fullscreen

eFinder

eFinder

Tessera AI model offers accessible way to view Earth

Open Source vs. Closed Models Environmental Monitoring Artificial Intelligence in Earth Observation
headphones Listen to the eFinder podcast briefing
Ready to play
Daily briefing

What to know about Open Source vs. Closed Models

The article introduces Tessera, an open-source AI foundation model developed by the University of Cambridge and partners to compress Earth observation data from Copernicus satellites. It explains the model's technical benefits, its application in tracking habitat change in the UK, and compares it to other geospatial AI models like AlphaEarth, Thor, and TerraMind.

Propaganda risk 10%
Claims checked 19
Techniques found 2
Topics 3

Coverage spectrum

Coverage gap: Low Left coverage
Left0%
Center67%
Right33%

3 sources compared across this story cluster. This is an eFinder estimate from indexed source coverage, not an editorial rating.

What happened

Tessera AI model offers accessible way to view Earth Lisa Lock Scientific Editor Andrew Zinin Lead Editor A foundation model trained on Earth observation data from Copernicus Sentinel-1 and Sentinel-2 has been made widely available to researchers, it was…

Why it matters

Tessera, an advanced artificial intelligence (AI) model, offers high-accuracy datasets that encode what the satellite "sees" of Earth's surface during the course of a year.

Common ground

This compressed data can be used by the scientific community to generate information-rich maps.

Perspective signals

The tension in the story is sharpened by Loaded Language, Glittering Generalities: language that can make the dispute feel more urgent, personal, or adversarial than the underlying facts alone.


The article introduces Tessera, an open-source AI foundation model developed by the University of Cambridge and partners to compress Earth observation data from Copernicus satellites. It explains the model's technical benefits, its application in tracking habitat change in the UK, and compares it to other geospatial AI models like AlphaEarth, Thor, and TerraMind.

analyticsAnalysis

10%
Propaganda Score
confidence: 95%
Low risk. This article shows minimal use of propaganda techniques.

psychologyPropaganda Techniques Detected

eFinder identified 2 propaganda techniques in this article. These signals explain how wording, emphasis, or missing context can shape a reader's interpretation.

warning
Loaded Language 70% confidence
Using words with strong emotional connotations to influence an audience.
Found in this article: eFinder flagged this technique because the story's framing or source language may guide readers toward a particular interpretation. Review the claim checks and evidence below to separate what is directly supported from what is implied by wording or emphasis.
Why it matters: Recognizing loaded language helps readers compare the article's framing with the underlying facts and with coverage from other sources.
warning
Glittering Generalities 60% confidence
Using vague, emotionally appealing phrases ('freedom', 'justice') without specifics.
Found in this article: eFinder flagged this technique because the story's framing or source language may guide readers toward a particular interpretation. Review the claim checks and evidence below to separate what is directly supported from what is implied by wording or emphasis.
Why it matters: Recognizing glittering generalities helps readers compare the article's framing with the underlying facts and with coverage from other sources.

fact_checkClaims Checked

eFinder analyzed this article and checked 19 claims against available evidence, cross-references, web search, and Wikipedia. Here is what the fact-checking layer found.

