Academic on Dani Arribas-Bel

Fri, 08 May 2026 11:30:22 +0100

Happy release day (+1) to those who celebrate! Third week in a row shipping imagery-based data products. One is a fluke, two is a pattern, three is real team effort. Imago releases CLiVE Air Temperature and Precipitation:

imago.ac.uk/news/imag…

Thu, 07 May 2026 11:15:08 +0100

Talking about babies (and everything around them) was trickier on tape than on paper, but I think it was worth the effort, audience be the judge! New #GLADpodcast on academic babies:

What Battersea Power Station taught me about the value of satellite embeddings

Tue, 05 May 2026 09:59:51 +0100

Sometimes, magic finds its way through the forest of math that underpins most of my research. I spent a good amount of time a couple of weeks ago working on our embeddings workshop for GISRUK. We just released a new data product with Google satellite embeddings for small areas in the UK, and we couldn’t wait to take it on the road. This post is a note about one of the most insightful moments I had while preparing the materials but, if you want to check out the entire workshop, it’s all open at:

https://imago-sdruk.github.io/embeddings_workshop/jupyterlite/content/02-Change.html

One of the most appealing characteristics of satellite embeddings is their ability to explore change. Since embeddings map the information in an image to a shared latent space, it doesn’t matter where or when that image was taken, it all gets encoded in the same mathematical “language”. Exploring whether the location of an image is similar or not to that of a different image; or whether such location has changed compared to what it looked like at a different point in time, is relatively straightforward. You can play with the “comparison across space” idea in our Imago UK embedding Explorer. And we played with change across time in this notebook.

The part that got me is the last exercise. We ask the question what area has become the most like Hyde Park between 2020 and 2024? This seems a bit esoteric but, I think, is an interesting one to ask. We know areas change within a city all the time, wouldn’t it be cool to know which ones are becoming more like some specific landmarks? In the workshop, I called it “Hyde Park-ification”, but I may deny this in public… It also turns out this is relatively straightforward to check with embeddings. You can follow all the details, code included, in the notebook. The gist is you calculate how similar all areas are to Hyde Park in both years, take the difference of that distance, and pick your winner as the smallest of those.

Here’s our winner¹:

For the uninitiated reader, this is Battersea Power Station. Which, even if all you know is the first photo in the Wikipedia page I just linked to, you’d be forgiven to think this embeddings sorcery is nonsense. This is as far as you can get from Hyde Park in terms of look and feel. So, where’s the catch?

The catch, of course, is that we are not looking into overall similarity, but change. Our approach looks for areas that, over the period we consider, have become more like Hyde Park. That does not mean they are like Hyde Park. There’s another interesting bit we show in the notebook: Battersea Station, by the standards of the areas we use, has changed very little. Again, this is counterintuitive maybe, but not incompatible with what we’re asking of embeddings in this exercise: you can change very little, but entirely in one particular direction.

As it turns out, this is what happened to our winner. This insight did not come painlessly to me, as I struggled through a good 20/30 minutes of scratching my head about whether I was asking too much of this technology (particularly when it’s aggregated from the pixel to an irregular area). I’m glad I stuck with this and followed it to the bottom. And I’m glad Google keeps funding Google Earth for free, including its time travel feature. Below is a comparison of the area in question between 2020 and 2024²:

If you can’t spot the difference (I couldn’t for the first ten minutes), follow the red arrow (which wasn’t there when I was looking for twenty minutes). The area, broadly speaking, has not changed much (which checks out with our low score of change). It was, and still is, a retired power station turned epicenter of cool south of the river. Mostly chimneys, mostly concrete. But there’s a small part that has changed. A small patch by the river used to be concrete buildings but, in between 2020 and 2024, it was flattened. Instead, it is now a patch of grass where Londoners enjoy the three days a year where the sun shines with all its fury³. You can see some of the before and after photos in this article by the BBC.

I love this example because it captures very well why I’m so excited about embeddings and about making them accessible to more people through data products like our small area one. I knocked out that notebook in about an hour (if you exclude my Google Earth rabbit hole). In that period, I was able to leverage data from seven massive satellite sources (see Figure S2 in this paper for details), across two periods of time on a setup that runs on my iPad’s browser. Just let that sink in. What questions can we tackle that we couldn’t before? More importantly, which ones will we actually consider now that the price of asking is so low? I think we’re about to find out, and I can’t wait.

