Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Introducing OlmoEarth 🌍, state-of-the-art AI foundation models paired with ready-to-use open infrastructure to turn Earth data into clear, up-to-date insights within hours—not years.

Ai2

86,562 subscribers

680,546 views • 11 months ago •via X (Twitter)

Health & Wellness Science & Technology

Anya Rossi• Live Now

Private livecam show

26 Comments

Ai211 months ago

By applying AI to a planet’s worth of data, OlmoEarth Platform is already empowering communities to act faster & with confidence to secure a sustainable future. 🌲 OlmoEarth delivers intelligence to people on the ground for anything from aiding restoration efforts to protecting natural resources and communities.

Ai211 months ago

Under the hood is our industry-leading OlmoEarth foundation model family—AI that fuses 🛰️ satellite imagery, 📡 radar, ⛰️ elevation, & 🗺️ detailed map layers. Open, fast to adapt + deploy—industry-leading on key benchmarks and real-world applications for our partners. Learn more →

Ai211 months ago

OlmoEarth Platform is focused on impact across a range of sectors—agriculture, wildfire prevention, & more. 👇

Ai211 months ago

🔥 Wildfire deployments with @NASAJPL are mapping live fuel moisture at scale to inform readiness. Learn more →

Ai211 months ago

🇰🇪 With @IFPRI in Nandi County, Kenya & Mozambique, we built in-season crop-type maps to vastly improve seasonal planning + trusted info for officials. Learn more →

Ai211 months ago

@IFPRI 🌊 @MangrovesNow is using OlmoEarth to refresh mangrove map baselines faster, with higher accuracy & less manual annotation—allowing orgs + governments to respond to threats more quickly. Learn more →

Ai211 months ago

@IFPRI @MangrovesNow OlmoEarth available now. If you’re working in food security, wildfire resilience, or on sustainability and conservation initiatives, let’s talk. Get started → 💬 Discuss:

Vaibhav (VB) Srivastav11 months ago

Super cool release! 🔥

edgar11 months ago

holy shit this is cool

Florian Brand11 months ago

finally!!! 🔥

Roy11 months ago

89M parameter base model btw, thanks for keeping ai open

Alex Caswen8 months ago

Does this use CesiumJS ? What is your rendering layer ?

NexGen Cloud11 months ago

Game changer 👏

Jeroen Van Goey11 months ago

How does this compare to InstaGeo?

ghotoman🛡️11 months ago

gonna make deforestation alerts, crop health, and flood mapping actually timely, pin this.

Himanshu Kumar11 months ago

That's quite a leap, Ai! Using AI to speed up Earth data analysis is a brilliant idea, it's definitely the need of the hour, no?

FutureChain Insights(✸,✸)11 months ago

Turning complex Earth data into actionable insights in hours? This is exactly what we need to tackle climate challenges faster.

Rodrigo Sampaio11 months ago

@threadreaderapp unroll

Benedict Kerres11 months ago

very cool @pjreddie

Raghav11 months ago

This is huge, Earth data is notoriously fragmented and slow to process. If OlmoEarth can shorten that cycle, it changes how we respond to climate, agriculture, and infrastructure in real time

Softprobe.ai11 months ago

It defiantly looks amazing!

Vapor11 months ago

In laymen terms?

Min Chon Chi11 months ago

Reducing data processing from years to hours would be quite impactful.

Moods5811 months ago

Yep

Today in AI11 months ago

A 10TB multimodal foundation model is a *magnificent* data flex for real-time Earth observation! That latency reduction is the elegant, technical lever industrial applications have craved.

Lyceum11 months ago

Sounds promising! The blend of AI and Earth data could really change the game. Let’s see how well it delivers on those insights!

Related Videos

With Planet’s AI app, users can combine the power of AI with near-daily satellite data to explore what’s happening on Earth, uncover insights, and better understand change at scale. This is a glimpse into the future of Planetary Intelligence: transforming the world’s most comprehensive Earth data into actionable intelligence. Sign up today, in open beta now:

With Planet’s AI app, users can combine the power of AI with near-daily satellite data to explore what’s happening on Earth, uncover insights, and better understand change at scale. This is a glimpse into the future of Planetary Intelligence: transforming the world’s most comprehensive Earth data into actionable intelligence. Sign up today, in open beta now:

Planet

10,433 views • 1 month ago

Introducing CodeGuide You have an Idea to turn into Software? Use CodeGuide to turn that idea into proper developments documentation for AI coding models. AI Coding = Detailed Context + Clear Prompting. Build web apps, mobile apps, landing pages, extentions...