schedule Pending 9
check_circle Corroborated 5
info Single Source 3
verified Verified 1
verified Verified By Reference 1
info
Claim 1: “The article is available on the arXiv preprint server.”
SINGLE SOURCE
While web results mention arXiv generally and other research papers on Academia.edu, there is no specific evidence provided in the search results confirming that the TESSERA paper specifically is hosted on arXiv.
travel_explore
web search NEUTRAL — The paper was publicly available on arXiv, so I thought submitting it to HuggingFace Daily Papers would be straightforward.The arXiv API can sometimes be slow, leading to indexing errors. This is a cr…
https://dredyson.com/fix-arxiv-indexing-failures-for-hugging…
travel_explore
web search NEUTRAL — AI Hot Research. ArXiv’s 1.7M+ Research Papers Now Available on Kaggle.To help make world’s largest free scientific paper repository even more accessible, arXiv announced yesterday that all of its res…
https://syncedreview.com/2020/08/06/arxivs-1-7m-research-pap…
travel_explore
web search NEUTRAL — View tessera Research Papers on Academia.edu for free.
https://www.academia.edu/Documents/in/tessera
verified
Claim 2: “The model itself was first launched in 2025”
VERIFIED
The ESA source explicitly states the model was first launched in 2025.
menu_book
wikipedia NEUTRAL — Steve Teig is an American business executive and entrepreneur, who became the chief executive officer of the technology company Perceive before it was acquired by Amazon. He was founder and/or Chief T…
https://en.wikipedia.org/wiki/Steve_Teig
menu_book
wikipedia NEUTRAL — Miwa Watabiki (綿引 美和, Watabiki Miwa; born January 13, 1968), better known by her stage name Chara (ちゃら), is a Japanese singer, actress and video jockey. She debuted in 1991 with the single Heaven. She…
https://en.wikipedia.org/wiki/Chara_(singer)
menu_book
wikipedia NEUTRAL — The murder of Gabriele Sandri is a crime that occurred on 11 November 2007 in Italy, in which the police officer Luigi Spaccarotella fired a gunshot on the A1 motorway near the Autogrill at Badia al …
https://en.wikipedia.org/wiki/Murder_of_Gabriele_Sandri
+ 3 more evidence sources
schedule
Claim 3: “Two foundation models to recently come out of Φ-lab are Thor, developed by the Norwegian Computing Center, and TerraMind, developed with IBM Research Europe.”
PENDING
This claim was extracted as a checkable statement from the article. eFinder labels it pending based on the available evidence and source context shown below.
schedule
Claim 4: “It was trained on a dataset of more than nine million globally distributed samples spanning eight complementary data types, including radar from Copernicus Sentinel-1 and optical Sentinel-2 imagery.”
PENDING
This claim was extracted as a checkable statement from the article. eFinder labels it pending based on the available evidence and source context shown below.
schedule
Claim 5: “This model was funded and supported through ESA's Foundation Models for Climate and Society (FM4CS) project.”
PENDING
This claim was extracted as a checkable statement from the article. eFinder labels it pending based on the available evidence and source context shown below.
check_circle
Claim 6: “Tessera processes huge amounts of remote-sensing data from the Copernicus missions, Sentinel-1 and Sentinel-2.”
CORROBORATED
Confirmed by ESA and the TESSERA research paper, which specifies the use of Sentinel-1 SAR and Sentinel-2 data.
travel_explore
web search NEUTRAL — Jul 25, 2025 ... TESSERA uses two separate, parallel Transformer-based encoders: one for Sentinel-1 SAR backscatter data in the C-band (VV and VH polarizations) ...
https://arxiv.org/html/2506.20380v2
travel_explore
web search NEUTRAL — Tessera processes huge amounts of remote-sensing data from the Copernicus missions, Sentinel-1 and Sentinel-2. It combines two types of data: optical data from ...
https://www.esa.int/Applications/Observing_the_Earth/Coperni…
travel_explore
web search NEUTRAL — Jun 25, 2025 ... We present TESSERA, a novel Remote Sensing Foundation Model (RSFM) that uses Self-Supervised Learning (SSL) to generate global, robust representations at 10m ...
https://www.researchgate.net/publication/393022337_TESSERA_T…
check_circle
Claim 7: “A paper on Tessera was presented at the 2026 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2026), held June 3–7.”
CORROBORATED
The claim is confirmed by Phys.org, ESA, and a CVPR 2026 papers list, all specifying the dates June 3-7, 2026.
travel_explore
web search NEUTRAL — A paper on Tessera was published at the 2026 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), held 3-7 June. ... launched in 2025 and ...