I’m pasting here screenshots because it’s 2026 and YOLO, but you can play with the interactive map on the workshop site. ↩︎
You can play with the feature here. ↩︎
This is a joke. I know it’s, at least, five days. ↩︎

Fri, 01 May 2026 08:56:01 +0100

Happy release day to those who celebrate!!! Today, you can access our derived product that packages Google embeddings for small areas in the UK. Embeddings are changing how we work with satellite data. With this product, we hope it’ll be even easier to access and get started to look at places. If you take them out for a spin, let us know!

https://imago.ac.uk/news/imago-releases-google-satellite-embeddings-at-the-small-area-level-across-uk

Fri, 24 Apr 2026 13:24:58 +0100

Happy data release day to those who celebrate!!! We’ve been working really hard (how hard can it be to count clouds? a lot, it turns out…) to bring you all your cloudy needs neatly packaged. If you play with SPF, we’d love to hear from you!

imago.ac.uk/news/imag…

Notes from a week in the Bay Area

Mon, 23 Mar 2026 13:01:00 +0100

I’m just wrapping up a week in Berkeley and San Francisco. I came for two reasons, both have been fantastic, and I’m definitely feeling now the post-high blues that good academic interaction tends to induce.

I spent the first few days at the Berkeley Institute for Data Science, where the good folks of PySAL organised the Spatial Data Science Summit. This was a meeting to discuss opportunities and overlaps across the spatial data science community, and beyond, including the wider Python ecosystem for scientific computing. These days, I’m much less active (and that’s a kind way of putting it) in the development of PySAL. But it was nevertheless a fantastic experience. PySAL 1.0 shipped in 2009 and I was there to see it. Since then, it’s been a project and a community that has brought me much of what I am and who I’ve become. And, as the cliché goes, many of the collaborators have become close friends. Clichés are clichés for a reason.

Then I hopped on the BART to San Francisco’s Tenderloin, where geographers were descending left and right to discuss all things Geography at the AAG. I was part of a session brilliantly put together by Elizabeth Delmelle and Geoff Boeing on “problem-driven methods” (as opposed to the seemingly more common “method-driven problem development”) in the context of cities. I presented on satellite embeddings. When I was preparing the slides, I felt a bit uncomfortable because, arguably, I was about to engage in precisely the type of behaviour the sessions sought to avoid: “reaching for this year’s shiny new tool” instead of addressing cities' ‘wicked problems’”. Elizabeth and Geoff prompted us to include a slide at the beginning stating the “big urban problem” we were tackling. I’m so glad they did because it really nudged me to spell out why I think embeddings are more than this year’s shiny tool. My framing revolved around two key arguments. First, there is much more we can (and should!) do to tailor the data we use to the problems we tackle. Second, there is a lot of untapped data to help in that tailoring. In this context, satellites are one of those underutilised sources that can help provide better empirical fit to the questions we care about. And embeddings lower the barrier to access satellite data, making it cheaper to ask questions and explore ideas. I think, in the end, it went well and was well received.

I also participated in a panel organised as part of the discussion we had started in Berkeley earlier in the week around open source in spatial data science research. Serge Rey prompted us to think about existing gaps, low-hanging fruit, and surfaces of overlap. We covered quite a bit of territory, and Serge structured the conversation so there was clear and constant interaction with the audience, which became an “additional panelist”. A lot of fun.

Besides the strictly “work” things, this week also had plenty of space for fun. We (i.e., Rachel, Levi and your truly) attended the AAG Awards ceremony to pick up our Media Achievement award for GLaD. To celebrate it, that afternoon we hijacked a boardroom, stuck a hand-written note in the door that read “recording in process”, and taped the first episode in a long while where we were physically together. And, after all that flurry of activity, the day after, I managed to convince Geoff Boeing and Martin Fleischmann to join me on a walk around very tall trees north of the Golden Gate. Long walks are underappreciated ways to exchange ideas.

With that, the week came to an end. It’s been so much compressed in such a small amount of time and space. I know it’ll take me a few days to unpack, literally and figuratively. This is conferencing at its best: more brain cycles in less days, all away than your usual routine. Academic life the way it should be.

