asterisk-labs/iris-datasets
Updated โข 124
AI & ML interests
Earth Observation, Climate, Environment, Interdiscipinary Science
Recent Activity
View all activity
csaybarย
updated a
dataset 9 days ago
csaybarย
published a
dataset 9 days ago
csaybarย
updated a
dataset 21 days ago
csaybarย
updated a
dataset 23 days ago
csaybarย
published a
dataset about 1 month ago
csaybarย
updated a
dataset about 1 month ago
csaybarย
published 2
datasets about 1 month ago
BBertozziย
updated a
Space 2 months ago
BBertozziย
updated a
dataset 2 months ago
BBertozziย
published a
Space 3 months ago
BBertozziย
published a
dataset 3 months ago
mikonvergenceย
posted an update 6 months ago
Post
266
๐ฅ Introducing BetaEarth - your own Earth embedding emulator [๐๐ซ๐-๐๐๐ฅ๐๐๐ฌ๐]
The past year has brought many notable embedding products, like AlphaEarth, TESSERA or OlmoEarth. We are entering a phase where embeddings begin to act as a substitute for real observation data.
BetaEarth is an attempt to explore how much one can learn from a model based on its embeddings alone, and whether those embeddings can serve as a useful training target for other models. Huge credit to the AlphaEarth team for releasing the embedding archive openly โ it's what made this kind of community-built extension possible.
[๐๐๐ญ๐๐๐๐ซ๐ญ๐ก ๐ข๐ฌ ๐ง๐จ๐ญ ๐ ๐๐จ๐ฎ๐ง๐๐๐ญ๐ข๐จ๐ง ๐ฆ๐จ๐๐๐ฅ ๐๐ฎ๐ญ ๐ข๐ญ ๐ญ๐ซ๐ข๐๐ฌ ๐ข๐ญ๐ฌ ๐๐๐ฌ๐ญ]
BetaEarth is a flexible (and relatively lightweight) emulator of the AlphaEarth annual product. It doesn't reproduce AlphaEarth's exact outputs, nor the product, but it reaches ~0.87 cosine similarity on held-out data and retains 97% of downstream land-cover classification accuracy. It only took 1-2 days to train.
It can encode any combination (including multi-temporal) of:
- Sentinel-2 L1C
- Sentinel-2 L2A
- Sentinel-1 RTC
- COP-DEM 30 product
The model weights are open, just like its training data (built exclusively using Major TOM). The GitHub repository provides a script for automated generation of embeddings across any footprint.
You can also try the workflow over small bounding boxes on the free Hugging Face web app!
โ๏ธ GitHub: https://github.com/asterisk-labs/beta-earth
๐ฅ๏ธ Web App: asterisk-labs/betaearth
๐ญ Models: https://huggingface.co/collections/asterisk-labs/beta-earth
๐จ Colab: https://colab.research.google.com/github/asterisk-labs/beta-earth/blob/main/examples/generate_demo.ipynb
๐๏ธ Pre-print: https://github.com/asterisk-labs/beta-earth/blob/main/docs/beta_earth_preprint.pdf
The past year has brought many notable embedding products, like AlphaEarth, TESSERA or OlmoEarth. We are entering a phase where embeddings begin to act as a substitute for real observation data.
BetaEarth is an attempt to explore how much one can learn from a model based on its embeddings alone, and whether those embeddings can serve as a useful training target for other models. Huge credit to the AlphaEarth team for releasing the embedding archive openly โ it's what made this kind of community-built extension possible.
[๐๐๐ญ๐๐๐๐ซ๐ญ๐ก ๐ข๐ฌ ๐ง๐จ๐ญ ๐ ๐๐จ๐ฎ๐ง๐๐๐ญ๐ข๐จ๐ง ๐ฆ๐จ๐๐๐ฅ ๐๐ฎ๐ญ ๐ข๐ญ ๐ญ๐ซ๐ข๐๐ฌ ๐ข๐ญ๐ฌ ๐๐๐ฌ๐ญ]
BetaEarth is a flexible (and relatively lightweight) emulator of the AlphaEarth annual product. It doesn't reproduce AlphaEarth's exact outputs, nor the product, but it reaches ~0.87 cosine similarity on held-out data and retains 97% of downstream land-cover classification accuracy. It only took 1-2 days to train.
It can encode any combination (including multi-temporal) of:
- Sentinel-2 L1C
- Sentinel-2 L2A
- Sentinel-1 RTC
- COP-DEM 30 product
The model weights are open, just like its training data (built exclusively using Major TOM). The GitHub repository provides a script for automated generation of embeddings across any footprint.