https://www.esa.int/Applications/Observing_the_Earth/Coperni…
travel_explore
web search NEUTRAL — Jun 1, 2026 ... The 2026 event will be held in Denver, starting June 3rd. To facilitate rapid community engagement with the presented research, we have ...
https://www.paperdigest.org/2026/06/cvpr-2026-papers-with-co…
travel_explore
web search NEUTRAL — Jun 4, 2026 ... A paper on Tessera was presented at the 2026 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2026), held June 3–7. The ...
https://phys.org/news/2026-06-tessera-ai-accessible-view-ear…
schedule
Claim 8: “It is open-source and aligned with FAIR principles (Findable, Accessible, Interoperable, Reusable)”
PENDING
This claim was extracted as a checkable statement from the article. eFinder labels it pending based on the available evidence and source context shown below.
schedule
Claim 9: “Thor... is trained on data from Sentinels 1, 2 and 3.”
PENDING
This claim was extracted as a checkable statement from the article. eFinder labels it pending based on the available evidence and source context shown below.
schedule
Claim 10: “ESA has also pioneered the development of foundation models trained on Earth observation data through its open innovation laboratory, Φ-lab”
PENDING
This claim was extracted as a checkable statement from the article. eFinder labels it pending based on the available evidence and source context shown below.
schedule
Claim 11: “TerraMind, a foundation model released in April 2025”
PENDING
This claim was extracted as a checkable statement from the article. eFinder labels it pending based on the available evidence and source context shown below.
info
Claim 12: “as an open-source project, it is freely modifiable”
SINGLE SOURCE
The provided evidence for this claim consists of irrelevant search results for 'Discount Tire' and does not mention the open-source status of Tessera.
travel_explore
web search NEUTRAL — 12 hours ago · Shop and order new tires and wheels online at the LOWEST prices with our famous customer service. Enjoy a shorter wait time in-store when you book and buy new tires and wheels online!
https://www.discounttire.com/
travel_explore
web search NEUTRAL — Privacy Policy Terms of Use Invoice Terms State Privacy Notice Your Privacy Choices Accessibility Statement Sustainability Site Map
https://www.discounttire.com/schedule-appointment
travel_explore
web search NEUTRAL — Shop tires by vehicle, tire size, type, and driving conditions. Compare all-season, all-terrain, winter, and performance tires from leading brands in one place. Enter your vehicle or tire size to see …
https://www.discounttire.com/tires-catalog
check_circle
Claim 13: “A foundation model trained on Earth observation data from Copernicus Sentinel-1 and Sentinel-2 has been made widely available to researchers”
CORROBORATED
The claim is explicitly confirmed by the ESA source and mentioned in the context of the TESSERA model's training data.
travel_explore
web search NEUTRAL — Aug 3, 2023 ... Based on NASA's Harmonized Landsat Sentinel-2 (HLS) data, the artificial intelligence (AI) foundation model is a milestone in the ...
https://www.earthdata.nasa.gov/news/nasa-ibm-openly-release-…
travel_explore
web search NEUTRAL — A foundation model trained on Earth observation data from Copernicus Sentinel-1 and Sentinel-2 has been made widely available to researchers, ...
https://www.esa.int/Applications/Observing_the_Earth/Coperni…
travel_explore
web search NEUTRAL — In this study, Sentinel-1 inputs are transformed into Sentinel-2 outputs using a learned mapping within a compact latent space. As illustrated in Fig. 1(b), the ...
https://www.sciencedirect.com/science/article/pii/S266601722…
schedule
Claim 14: “Researchers used Tessera embeddings to track habitat change on land designated for protection across Cumbria, an area of northern England.”
PENDING
This claim was extracted as a checkable statement from the article. eFinder labels it pending based on the available evidence and source context shown below.
check_circle
Claim 15: “The foundation model—Temporal Embeddings of Surface Spectra for Earth Representation and Analysis, or Tessera for short—was developed by researchers at the University of Cambridge in the U.K., alongside global and European partners, including Aalto University in Finland.”
CORROBORATED
The full name 'Temporal Embeddings of Surface Spectra for Earth Representation and Analysis' and the involvement of the University of Cambridge and Aalto University are confirmed by ESA and the TESSERA research papers.