Sun, 22 Mar 2026 21:16:45 +0100

We’re recruiting for two PhD positions at Liverpool with the Imago team and based at the GDSL:

Pixel2Policy, led by Elisabetta Pietrostefani

This project investigates how satellite-derived indicators can be co-produced with policymakers and communities to better reflect real needs and lived realities. Bridging Earth observation, participation, and policy, it aims to make satellite data more inclusive, credible, and impactful in decision-making.

Space2Health, led by Ron Mahabir

Space2Health explores how satellite imagery can be transformed into meaningful measures of environmental exposures linked to health. The project relies on recent AI technologies to develop and evaluate satellite-derived indicators, examining how data choices and analytical approaches shape health-relevant evidence for research and decision-making.

Both open until April 13th, get in touch for any queries.

The GLaD Podcast recognised with AAG award

Mon, 16 Feb 2026 13:04:56 +0100

This happened, the GLaD podcast is now the “award-winning” GLaD podcast:

https://www.aag.org/2026-aag-awards-recognition/

Reproduced here for posterity:

AAG Media Achievement Award

The 2026 Media Achievement Award is presented to Drs. Daniel Arribas-Bel, Rachel Franklin and Levi Wolf, the co-creators and hosts of the Geography, Life + Data (GLaD) Podcast. This podcast is celebrated for enhancing the understanding of geography by exploring the intersection of our discipline with data science, public life, and academia—or, as their episode intro says, “geography, life, geography life, and data. Launched in 2023, the GLaD Podcast and its predecessor series have produced over 50 episodes, amassing over 8,000 downloads, over 15,000 views on YouTube, and attracting more than 5,000 listeners worldwide. The podcast is renowned for its ability to simplify complex topics—such as spatial data science and urban analytics—through an engaging and accessible conversational style. It effectively breaks down barriers for students, early-career researchers, and non-specialists. Recognized as an invaluable educational resource, it has been integrated into graduate seminars and serves as a platform to humanize leading scholars. The podcast offers candid, practical advice on academic challenges like job searching and conference navigation, fostering a supportive community. GLaD’s continued independent production underscores the creators’ commitment to bridging the gap between academic research and the wider public.

Like most things worth your time in life, we did not set out to do a podcast (the “I’m in a band” of the XXIst Century…) for the awards, but it does feel very good to be recognised, mostly by people listening to it every month, and now with this too.

Thank you, thank you, thank you to everyone who’s clicked on the Play button at some point. And Thank you, Thank you, Thank you to the kind souls who nominated us for the award. Like I’ve said elsewhere, whatever they tell you, what academics really crave is peer recognition, and this feels pretty close to it!

Fri, 13 Feb 2026 17:39:02 +0100

New episode of the one and only #GLaDpodcast. For this one, we dust off our oracles to speculate what 2026 (whatever is left of it anyway) has in store for Geography, Life, Geography Life, and Data! Come for the hot takes, stay for Polymarket-style futures contracts!

Wed, 28 Jan 2026 12:26:17 +0100

Yesterday, we (the Imago team) gave a workshop on satellite embeddings for a room with about 50 people from different corners of the UK Government. It was fantastic in every respect (with the possible exception of Github bringing down our website because it thought it was receiving a DDoS attack lol). It’s so exciting to see these ideas and technology move at the speed of light from state of the art research to Government. Anything we can do at Imago to facilitate that transfer, we’re here for that!

If you’re curious, materials are available at:

imago-sdruk.github.io/EMBED2Soc…

And if this looks interesting to your and/or your organisation, do get in touch!

🔗 Earth Embeddings: Towards AI-centric Representations of our Planet

Fri, 23 Jan 2026 22:35:26 +0100

Very very timely paper that captures the current zeitgeist in EO and AI. If nothing else, it serves as a fantastic introduction to one of the technologies that I think(/hope) will help the most bring imagery to the masses in the coming years.

