sentinel-1, Sentinel-2, and COP-DEM data. Along the way, we cover practical considerations such as cloud contamination, modality trade-offs, tiling artefacts, and strategies for merging multi-temporal signals. Finally, we discuss what this complementary tooling enables for the geospatial ML community — embeddings as pretraining or regularisation signals, lightweight local inference alongside AEF's global annual rasters, and what the combination of large proprietary archives and open emulator-style tools could unlock next. * 📺 Video of this conversation & demo on YouTube * 🖥️ BetaEarth Github page * 🖥️ BetaEarth demo on Huggingface Bio: Miko is a researcher specialising in AI, computer vision, signal processing and Earth observation. Before co-founding Asterisk Labs he was a postdoc…

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/satellite-image-deep-learning-5989248/episodes/betaearth-open-embeddings-of-sentinel-2-and-sentinel-1-with-a-little-help-of-alphaearth/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/satellite-image-deep-learning-5989248/betaearth-open-embeddings-of-sentinel-2-and-sentinel-1-with-a-little-help-of-alphaearth.md` — Read the agent-friendly Markdown representation of this episode resource.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.