Introducing CodeGuide You have an Idea to turn into Software? Use CodeGuide to turn that idea into proper developments documentation for AI coding models. AI Coding = Detailed Context + Clear Prompting. Build web apps, mobile apps, landing pages, extentions...

CJ Zafir

153,193 views • 1 year ago

Today, we are introducing you to the Coraliser. 🪸 You can now turn any MCP server into an AI agent within seconds. Ready to connect to the Internet of Agents?

Today, we are introducing you to the Coraliser. 🪸 You can now turn any MCP server into an AI agent within seconds. Ready to connect to the Internet of Agents?

CoralOS

43,498 views • 1 year ago

Turn data into insights, faster. 🛰️ Aurora, Pixxel’s Earth observation studio, just got smarter. With Aurora Intelligence, its AI-powered assistant, you can ask questions in natural language, set up your Area of Interest, find the right indices/models to run, and interpret the outputs without navigating complex workflows. Explore now:

Turn data into insights, faster. 🛰️ Aurora, Pixxel’s Earth observation studio, just got smarter. With Aurora Intelligence, its AI-powered assistant, you can ask questions in natural language, set up your Area of Interest, find the right indices/models to run, and interpret the outputs without navigating complex workflows. Explore now:

Pixxel

10,885 views • 3 months ago

State-of-the-art robot policies often need hundreds of hours of data. What if we needed none? Introducing TiPToP: a manipulation system that zero-shots open-world tasks from pixels and language using vision foundation models and GPU-parallelized Task and Motion Planning (TAMP).

State-of-the-art robot policies often need hundreds of hours of data. What if we needed none? Introducing TiPToP: a manipulation system that zero-shots open-world tasks from pixels and language using vision foundation models and GPU-parallelized Task and Motion Planning (TAMP).

Nishanth Kumar

79,566 views • 7 months ago

Introducing AI Codex: the self-improving system for Cursor. ◆ Error and learning repository. ◆ Auto-save new insights. ◆ Smart categorization. Free. Open Source. Ready-to-use template.

Introducing AI Codex: the self-improving system for Cursor. ◆ Error and learning repository. ◆ Auto-save new insights. ◆ Smart categorization. Free. Open Source. Ready-to-use template.

zbeyens

173,158 views • 2 years ago

AI has spent years reading the internet, but now it’s time for it to see the world. We’ve been indexing the physical Earth for 8+ years. When you marry this data with foundation models, you move past chatbots to get a queryable Earth. Watch the full breakdown with Will Marshall on “The Future Of” podcast:

AI has spent years reading the internet, but now it’s time for it to see the world. We’ve been indexing the physical Earth for 8+ years. When you marry this data with foundation models, you move past chatbots to get a queryable Earth. Watch the full breakdown with Will Marshall on “The Future Of” podcast:

Planet

35,690 views • 7 months ago

By 2030, the entire state of Michigan is going to turn into a giant AI data center.

By 2030, the entire state of Michigan is going to turn into a giant AI data center.

RyanMatta 🇺🇸 🦅

115,022 views • 4 months ago

Discover how AI query engines enable enterprises to turn data into actionable insights for more accurate AI-powered applications. 📖 Read the blog to learn more:

Discover how AI query engines enable enterprises to turn data into actionable insights for more accurate AI-powered applications. 📖 Read the blog to learn more:

NVIDIA AI

38,856 views • 1 year ago

Introducing Project Stera by FPV Labs, an open data infra for embodied AI research. Project Stera includes Stera-10M, with 10M+ frames of long-horizon data with persistent state tracking, and an open-source pipeline that converts raw data into training-ready formats.

Introducing Project Stera by FPV Labs, an open data infra for embodied AI research. Project Stera includes Stera-10M, with 10M+ frames of long-horizon data with persistent state tracking, and an open-source pipeline that converts raw data into training-ready formats.