Metadata

Author: eartharxiv.org
Category: article
Document Tags: paper
URL: eartharxiv.org/repositor…

Highlights

Earth embedding vectors emb are produced by a family of embedding functions E that map continuous location inputs (i.e., longitude, latitude with optionally elevation, and time) into a d-dimensional vector space:

Figure 2: Earth embeddings provide different functions: (1) They compress high-dimensional data into a lower-dimensional vector format. (2) They fuse together different geospatial data modalities, from different types of images to text and tabular data. (3) They can interpolate to unseen spatiotemporal locations, where raw data is missing. (4) They are interoperable with other AI foundation models, such as LLMs, through aligned embedding spaces.

as explicit models, extracting embeddings from raw data (e.g. satellite imagery) associated with a location (emb ∼ Eexplicit(datalocation))

implicit models, returning embeddings from only location inputs (emb ∼ Eimplicit(location)).

Earth embeddings map places and times that share similar properties closer together in embedding space.

GeoFMs are large-scale modeling and learning frameworks, whereas Earth embeddings constitute the interoperable, location-indexed data outputs that can be stored, shared, or queried independently of the model that created them.

We posit that Earth embeddings will emerge as the dominant format of geospatial data in the AI age

ways in which users can employ Earth embeddings for prediction, conditioning, simulation, and search

Call to action: Advancing analyses and applications with Earth embeddings.

• Evaluating and benchmarking Earth embeddings

• Explainable and interpretable Earth embeddings

• Learning planetary processes with Earth embeddings

Earth Embedding Models: Explicit Feature Extraction versus Implicit Neural Representation

Challenges and opportunities for improving Earth embeddings.

• Model capacity

• Spatio-temporal heterogeneity

• Data curation and scaling

• Learning objective

The research agenda we outline is fundamentally interdisciplinary: Earth embeddings will rely on feedback from domain scientists, e.g. in ecological, geological, oceanographic, and atmospheric sciences, that incorporate Earth embeddings into their analyses and from data practitioners apply- ing Earth embeddings in their workflows and products.

Wed, 21 Jan 2026 18:29:07 +0100

A bit late to post about (though not to publish!), we have a new episode of the #GLaDpodcast out. If nothing else, be enticed by the title (the oldest profession in Geography?!?!?!); if something else, delight in Anthony Robinson’s views on maps, AI, and microwave ovens!

🎧 From Data Dump to Data Product

Mon, 19 Jan 2026 00:07:31 +0100

So many common points and arguments that really resonate here and make me more hopeful for Imago. The discussion of data as infrastructure, invisibility as success, and thinking really hard about how to make sure “it”’s not only here now, but tomorrow and the day after are points that’ll stay with me. And it’s also great to find more people who’re thinking creatively (not only from the tech side of things) to ensure the world has more collective-ness around data. Most recommended listen.

Metadata

Author: MapScaping
Category: podcast
Document Tags: audio
URL: podcasts.apple.com/gb/podcas…

Highlights

The way I frame it is like, the game is figuring out how to lower the cost of asking questions.

🔗 Why "Science-as-a-Service" Doesn't Work for Earth Science

Thu, 18 Dec 2025 16:54:05 +0100

Very important, if sobering, piece on the TerraWatchSpace newsletter on why “handing off to industry” is not a great idea for Earth Observation (EO) for basic science. In some ways, I see parallels with the discussion in the social sciences around how traditional sources (think decadal censuses, but also large surveys, etc.) could potentially be replaced by new sources such as mobility from phones or, for that matter, modern uses of Earth Observation. Don’t get me wrong, I am more excited than most about the potential of new data in the social sciences (imagery in particular!). We do need more data than a drop every ten years to not fly blind through everything that happens between release points (which is a lot). The bit that makes me very uneasy here is the replace, rather than complement. Without the census, satellites and phones are fairly close to useless for social scientists, and the reasons are very similar to why commercial EO needs large, public, and free programmes like Sentinel and Landsat.

Metadata

Author: Aravind
Category: rss
URL: newsletter.terrawatchspace.com/why-scien…

Highlights

Jared Isaacman, President Trump’s nominee for NASA Administrator has articulated a compelling vision: “NASA needs to constantly be recalibrating to do the near impossible, what no one else is doing - and the things they figured out, they hand off to industry.”

Earth Science Data Is Infrastructure, Not a Service

Infrastructure requires institutional commitment that transcends market cycles and political administrations. It requires transparency, neutrality, and guaranteed long-term access. It requires optimization for societal benefit rather than profit margins.