You can also try the workflow over small bounding boxes on the free Hugging Face web app!
โ๏ธ GitHub: https://github.com/asterisk-labs/beta-earth
๐ฅ๏ธ Web App: asterisk-labs/betaearth
๐ญ Models: https://huggingface.co/collections/asterisk-labs/beta-earth
๐จ Colab: https://colab.research.google.com/github/asterisk-labs/beta-earth/blob/main/examples/generate_demo.ipynb
๐๏ธ Pre-print: https://github.com/asterisk-labs/beta-earth/blob/main/docs/beta_earth_preprint.pdf
mikonvergenceย
authored 2
papers 7 months ago
mikonvergenceย
posted an update about 1 year ago
Post
543
๐๐๐ฃ๐จ๐ซ ๐๐๐ โ ๐๐จ๐จ๐ ๐ฅ๐ ๐๐๐๐ฉ๐๐ข๐ง๐'๐ฌ ๐๐ฅ๐ฉ๐ก๐๐๐๐ซ๐ญ๐ก ๐๐ฆ๐๐๐๐๐ข๐ง๐ ๐ฌ ๐๐ซ๐ ๐ง๐จ๐ฐ ๐๐ฏ๐๐ข๐ฅ๐๐๐ฅ๐ โผ๏ธ
This is a tiny (about 6 TB of data, but only 62,489 grid cells of ~100 sqkm) prototype dataset that allows to instantly connect existing Major TOM data with AlphaEarth embeddings.
Major-TOM/Core-AlphaEarth-Embeddings
I curated it to support several relevant research projects, but I figured it could help more people in the community to experiment and explore new applications of AlphaEarth.
๐๐ข๐ซ๐๐๐ญ๐ข๐จ๐ง๐ฌ ๐๐จ๐ซ ๐๐ฌ๐
Each embedding sample comes from the original annual dataset produced by Google DeepMind. It means that, unlike samples from Sentinel-2 or Sentinel-1, it contains aggregated annual information from a particular year and is not linked to one particular observation. The existing Major TOM samples from physical sensors provide information potentially (and likely) contained in the AlphaEarth embedding sample, but they miss the temporal component represented within AEF embedding fields.
For more information, please check the dataset card on HuggingFace.
โ ๏ธ ๐๐๐๐๐๐๐: ๐๐ฆ๐๐๐๐๐ข๐ง๐ ๐ฌ ๐ข๐ง ๐ญ๐ก๐ข๐ฌ ๐๐๐ญ๐๐ฌ๐๐ญ ๐๐จ ๐ง๐จ๐ญ ๐ซ๐๐ฉ๐ซ๐๐ฌ๐๐ง๐ญ ๐ข๐ง๐๐ข๐ฏ๐ข๐๐ฎ๐๐ฅ ๐ฌ๐๐ฆ๐ฉ๐ฅ๐๐ฌ, ๐๐ฎ๐ญ ๐ ๐ฐ๐ก๐จ๐ฅ๐ ๐ฒ๐๐๐ซ ๐จ๐ ๐ฆ๐ฎ๐ฅ๐ญ๐ข-๐ฆ๐จ๐๐๐ฅ ๐จ๐๐ฌ๐๐ซ๐ฏ๐๐ญ๐ข๐จ๐ง๐ฌ. ๐๐๐ฏ๐ ๐๐ฎ๐ง!
๐ Built on top of fantastic work of
Christopher Brown, Michal Kazmierski, Valerie Pasquarella, Emily Schechter and others at Google DeepMind.
This is a tiny (about 6 TB of data, but only 62,489 grid cells of ~100 sqkm) prototype dataset that allows to instantly connect existing Major TOM data with AlphaEarth embeddings.
Major-TOM/Core-AlphaEarth-Embeddings
I curated it to support several relevant research projects, but I figured it could help more people in the community to experiment and explore new applications of AlphaEarth.
๐๐ข๐ซ๐๐๐ญ๐ข๐จ๐ง๐ฌ ๐๐จ๐ซ ๐๐ฌ๐
Each embedding sample comes from the original annual dataset produced by Google DeepMind. It means that, unlike samples from Sentinel-2 or Sentinel-1, it contains aggregated annual information from a particular year and is not linked to one particular observation. The existing Major TOM samples from physical sensors provide information potentially (and likely) contained in the AlphaEarth embedding sample, but they miss the temporal component represented within AEF embedding fields.
