Climate

Also published on LinkedIn. Those of us at the intersection of EO and AI still have a lot to bring, but further maturing a separate domain might not be the most impact-driven path. This is the article form of the talk I gave at #ECCV conference workship on Conservation and Climate change. Thank you Climate AI Nordics for the invitation. Hope I was able to sir the pot enough. Is geodata just data? We geo experts adopt most frontier techniques fast — SAM (“Segment Anything Model”) was applied to satellite imagery within three weeks, with fantastic applicability. Yet there is no evidence that the general-purpose frontier models (Gemini, GPT, Claude, DeepSeek, Kimi, GLM) treat Earth observation in any of the specific ways we in GeoAI do: feature engineering around metadata, rasters, projections, bands, and sensor physics. Models that do accept images expose only an RGB image interface, and while they can appear well versed and able to generate GIS code, the primitives that define GeoAI (e.g. geoattention) are absent from their published core architectures. I have reviewed eighteen frontier-lab model cards and technical reports from this year. Not one documents an Earth-observation input or an Earth-observation benchmark. This is absence of evidence, not evidence of absence, but it does show that geo is not a publicly stated architectural priority. ...

This meeting remains the densest gathering of decision-makers anywhere: public, private, science, technology, and civil society, all compressed into one intense week. There’s nothing like Davos, and overall we do need Davos, imo. I was on the ground, but our whole team worked incredibly hard to make this week count. Between interviews, articles, meetings, panels, and strategy sessions, the pace was unrelenting. And yet, looking back at the blur of 72 calendar entries and the “who’s who”, it is hard for me not to feel the familiar tug of “more”. One more session. One more corridor conversation. One more unexpected connection. ...

I’ll miss bedtime stories next week. Not because I love the 75 events in my calendar at Davos, but because I’m carrying something personal with me. My kids are growing up in the EU, in Denmark, where safety, nature, and independence are built into everyday life. That kind of childhood isn’t magic. It’s the result of decades of public investment, data, and care. For most of the world, that model has simply been out of reach. At LGND AI and Clay we’re building extremely horizontal planetary intelligence: tools designed to understand the world at scale. Child infrastructure, air quality, climate risk, food security, disaster response. This is just one possible use. ...

Greenland is increasingly framed through geopolitics, resources, and strategic interest. But it is first and foremost a place of extraordinary beauty, culture, and people. In 2014, I had the opportunity to visit Greenland during a climate-change event and document the place from the air (planes, helicopters, and drones) and the ground (including the then-fancy Google Glass). Given the growing attention on the Arctic, I’ve uploaded hundreds of my photos and videos as open data (CC-BY) to support journalists and independent media who need high-resolution, reusable visuals to tell accurate and respectful stories about Greenland. ...

I was recently invited to come to the European Commission conference on Clean Air, about the role of AI. Most people would expect the usual story: AI will make things faster , models better , and cheaper. All of that is true, but that’s not the point. The most important aspect of AI here, and in many other domains, is to make stuff invisible. Stuff that just works, reliably, so we can build on it, depend on it, and focus on outcomes, not tools. To reduce the cognitive load, not increase it. ...

Last week I was invited to speak at the Aarhus Symposium to technical and business students exploring the theme “Beyond the AI Hype: AI for Earth.” To make sense of this broad brief, I divided my class into three parts: a very candid view of what AI is (and isn’t) today in general, then AI applied to understanding Earth, and finally the impact of AI on Earth (its environmental footprint). My goal was simple: to cut through both hype and doom, showing where the technology genuinely shines, where it falls short, and why it matters for Earth. ...

TL;DR: Training Clay v1.5 was “carbon neutral” and actually emitted ~10 tonnes of CO₂e. Moreover, focusing on lower emissions during geoAI training is a climate distraction compared to understanding geoembeddings. A year ago we trained Clay model v1.5 — still one of the most capable geoAI models today: open-source, open-data, open-license. At the time we promised to publish its emissions. I just updated the docs, but sharing this longer post since it proved harder — and had deeper pragmatic implications — than I expected. ...

Climate change is what we deserve were the exact words I heard from an otherwise well educated and reasonable scientist. The logic was something like: Climate has changed in the past. Yes there might be a significant change lately but so has happened millennia ago, for natural reasons, like volcanoes and other stuff. If you look at the long term climate, it's full of variations. *Climate changes* Therefore this change, that is doubtfully due to humans, is not really worrisome. Climate changes and we have to deal with it. And if we are the cause of it, more so. Why fight against the consequences we deserve? We are too many, we harm the environment too much. If we indeed are the cause and we disappear due to climate change, it's the natural thing. Like if we were a virus and Earth needs to heal. The earth will come back into its equilibrium afterwards. This logic comes from a highly educated person, doing basic research science. And the fact is this is not the first time I hear a similar catastrophic argument of cosmic justice. On this particular case, few others around the table agreed on it. ...

[Cross posted at GAIN] Engineers will be among those on the front lines of adaptation. From improving the resilience of water pipes and energy transport systems to redesigning how entire urban areas are built, engineering firms will need to solve new challenges created by population growth, urbanization and climate change. Incorporation of new scientific, economic and social science data is becoming more critical as unprecedented changes are upon us. Engineering innovation and technology will be part of the solution. These were the main takeaways according to participants at the Engineers Without Borders (EWB)–USA 10-year anniversary International Conference in Henderson, Nev., March 22-24. ...

Today I went to a lunch meeting with the Apps 4 Climate folks. It is basically a challenge for developers to make apps using the vast archive of open data at the Bank. It was great to see such a motivated team behind the project. We talked about the challenge itself, requirements and timelines. It was very appropriate for Habiba Gitay to point out the importance of rightful sourcing attribution (most times the Bank acts as a portal that archives someone else’s data). Alex Barth also gave a talk about building maps with World Bank Climate Data (slides here). ...