Tue, 16 Dec 2025 11:37:08 +0100

Just in time for a cozy listen this coming break, a new #GLaDpodcast episode! This time, we welcome the one and only Serge Rey to talk all things open, open source, and academia! Come for the code, stay for the stories of lives changed!

Tue, 16 Dec 2025 11:32:38 +0100

With all the rush last month, I forgot we released a new #GLaDpodcast episode. We finally gave in to the GeoAI craze and went straight to the source. Join us for a conversation with Krzysztof Janowicz, who’s been laying the grounds for what today is called “GeoAI” for longer than you can think of!

🔗 World Urbanization Prospects 2025

Sun, 30 Nov 2025 12:46:50 +0100

Cities are (still) a pretty cool thing…

Metadata

Author: Population Division of the United Nations Department of Economic and Social Affairs (UN DESA)
Category: pdf
URL: population.un.org/wup/asset…

Highlights

The world has become increasingly urban; more people live in cities today than in towns or rural areas.
The number of “megacities” (10 million inhabitants or more) continues to grow; over half are in Asia.
More people live in small and medium-sized cities than in megacities; many of these smaller settlements are among the fastest growing, especially in Africa and Asia.
Growth of the world’s city population between now and 2050 will be concentrated in seven countries.
City population growth is uneven; most cities are growing, but thousands have shrinking populations.
Towns are home to more than a third of humanity and are critical for sustainable development.
As the world’s rural population approaches its peak size, it faces unprecedented challenges.
The expansion of built-up areas is outpacing population growth worldwide.
The Degree of Urbanization methodology reveals the world is more urbanized than national statistics suggest.
Sustainable development requires integrated planning that treats cities, towns and rural areas as interconnected and interdependent.

Dispatch from the Human Planet Forum

Mon, 24 Nov 2025 12:28:58 +0100

I’m just back from my first Human Planet Forum. In its own words:

The Human Planet Forum 2025 is a flagship event of the GEO Human Planet Initiative (GHP) which works to understand and map human presence on earth using open geospatial data.

In my own, it’s an (the?) opportunity to see in one room, at the same time, all the wonderful nerds behind some of the most interesting data products using earth observation (EO) to map the world’s population. As an understatement, I was excited.

The organisers kindly asked me to prepare a ten minute summary of the event that’d help conclude it. As my email inbox will attest, I “had to” pay attention to all presentations, and thus the opportunity cost of getting distracted was higher than usual. I’m glad I was given this constraint because it made me appreciate the event and what was presented there much more. Below is a write up of that summary. Heads up, this is not a detailed account of each presentation (for that, you’ll have to wait for the report the JRC will put out in time), more of an opinionated view of what the event represents and why it is valuable.

I structured my contribution along three key dimensions: domains discussed, perspectives used, and common threads. I then added two extra slides, one with themes that will keep this community busy for the foreseeable future, and one with my own perspectives to wrap up.

Start with the domains. There was an important chunk of time spent discussing new ways and products that characterise environments. A lot of this is the evolution from the earlier work defining the extent of human settlements (the HS in GHSL!), and it’s very welcome to see these attempts becoming more sophisticated, adding more depth and providing more detail than what it has already been shown possible. It was not surprising to see a lot of work also towards identifying, measuring and monitoring disasters, vulnerability and exposure. Underlying it all was the looming presence of climate change and the consequences it is increasingly having on human systems. And one of the key distinctions between this meeting and almost any other one I can think of is its ambition to combine these domains with socio-economic aspects. Of course, population estimates is by now a staple of this community, but we also heard from efforts to characterise the building stock, the degree of urbanisation, or poverty, to name a few.

I identified three key perspectives. One is presentations on advances in the field, technical or otherwise. What are the things we can now do we couldn’t a few years ago? The second is a focus on introducing foundational layers. The word foundation has lost much meaning in the past few years “thanks” to the AI hype around LLMs¹, but its use here referred to something more meaningful: data layers built to develop a lot of applications on top of them, to be used by a wide range of stakeholders in a variety of contexts, and relied upon for many years to come. This aspect of temporal continuity for me deserves special praise. While the Valley mentality of “disrupting”, using the latest and greatest to put out catchy data products has its (mostly demonstrational) value, to me it pales in comparison with the commitment to support a data product over time.

