We foolishly think AI for Earth is yet another try to deliver the same vision geospatial has promised for decades. The reality is much harsher. This was the provocative prompt I wanted to articulate on my plenary at SatSummit Lisbon. That room, and the network I can reach here, has some of the main shapers and doers of AI for Earth, bo...

Historically, the sheer size of the EU (+500 million people and its +$20 trillion economy) has compelled companies globally to adopt EU standards - it was simply cheaper to raise the bar for everyone. This "Brussels Effect" has shaped world standards on data protection, airline emissions, and even USB-C adoption. However, when it comes...

[From a keynote at the European Rover Challenge last week in Krakow, and celebrating the 150th anniversary of "The Lunar Trilogy" by Jerzy Zulawski. Video at the end] The conference hall was buzzing. Outside, teams of students around the world were competing with their DIY robots on a Mars landscape, driven by the same age-old question...

Fig 1. A screenshot of Google Maps with a search for “grass” returns with “No results” even when it’s obvious to find the grass on the satellite image. Google Maps excels at providing detailed information on restaurants, live updates on public transport, and more. Yet, it struggles to identify something as simple as grass or an entire ...

Last week I taught on a PhD-level summer course on geoAI, or AI for Earth, at the University of Copenhagen. I saw other speakers give their fantastic technical talks, some on fundamentals, and some on real specific applications. The organizers made a fantastic job to equip these selected and global group of PhD students with truly the ...

Would you defend the position that “AI, and not humans, hold the key for understanding risk today”? and would you do it at the plenary of the largest and most important conference about disaster risks, hosted by the World Bank? That’s what I just did in Himeji, Japan. On a debate where the opposing side was Ivan Gayton, from HOT, who d...

In AI every large player is spending truly absurd amounts of compute using roughly the same hardware with roughly the same AI tools and roughly the same data... to achieve roughly same results 🤷♂ Gets worse, in AI for Earth it is EXACTLY the same open data (Sentinel/Landsat/…). But, wait, plot twist, no large AI player is touching geos...

8 years to publish our paper that there's 1.18 billion people energy poor, 60% more than expected, lost in the dark every night. Poverty happens *somewhere*, and being good at "What is where" matters. 8 years ago, at the The World Bank we used space images at night to actually see who has lights across India when the satellites pass af...

I'll be teaching part of the PhD course on AI for Earth, so excited! As we roll out Clay it's become clear to me that this is NOT about creating a finest AI to solve all our problems, nor is it about dismissing AI as just stochastic parroting hallucinations. Technology, or data, doesn't change the world—people do. People with the right...

We made a great AI for Earth model. So what? It really doesn't matter if it just joins the pile of geo AI models, already 20+ or so depending how you count. It doesn't even matter if it can use any dataset, latest architecture learning from others, or even if it has a permissive license, ... even if then we were the only option. What m...

See below the recording of our last live demo Introducing Clay: AI-Powered Geospatial Search Engine 🌍 (In 20min + 40min of QAs) We've done this weekly live for a while, and many have asked for a recording. There's lots of room to improve our audio/video and script, but better this than later. Please do comment and provide feedback. Wha...

We have a very clear set of needs to understand Earth’s climate and nature, including measuring biodiversity, mapping disasters, and monitoring crops, to mention just a few. Yet despite having an enormous amount of diverse, Earth data (both open and commercial), most insights about the Earth are locked in the data, requiring very advan...

No better proof that science is falling short of needed action than climate change. Of course, scientific research has given us invaluable knowledge in theory, but as a strategy to solve it in practice, our approach is falling short of what we need. Hold on, let me explain why, and how we are trying to do our part with AI for Climate, ...

With our first baby, I remember thinking how absolutely impossible it seemed to me that babies can be born in nature, without any healthcare system. With our second, I can very much believe so. I am surely glad we had a healthcare system seconds away prepared for all complications, but I appreciate why it was kept around the corner out...

AI is changing the world of text, images, audio, ... but not Earth data. Yes, its hard to work with, but not only we are dropping the [globe] ball, AI for Earth has outsized benefits (impact and profits alike), specially if done fully in the open. We have amazing breakthroughs in AI with text, images, video, and audio — but not Earth d...

In the field of genetic ancestry, services like 23andMe enable us to trace our roots back 100,000 years. However, the recent ancestry --the closer generations to us-- are paradoxically harder to trace. Why? This is in part due to advent of increasingly common, fast, and cheap travel: horses, ships, trains, cars, planes, ... It basicall...

AI dominates every digital space. More specifically OpenAI with ChaptGPT and GPT4, clearly outperforming [at least in public perception] usual suspects like Google who claimed to be "AI first", since 2016. The irony is that OpenAI uses Transformers for it's star product ChatGPT and friends, which is a Google invention from 2017. There ...

I've been thinking about this the whole weekend. Been working on this for at least 15 years, even wrote a book about it, but it's always good to sit down and try to think it over from scratch. Sometimes I think I'm wrong and I´m crazy, sometimes that I´d be crazy not to do this. I see no better way to spend my intellect than to pursue ...

Today is my last day leading Microsoft's Planetary Computer. As all of you know, I'm truly and incredibly proud of the team and platform we built. It's hard to believe that a little over 2 years ago I was given the generous trust, and budget, to deliver one of the four Microsoft's Environmental Sustainability topline commitments. We st...

I have recently finished the most important book I have read in decades. And I am not joking. But the core message is an old, plain, and simple thing: Telling stories works. As a scientist, I have heard that too often from communicators and journalists, usually when doing an interview where they struggle to understand what it is what w...

My paternity leave has easily been among the hardest things I’ve done. It’s also, without doubt, the most meaningful and rewarding thing I’ve done. Far from a “nice long vacation” as someone told me, it’s been fully a deconstruction and reconstruction of so much of myself. The more I reflect on it, the more I realize both things: It is...

Finally, I'm "40 under 40". 40 days to my 40th birthday that is, not the Forbes award. I won't lie that the number weighs on me, 40 years old is a big number. Entering the 20s was all about new worlds to explore. Life looked amazing, infinite, boundless. There wasn't much thought of who I wanted to be, other than a scientist. That was ...