travel_explore
web search NEUTRAL — Jul 25, 2025 ... In this work, we introduce TESSERA, an innovative Remote Sensing Foundation Model that provides ready-to-use embeddings with worldwide coverage ...
https://arxiv.org/html/2506.20380v2
travel_explore
web search NEUTRAL — The foundation model – Temporal Embeddings of Surface Spectra for Earth Representation and Analysis ... partners, including Aalto University in Finland.
https://www.esa.int/Applications/Observing_the_Earth/Coperni…
travel_explore
web search NEUTRAL — TESSERA advances the embedding-as-data approach for Earth Observation. It delivers (a) analysis-ready global-scale products, (b) pixel-wise, high-fidelity ...
https://anil.recoil.org/papers/2025-tessera.pdf
info
Claim 16: “It does this at a resolution of 10 m, which is the same as the highest resolution captured by Sentinel-2.”
SINGLE SOURCE
The PDF research paper for TESSERA explicitly mentions generating representations at 10m, which matches Sentinel-2's highest resolution. However, the Wikipedia results provided are irrelevant.
menu_book
wikipedia NEUTRAL — An Asian fetish is a strong sexual or romantic preference for people of Asian descent or heritage. The term usually refers to women specifically of East or Southeast Asian descent though it may also i…
https://en.wikipedia.org/wiki/Asian_fetish
menu_book
wikipedia NEUTRAL — The following is a comprehensive index of all games released in 2022, sorted chronologically by release date, and divided by quarter. Information regarding developer, publisher, operating system, gen…
https://en.wikipedia.org/wiki/List_of_video_games_released_i…
check_circle
Claim 17: “Tessera, an advanced artificial intelligence (AI) model, offers high-accuracy datasets that encode what the satellite "sees" of Earth's surface during the course of a year.”
CORROBORATED
Multiple sources, including ESA and the TESSERA research paper, confirm the model provides high-accuracy datasets/embeddings encoding Earth's surface observations.
travel_explore
web search NEUTRAL — Tessera, an advanced artificial intelligence (AI) model, offers high-accuracy datasets that encode what the satellite 'sees' of Earth's surface during the ...
https://www.esa.int/Applications/Observing_the_Earth/Coperni…
travel_explore
web search NEUTRAL — Aug 20, 2025 ... We present TESSERA, an open, global, land-oriented remote sensing foundation model that uses self-supervised learning to generate 'ready-to-use' ...
https://arxiv.org/html/2506.20380v4
travel_explore
web search NEUTRAL — It uses self-supervised learning to summarise petabytes of Earth observation data. We compare our work with state-of-the-art task-specific models and other ...
https://github.com/ucam-eo/tessera
verified
Claim 18: “The optical and radar datasets are fused by the foundation model and processed into global embeddings spanning each year from 2017 to 2025.”
VERIFIED BY REFERENCE
The provided Wikipedia results are completely irrelevant (political parties, Venus, Xperi) and do not contain information about Tessera's data fusion or date ranges.
menu_book
wikipedia NEUTRAL — This is a list of political parties by reported number of members. These reported membership numbers are usually claimed by the parties themselves and are not necessarily confirmed by independent stud…
https://en.wikipedia.org/wiki/List_of_largest_political_part…
menu_book
wikipedia NEUTRAL — The mapping of Venus refers to the process and results of human description of the geological features of the planet Venus. It involves surface radar images of Venus, construction of geological maps, …
https://en.wikipedia.org/wiki/Mapping_of_Venus
menu_book
wikipedia NEUTRAL — Xperi Inc. is an American multinational technology company headquartered in San Jose, California, that develops software for consumer electronics and connected cars, as well as media platforms for vid…
https://en.wikipedia.org/wiki/Xperi
schedule
Claim 19: “AlphaEarth Foundations, an AI model by Google DeepMind, which also compresses complex satellite data from multiple sources to create embeddings using a closed model.”
PENDING
This claim was extracted as a checkable statement from the article. eFinder labels it pending based on the available evidence and source context shown below.

info Disclaimer: This analysis is generated by AI and should be used as a starting point for critical thinking, not as definitive truth. Claims are verified against publicly available sources. Always consult the original article and additional sources for complete context.