All of the above stems from a series of shared values, a common narrative, that permeated through pretty much everything that was said in the meeting. The first is the very clear ambition to develop and use data to inform real decisions. There was a very interesting debate across different sessions of how much this ambition should dictate the data we develop and how we go about this task. The appeal to tailor something as close as possible to what decision makers state they need is clear. Less clear to me until I heard it was the notion that maybe such stakeholders are not always aware of what is possible and hence, when they specify needs, miss opportunities. It is then up to us to grab such opportunities to show new ways in which data can influence policy. There was also a lot of discussion about the need for capacity building, for addressing that “last-mile delivery” challenge to make sure the data and insights we develop have real impact. I half joked that, in some cases, I’m not sure how long that mile is. Sometimes, it feels our outputs should inform decisions, but in reality there’s a broader gap between them and the evidence needed to make a difference. At any rate, that this conversation featured so prominently across sessions seems to me like like a very healthy pre-condition to figure out the best way forward. And, finally, the third common thread was the value of Open. Everyone here understands that, for this work to be relevant, it is imperative it be openly available through permissive licenses. This is in contrast to other academic fora where my sense is that openness is seen as a desirable though not critical feature of work. I think the Human Planet folks are “on the right side of history” here.

After touching on domains, perspectives and common threads, I reflected on themes that, in my view, will remain relevant in the coming years, despite all progress already made. The first was the tension between developing global products and aiming to influence local decisions. This is what I called the everything, everywhere, all the time goal of the data products we develop. This is not only an aspirational goal, it is one whose goalposts are constantly shifting (what was “high resolution” or “frequent” five years ago is no longer now), so the need to always push the envelope does not go away with technological advances. To me the real value of the goal is not achieving it per-se (it is always going to somehow elude us), but to help focus our minds about the direction of travel and the “itinerary”: what are the pieces we really cannot sacrifice and which ones we can give up in the name of actually existing datasets? The second point I raised was that notion of “last-mile” discussed above. Figuring this one out will keep us entertained for a while. And the third was the need to continue standardising and harmonising data and approaches to make the ecosystem more useful than the sum of its (data product) parts. As more datasets are created, this becomes more important, but also more onerous.

I closed with three thoughts this Human Planet Forum has stimulated. First is this notion I’ve been mulling over for a while of EO as a data source of first resort. For a long time, at least in social science, one would use satellites because the data one was really interested in wasn’t available (a census, a survey, a building cadaster….). I think the time is ripe for this to change. Data from satellites (and the techniques we now have to work with them) have advanced to a point where I think, in many cases, they make for the best option. This is not fully obvious to everyone (yet) and perhaps it needs a bit more of shouting from people like us to spread this gospel. The second is the value, not only of pushing the boundaries of what is possible with these data, but also to bring such boundaries to the masses. So much of science gets “locked” in niche communities because it is too complicated, obscure, or there is no effort to disseminate. We cannot afford this with advances in satellite data. In this context, I really take away the idea of the “last-mile” as a neat way to encapsulate much of this challenge (and, perhaps, part of its solution). The final reflection I made is that there’s a lot of opportunity in bringing in conversation work along these lines of the Global North with that of the Global South. A lot of the focus in this community has historically focused in less developed countries (see the point about data of last resort above). As technology gets better and becomes more relevant not as a substitute for another data, but as the main focus, I think there’s a great opportunity for all the lessons learned while working on the Global South to be shared and amplified elsewhere. Yet more avenues for cross-pollination and collaboration.

And that was it. As I mentioned at the start, these were three very intense but extremely productive days. Michele and team did a stellar job in putting a fantastic show together and I’d like to thank them again for letting me be part of it. I hope to see many of the participants again very soon in different venues!

Ironically, an area I expected to hear more here was foundation models for satellite imagery but, alas, it was barely mentioned. Perhaps for the better, although I’d have very much enjoyed seeing this community’s take on the new wave of computer vision models trained on satellites for satellites. ↩︎

Entry for #30DayMapChallenge

Thu, 06 Nov 2025 15:54:01 +0100

I have an entry today at the GDSL’s #30DayMapChallenge with an attempt at “Dimensions”. It’s a story of 64 dimensions, mapped in two, with a bit of an extra dimension.