FPV Labs

16,028 views • 4 months ago

Introducing Conversational AI 2.0 Build voice agents with: • New state-of-the-art turn-taking model • Language switching • Multicharacter mode • Multimodality • Batch calls • Built-in RAG Now fully enterprise-ready with HIPAA compliance, EU data residency, and robust security.

Introducing Conversational AI 2.0 Build voice agents with: • New state-of-the-art turn-taking model • Language switching • Multicharacter mode • Multimodality • Batch calls • Built-in RAG Now fully enterprise-ready with HIPAA compliance, EU data residency, and robust security.

ElevenLabs

232,837 views • 1 year ago

🌍 Announcing the latest advancements to Google Earth AI - a platform designed to unlock a new level of planetary understanding. ➡️ 🔗 Geospatial Reasoning framework 🧠 Deeper Insights in Google Earth 🎉 Expanded access to Earth AI

🌍 Announcing the latest advancements to Google Earth AI - a platform designed to unlock a new level of planetary understanding. ➡️ 🔗 Geospatial Reasoning framework 🧠 Deeper Insights in Google Earth 🎉 Expanded access to Earth AI

Google Earth

95,496 views • 11 months ago

🚀 Introducing the AI Alliance: Shaping the Future of AI and Data Security We’re proud to unveil the AI Alliance, a collaboration of expert teams from ARC, DMAIL.AI and XAlpha AI Agent to name a few, who are working together to drive innovation in AI and data security. By leveraging the power of LLMs (Large Language Models), we’re building the foundation for future AI applications. 🌐✨ 💡 This is just the beginning! Stay tuned for more insights and updates from this recently held AI Alliance AMA. We’ll dive deeper into how these teams are helping to shape the future of AI.

🚀 Introducing the AI Alliance: Shaping the Future of AI and Data Security We’re proud to unveil the AI Alliance, a collaboration of expert teams from ARC, DMAIL.AI and XAlpha AI Agent to name a few, who are working together to drive innovation in AI and data security. By leveraging the power of LLMs (Large Language Models), we’re building the foundation for future AI applications. 🌐✨ 💡 This is just the beginning! Stay tuned for more insights and updates from this recently held AI Alliance AMA. We’ll dive deeper into how these teams are helping to shape the future of AI.

ARC

20,658 views • 1 year ago

Edge Computing 🤝 Federated Learning The next AI breakthrough lies in unlocking private data. By expanding training from public to private data, FLock enables AI models to specialise, delivering deeper insights and continuous innovation. Introducing the FLock FL Alliance.

Edge Computing 🤝 Federated Learning The next AI breakthrough lies in unlocking private data. By expanding training from public to private data, FLock enables AI models to specialise, delivering deeper insights and continuous innovation. Introducing the FLock FL Alliance.

FLock.io

102,558 views • 1 year ago

Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models turn the publicly available, state-of-the-art text-to-image LDM Stable Diffusion into an efficient and expressive text-to-video model with resolution up to 1280 x 2048 abs: project page:

Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models turn the publicly available, state-of-the-art text-to-image LDM Stable Diffusion into an efficient and expressive text-to-video model with resolution up to 1280 x 2048 abs: project page:

AK

718,760 views • 3 years ago

Another 1GW Data Center incoming, this time by Meta "a state-of-the-art 1GW campus in Lebanon, Indiana. This facility represents an investment of over $10 billion in data center infrastructure and the surrounding community, one of our largest infrastructure investments to date."

Another 1GW Data Center incoming, this time by Meta "a state-of-the-art 1GW campus in Lebanon, Indiana. This facility represents an investment of over $10 billion in data center infrastructure and the surrounding community, one of our largest infrastructure investments to date."

Chubby♨️

20,892 views • 7 months ago

Introducing Hark, an AI lab building the most advanced, personal intelligence in the world. We're creating intelligent foundation models paired with next generation hardware designed to serve as a universal interface between humans and machines.

Introducing Hark, an AI lab building the most advanced, personal intelligence in the world. We're creating intelligent foundation models paired with next generation hardware designed to serve as a universal interface between humans and machines.