For more information, please check the dataset card on HuggingFace.
โ ๏ธ ๐๐๐๐๐๐๐: ๐๐ฆ๐๐๐๐๐ข๐ง๐ ๐ฌ ๐ข๐ง ๐ญ๐ก๐ข๐ฌ ๐๐๐ญ๐๐ฌ๐๐ญ ๐๐จ ๐ง๐จ๐ญ ๐ซ๐๐ฉ๐ซ๐๐ฌ๐๐ง๐ญ ๐ข๐ง๐๐ข๐ฏ๐ข๐๐ฎ๐๐ฅ ๐ฌ๐๐ฆ๐ฉ๐ฅ๐๐ฌ, ๐๐ฎ๐ญ ๐ ๐ฐ๐ก๐จ๐ฅ๐ ๐ฒ๐๐๐ซ ๐จ๐ ๐ฆ๐ฎ๐ฅ๐ญ๐ข-๐ฆ๐จ๐๐๐ฅ ๐จ๐๐ฌ๐๐ซ๐ฏ๐๐ญ๐ข๐จ๐ง๐ฌ. ๐๐๐ฏ๐ ๐๐ฎ๐ง!
๐ Built on top of fantastic work of
Christopher Brown, Michal Kazmierski, Valerie Pasquarella, Emily Schechter and others at Google DeepMind.
mikonvergenceย
authored 2
papers over 1 year ago
mikonvergenceย
posted an update over 1 year ago
Post
889
๐ต ๐๐๐-๐๐๐-๐๐๐ญ๐: ๐๐ง๐ข๐๐ข๐๐ ๐๐๐ง๐๐ซ๐๐ญ๐ข๐ฏ๐ ๐๐จ๐๐๐ฅ๐ฅ๐ข๐ง๐ ๐จ๐ ๐๐๐๐๐ซ๐ง๐ข๐๐ฎ๐ฌ ๐๐ฆ๐๐ ๐๐ซ๐ฒ ๐๐ก๐ฎ๐ฆ๐๐ง๐๐ข๐ฅ๐ฌ
Today we release a prototype of COP-GEN - a universal generative model for Copernicus data. ๐๐๐-๐๐๐-๐๐๐ญ๐ is a model trained globally on the thumbnails of the Major TOM Core datasets, including Sentinel-2 L1C, Sentinel-2 L2A, Sentinel-1 RTC, and COP-DEM GLO-30.
โ๏ธ ๐๐จ๐๐๐ฅ mespinosami/COP-GEN-Beta
๐ฑ ๐๐๐ฆ๐จ mikonvergence/COP-GEN-Beta
How is it universal? COP-GEN learns a joint generative process of all modalities, which means that it can reconstruct data from any subset of present observations. ๐๐ข๐ญ๐ก๐จ๐ฎ๐ญ ๐ญ๐ซ๐๐ข๐ง๐ข๐ง๐ ๐ฌ๐ฉ๐๐๐ข๐๐ข๐๐๐ฅ๐ฅ๐ฒ to perform any of these tasks it can be used to approximate:
โ Sentinel-1 to Sentinel-2 translation
โ Elevation estimation from Sentinel-2 or Sentinel-1
โ Atmospheric Correction (L1C to L2A pipeline)
โ Atmospheric Generation (L2A to L1C)
โ ...and any other task involving translation between the supported modalities
On its own, the model can be used as a useful prior for estimating the data likelihood distribution for Copernicus data. COP-GEN-Beta learns joint, conditional, and marginal distributions within a single unified backbone, allowing to flexibly sample any modality given any condition.
Why is it Beta? Because thumbnails are a low-cost representation of the data that scales well and we managed to develop this prototype quite fast. We are currently developing the more costly COP-GEN model that supports the original data. For now, we wanted to showcase the prototype and make it available to the community for a test!
๐ ๐๐๐๐ฌ๐ข๐ญ๐ https://miquel-espinosa.github.io/cop-gen
๐ป ๐๐จ๐๐ https://github.com/miquel-espinosa/COP-GEN-Beta
๐ ๐๐๐ฉ๐๐ซ https://arxiv.org/pdf/2504.08548
Today we release a prototype of COP-GEN - a universal generative model for Copernicus data. ๐๐๐-๐๐๐-๐๐๐ญ๐ is a model trained globally on the thumbnails of the Major TOM Core datasets, including Sentinel-2 L1C, Sentinel-2 L2A, Sentinel-1 RTC, and COP-DEM GLO-30.