Official description:

This “map” is a projection to 2D of the 64 dimensions provided by Google’s Satellite Embedding V1 for all pixels of 100m x 100m in Liverpool for 2017 and 2024. Each dot is thus one area at one point in time. Because embeddings encode semantic similarity, nearby dots represent similar areas. Three areas (A, B, C) with substantive change are highlighted, and this change can be seen in the “journey” across the map from their 2017 location to that in 2024. Suggestive aerial images are included also to help understand the nature of the change.

Credits:

Embeddings provided by Google Satellite Embeddings V1
Aerial images are provided by Esri World Imagery
Liverpool boundary used to filter pixels by ONS

🔗 The City As Text

Mon, 03 Nov 2025 23:06:35 +0100

Neat paper by a great gang.

Metadata

Author: Jonathan Reades, Yingjie Hu, Emmanouil Tranos, Elizabeth Delmelle
Category: pdf
Document Tags: paper
URL: www.nature.com/articles/…

Highlights

This Review seeks to ground this opportunity in an introduction to the kinds of text and tools available to researchers, providing examples of the state of the art in urban research while contextualizing these applications in the broader framework within which this interest in textual data evolved.

(Satellite imagery) embeddings for the rest of us

Fri, 24 Oct 2025 14:52:00 +0100

Earlier this week, I attended a workshop on Geo Foundation Models put together by Weiming Huang and Nick Malleson, both at Leeds. It was a small group, high interaction day with plenty of coffee breaks to follow up con comments, and discussions as close to blue sky as academia permits these days. As the cool kids say, extremely high signal to noise ratio.

My contribution was a five minute talk on why embeddings (and, in particular, embeddings from satellite imagery) are a very cool technology we should be paying more attention in social research and policy. I titled it, in an attempt to sound clickbait’y, “(Imagery) embeddings for the rest of us”. The point I wanted to make was that, in my view, embeddings are one of the coolest (new) ways we have to democratise access to much of the value that satellite imagery has to offer. This is particularly so for communities who have not been able to engage much with but stand to benefit from satellites. But I’m getting ahead of myself. In this post, I wanted to give a quick overview of what those five minutes were. Here you go.

I started framing embeddings from Imago’s perspective. At Imago, we work to make satellite imagery more useful, useable, and used across social research and policy. A big part of this is about developing data products that translate pixels into data that meet our users “where they are”. That is, we take relevant information from pixels and provide it in familiar formats (e.g., Census geographies), in transformed/aggregated ways (e.g., tabular) that resonate more with how social mindsets would think.

Then I moved on to embeddings. It was a bit silly to include a slide on what embeddings are for a room full of experts on this area. Nevertheless, I did it because I thought it’d be useful to frame how I see embeddings in this context. As such, I defined embeddings as the internal representation a neural net builds from an image. This ends up being a vector of values that provides a dense but compressed representation of the statistical information encoded in an image. In more human-friendly terms, this is a bit like “an image, as seen by a computer”.

Now, here’s where the talk starts getting more interesting (hopefully). Why are embeddings, such an obscure property of modern neural architectures, so important for socially-minded folks? In my view, at least for three reasons. First, it’s a very direct translation of what is essentially a multi-dimensional tensor (an image) into tabular format. The embedding is a flat, one-dimensional (mostly) representation of an image¹, a very complex data structure. It’s a “buffer” that helps the non-initiated user to not have to touch a raw image, with all of its challenges, but to still get most of the benefits of doing so. Think of it as having the cake and eating it. Second, embeddings are not limited to a single type of image. Modern models are multi-sensor (i.e., they can incorporate different satellite feeds) and even multi-modal (e.g., combining satellite with other data types such as traditional geographic features). To me, this is an opportunity to make many data feeds, traditionally left aside for being “too hard to work with”, a first-class citizen in “tabular-land”, and maybe even a way to integrate seamlessly different communities that’d usually not speak to each other. And third, it’s 2025, we’re talking about embeddings because they’re tightly linked to foundation models, pre-trained general purpose encoders that can generate such embeddings easily once available. This is a really exciting field to observe these days. In the talk, I included a slide with examples of such models released (mostly) openly from Google, NASA, ESA, IBM and Cambridge. All of those examples were, at most, three months old.