Hark

93,642 views • 6 months ago

Foundation models reach their full potential when paired with data at planetary scale. By combining the capabilities of Google Earth AI imagery models with the scale, depth, and quality of Vantor’s satellite imagery, Vantor customers can rapidly unlock complex, high-value use cases. Running Earth AI embedding models on Vantor’s 30 cm-class satellite imagery allows analysts to instantly surface visually similar features, patterns, and objects across massive datasets. A single reference image becomes a search query. From there, the system can: • Identify similar vessels across thousands of square kilometers • Detect infrastructure patterns at scale • Accelerate damage assessment workflows • Narrow broad-area searches before human review Our agreement with Google marks the first commercial deployment of Earth AI imagery models against a dataset offering global 2D coverage of virtually all landmass, global-scale 3D terrain, a 20+ year high-resolution archive, and constellation revisit rates of up to 15 times per day. That combination matters. When advanced imagery models are applied to a globally consistent, temporally deep, and geometrically precise spatial foundation, insight shifts from experimental to operational. And when deployed within sovereign, air-gapped environments, these capabilities move beyond cloud-based analytics to deliver mission-ready intelligence. Learn more:

Foundation models reach their full potential when paired with data at planetary scale. By combining the capabilities of Google Earth AI imagery models with the scale, depth, and quality of Vantor’s satellite imagery, Vantor customers can rapidly unlock complex, high-value use cases. Running Earth AI embedding models on Vantor’s 30 cm-class satellite imagery allows analysts to instantly surface visually similar features, patterns, and objects across massive datasets. A single reference image becomes a search query. From there, the system can: • Identify similar vessels across thousands of square kilometers • Detect infrastructure patterns at scale • Accelerate damage assessment workflows • Narrow broad-area searches before human review Our agreement with Google marks the first commercial deployment of Earth AI imagery models against a dataset offering global 2D coverage of virtually all landmass, global-scale 3D terrain, a 20+ year high-resolution archive, and constellation revisit rates of up to 15 times per day. That combination matters. When advanced imagery models are applied to a globally consistent, temporally deep, and geometrically precise spatial foundation, insight shifts from experimental to operational. And when deployed within sovereign, air-gapped environments, these capabilities move beyond cloud-based analytics to deliver mission-ready intelligence. Learn more:

Vantor

17,050 views • 7 months ago

Introducing OpenLedger Datanet: Data across domains is often fragmented, unreliable, and lacks clear attribution , making it difficult to use as a trusted foundation for AI. Datanet transforms these raw contributions into structured, transparent, and attributable networks that power Specialized AI with verifiable provenance and explainability. Read more:

Introducing OpenLedger Datanet: Data across domains is often fragmented, unreliable, and lacks clear attribution , making it difficult to use as a trusted foundation for AI. Datanet transforms these raw contributions into structured, transparent, and attributable networks that power Specialized AI with verifiable provenance and explainability. Read more:

OpenLedger

199,564 views • 1 year ago

The largest fully annotated open egocentric human dataset. Today we're open-sourcing EgoSuite-Open100K with Hugging Face : 100,000 hours of egocentric human data, free for anyone to use. Physical AI has a scaling law of its own now, and its input is human data. That part is settled. What the field still needs is a shared foundation to build on. 15,000+ tasks. 15,000+ real scenes, from factory floors to retail backrooms. Hand pose, body pose and subtask-level semantics, with wrist camera coverage on part of the set. Licensed for commercial training, not research-only. We build the data infrastructure for Physical AI. Open100K is the first public layer of it. The first 10,000 hours are live now, with the rest rolling out in stages.

The largest fully annotated open egocentric human dataset. Today we're open-sourcing EgoSuite-Open100K with Hugging Face : 100,000 hours of egocentric human data, free for anyone to use. Physical AI has a scaling law of its own now, and its input is human data. That part is settled. What the field still needs is a shared foundation to build on. 15,000+ tasks. 15,000+ real scenes, from factory floors to retail backrooms. Hand pose, body pose and subtask-level semantics, with wrist camera coverage on part of the set. Licensed for commercial training, not research-only. We build the data infrastructure for Physical AI. Open100K is the first public layer of it. The first 10,000 hours are live now, with the rest rolling out in stages.

Lightwheel

75,420 views • 1 month ago