โ๏ธ ๐๐จ๐๐๐ฅ mespinosami/COP-GEN-Beta
๐ฑ ๐๐๐ฆ๐จ mikonvergence/COP-GEN-Beta
How is it universal? COP-GEN learns a joint generative process of all modalities, which means that it can reconstruct data from any subset of present observations. ๐๐ข๐ญ๐ก๐จ๐ฎ๐ญ ๐ญ๐ซ๐๐ข๐ง๐ข๐ง๐ ๐ฌ๐ฉ๐๐๐ข๐๐ข๐๐๐ฅ๐ฅ๐ฒ to perform any of these tasks it can be used to approximate:
โ Sentinel-1 to Sentinel-2 translation
โ Elevation estimation from Sentinel-2 or Sentinel-1
โ Atmospheric Correction (L1C to L2A pipeline)
โ Atmospheric Generation (L2A to L1C)
โ ...and any other task involving translation between the supported modalities
On its own, the model can be used as a useful prior for estimating the data likelihood distribution for Copernicus data. COP-GEN-Beta learns joint, conditional, and marginal distributions within a single unified backbone, allowing to flexibly sample any modality given any condition.
Why is it Beta? Because thumbnails are a low-cost representation of the data that scales well and we managed to develop this prototype quite fast. We are currently developing the more costly COP-GEN model that supports the original data. For now, we wanted to showcase the prototype and make it available to the community for a test!
๐ ๐๐๐๐ฌ๐ข๐ญ๐ https://miquel-espinosa.github.io/cop-gen
๐ป ๐๐จ๐๐ https://github.com/miquel-espinosa/COP-GEN-Beta
๐ ๐๐๐ฉ๐๐ซ https://arxiv.org/pdf/2504.08548
- 1 reply
mikonvergenceย
posted an update over 1 year ago
Post
1,735
๐๐๐๐ ๐๏ธ ๐๐๐ฑ๐ญ-๐๐๐ฌ๐๐ ๐ญ๐๐ซ๐ซ๐๐ข๐ง ๐ ๐๐ง๐๐ซ๐๐ญ๐ข๐จ๐ง ๐ฆ๐จ๐๐๐ฅ
MESA is a novel generative model based on latent denoising diffusion capable of generating 2.5D representations (co-registered colour and depth maps) of terrains based on text prompt conditioning.
Work developed by Paul BorneโPons (@NewtNewt ) during his joint internship at
Adobe & ESA, and in collaboration with asterisk labs.
๐๏ธ ๐๐ซ๐จ๐ฃ๐๐๐ญ ๐๐๐ ๐ : https://paulbornep.github.io/mesa-terrain/
๐ ๐๐ซ๐๐ฉ๐ซ๐ข๐ง๐ญ : https://arxiv.org/abs/2504.07210
๐ค ๐๐จ๐๐๐ฅ ๐๐๐ข๐ ๐ก๐ญ๐ฌ : NewtNewt/MESA
๐พ ๐๐๐ญ๐๐ฌ๐๐ญ : Major-TOM/Core-DEM
๐ง๐ปโ๐ปโ๐๐จ๐๐ : https://github.com/PaulBorneP/MESA
๐๐ ๐๐ฉ๐๐๐: mikonvergence/MESA
MESA is a novel generative model based on latent denoising diffusion capable of generating 2.5D representations (co-registered colour and depth maps) of terrains based on text prompt conditioning.
Work developed by Paul BorneโPons (@NewtNewt ) during his joint internship at
Adobe & ESA, and in collaboration with asterisk labs.
๐๏ธ ๐๐ซ๐จ๐ฃ๐๐๐ญ ๐๐๐ ๐ : https://paulbornep.github.io/mesa-terrain/
๐ ๐๐ซ๐๐ฉ๐ซ๐ข๐ง๐ญ : https://arxiv.org/abs/2504.07210
๐ค ๐๐จ๐๐๐ฅ ๐๐๐ข๐ ๐ก๐ญ๐ฌ : NewtNewt/MESA
๐พ ๐๐๐ญ๐๐ฌ๐๐ญ : Major-TOM/Core-DEM
๐ง๐ปโ๐ปโ๐๐จ๐๐ : https://github.com/PaulBorneP/MESA
๐๐ ๐๐ฉ๐๐๐: mikonvergence/MESA
- 2 replies