Undertaking the worlds toughest challenges with AI & ML applied to satellite & aerial imagery https://xitter.cf/t.co/QmbOWgdNqx
London, England
Joined April 2009
- Tweets8.4K
- Following4.2K
- Followers11.8K
- Likes70.3K
Stay tuned for more episodes coming soon, make sure to Subscribe here: satellite-image-deep-learnin…
Robin Cole retweeted
In the full episode of @robmarkcole's podcast, Joe covers how OlmoEarth grew out of Ai2’s unique expertise in both tech & conservation—and what's next for the model family: youtu.be/wzCHJf6Ly24
Robin Cole retweeted
"Embeddings only get you so far… if you want the next level in performance, I think fine-tuning is the way to go."
Ai2 research scientist @pjreddie explains how our partners customize OlmoEarth – our open-source Earth-observation models – to map crops, wildfire risk, & more. 👇
🎙️ New Podcast & YouTube: Building OlmoEarth: AI2’s Open Foundation Model for Satellite Imagery With Joseph Redmon
In this episode I sat down with Joe Redmond from the Allen Institute for AI (AI2) to discuss OlmoEarth, AI2's open geospatial foundation model for Earth observation. Joe explains how the project emerged from AI2's environmental and climate initiatives, where partners needed practical tools for analysing satellite imagery across applications such as agriculture, wildfire risk, ecosystem mapping, and conservation. We discuss the unique challenges of remote sensing data, including its temporal and multispectral nature, why geospatial machine learning differs from traditional computer vision, and AI2's philosophy of building open models and tools that can be adapted to real-world environmental problems.
🎙️ New Podcast & YouTube: A Single GPU Is All You Need for Self-Supervised Pretraining
In this episode I sat down with Lakshay Sharma, a machine learning scientist at Instacart and former member of Microsoft’s geospatial AI team, to discuss self-supervised learning for remote sensing and his recent research on efficient pretraining for semantic segmentation.
Lakshay explains the evolution of self-supervised learning, covering predictive, generative, and contrastive approaches, and discusses how foundation models such as DINO have transformed computer vision and geospatial machine learning. We explore the unique challenges of applying these techniques to remote sensing imagery, where assumptions that work for natural images often break down.
Tessera v1.1 is here
Tessera v1.1 is here — cleaner embeddings, fewer artefacts, and coastal coverage for the mangrove fans 🌿
Drop-in replacement for v1.0.
geotessera.org/blog/2026-06-…
#EarthObservation #RemoteSensing #Geospatial
Robin Cole retweeted
🎙️ Your Fields of The World podcast playlist:
🌍 Spatial Stack w/Matt Forrest -open.spotify.com/episode/7mO…
🛰️ Satellite Image Deep Learning w/@robmarkcole -open.spotify.com/episode/4ah…
💡 Great Data Products w/@jedsundwall @OurRadiantEarth @source_coop -youtube.com/live/viiPXej01iM…
We dive into the technical details behind the first global release: assembling noisy and uneven benchmark datasets from around the world, training models that generalise across diverse agricultural systems, and releasing everything from Sentinel-2 mosaics and raw segmentation probabilities to polygonised field boundaries through Source Cooperative. Along the way, we discuss community-driven improvement loops inspired by OpenStreetMap, the limitations of 10 m imagery for smallholder agriculture, and the importance of pairing academic researchers with engineering teams to rapidly operationalise new methods. Finally, we look ahead to Taylor Geospatial’s next phase - richer agricultural datasets, “Features of the World,” and a benchmarking initiative aimed at improving evaluation standards and reproducibility across geospatial foundation models.
Robin Cole retweeted
If you've adopted AI at your company but haven't seen any tangible results, read this 1990 article: "The Dynamo and the Computer" by Paul David.
When electricity first arrived, factories that "adopted" it barely got faster. They just swapped the steam engine for an electric one and ran everything else exactly as before: same machine layout, same workflow, same management. Electricity in, no real gains out.
The most common mistake with any new technology is to drop it into the old organization and then declare the transformation done.
The real leap came decades later, when each machine got its own small motor. Suddenly machines no longer had to be lined up around one central drive shaft. They could be rearranged around the actual flow of work.
The productivity gains didn't come from electricity. They came from REDESIGNING THE ENTIRE FACTORY around it.
AI is the same. Bolting it onto your existing process gets you a faster steam engine. The payoff comes when you redesign the work itself.
(link to paper in comments)
Robin Cole retweeted
“Penetration pricing” is the term used when a company burns through Venture Capital money selling a product under its cost to build market share.
Remember how cheap Uber and Lyft used to be? VCs subsidized the drivers and the riders for years. Then they went public and now it costs me $20 for a 3 minute ride down the road.
DoorDash, Uber Eats, Instacart.
MoviePass, Netflix, Hulu.
All of these companies sold below cost to get market share then massively raised their prices, added ads, diminished their products, etc.
AI today is no different. OpenAI and Anthropic are giving us all cheap rides. To do that, they’re selling $1.00 for 10 cents.
Get it while you can before a different kind of penetration begins.
EarthShift: a benchmark for measuring robustness to real-world distribution shifts in Earth observation
🔥 Hot take: Geospatial Foundation Models (GFMs) are brittle.
So, we built EarthShift 🌍 — the first public testbed for benchmarking the robustness of GFMs across realistic distribution shifts in remote sensing!
📄 Paper: arxiv.org/abs/2605.29330
(Thread)
Robin Cole retweeted
CEOs are quietly realizing the AI replacement plan has a problem.
Two problems, actually.
One: the token costs for running AI agents are now exceeding what they were paying the employees they fired.
Two: when the tokens run out, the AI stops. Just stops. No continuity. No workaround. Just a spinning wheel where your workforce used to be.
You fired humans to save money and bought a subscription that bills you into a corner.
The employees you let go knew what to do when things broke.
The AI just invoices you for the outage.
And then there’s the permission problem nobody wants to talk about.
To do its job, the AI agent needs access. Full access. Your systems, your patents, your contracts, your future plans. Everything you spent years building, handed over to a process that has no loyalty, no discretion, and no skin in the game.
You didn’t hire a replacement.
You gave a stranger with no soul the keys to everything you own.
Enjoy.