As an illustration, I gave a few examples of what one can easily do with these embeddings. They’re ideal for “semantic search”, where you are interested in finding locations that look, in fundamental ways, similar to another one (e.g., what is another area in the UK that looks like my neighbourhood in Liverpool?). They’re natural inputs for unsupervised classifications built with K-means or more modern algorithms (e.g., what are the key types of areas in this region?). And they have a lot of potential to help easily spot change (e.g., has this area changed between the two periods for which we have images?). Of course, these are the “standard” uses embeddings are being used for. One of the things I’m really excited about taking embeddings to a much broader audience of domain experts is seeing what they can do with them to help solve their specific challenges.

I closed the talk reflecting a bit why this is not commonplace yet. In particular, I brough up three thoughts. The first one is that what I had just said sounds likely obvious to the group I was speaking to (experts at the intersection of AI and Geo), but to pretty much no one else. We were about 30 people and I’m not sure many more in the UK (in relative terms) might appreciate the power of these ideas. We need to change this and I think this group is ideally placed to do so. Then I moved on to the two key challenges I see in widespread adoption of embeddings among social folks. One is definitely technical: it is still tricky and cumbersome to work with embeddings. This I’m less worried about because I can see how there are ways in which we could lower the access barrier and, more importantly, we already have vehicles (e.g., Imago and the rest of SDR-UK data services are a great example). So, things seem in motion on this front. The other one is more philosophical: embeddings are tremendously useful, but they’re not the most transparent way to work with imagery, precisely because the compression that makes them very useable also makes them obscure. For good reasons, social scientists and adjacent folks tend to be very sceptical of obscure measurements. But this doesn’t mean there’s no value at all in engaging with the technology. We need a lot of evangelism and a bit of research to bring better understanding of how to use embeddings productively in these domains.

And that was that! In classic professorial style, I totally over-run my five minutes, something I’m not proud of. Weiming very politely brought everything back in line and we moved on. Again, thank you so much for putting together such group and for thinking of me as part of it! If any of the above resonates with your, please do get in touch with us at Imago! We’d love to hear from your and start a conversation.

Here I focus on images because this is where my interests lay, but the idea of embeddings extends to pretty much any data type a neural net can deal with. Which is to say, to pretty much any data type you can think of. ↩︎

Thu, 16 Oct 2025 11:42:08 +0100

🎧New episode of the #GLaDpodcast 🎧 We liked talking to Wenfei Xu so much that we invited her back! Come for the fancy data, stay for engaging conversation about hopping between academia and industry, traversing disciplines, and… an Exhibitions entry in your CV.

🔗 GeoFM: how will geo-foundation models reshape spatial data science and GeoAI?

Thu, 18 Sep 2025 09:13:29 +0100

This was a much more insightful read than I anticipated. The first part is a fantastic introduction to the idea of state of the art foundation models today, in particular in the Geo space. The second is more prospective, and thus a little more speculative. Either way, very good food for thought.

Metadata

Author: Krzysztof Janowicz, Gengchen Mai, Weiming Huang, Rui Zhu, Ni Lao & Ling Cai
Category: article
Document Tags: paper
URL: www.tandfonline.com/doi/full/…

Highlights

Given these three motivating factors, GeoFM can be defined as follows: Geo-foundational models are foundation models specifically trained on heterogeneous spatiotemporal data, capable of reliably performing advanced spatiotemporal reasoning, and designed to incorporate spatial, temporal, and other contextual factors into their output to support a wide range of (geo)spatial downstream tasks in geography and neighboring disciplines that benefit from a spatial or geographic perspective.

Just as LLMs encode the syntax, semantics, and pragmatics of human language, GeoFM could encode the language of space, i.e., the place-agnostic properties that define geography – spatial dependence and heterogeneity (Anselin,Citation1988) and its related concepts such as scale, adjacency, spatial and temporal scopes, and so on.

why do we need geo-foundation models (GeoFM) at all, and what exactly are they or will they be? First, foundation models can only generalize within the scope of their training data.

Second, many geospatial tasks are highly specific

Third, geography is inherently local/regional or contextual.

GeoAI advances along two major dimensions: (1) it applies novel methods and technologies from the broader AI and machine learning community to geographic and geospatial research questions and (2) it feeds its own, novel theoretical and methodological contributions back to the broader AI community

location embeddings can be trained separately and concatenated with the embeddings representing learned building footprints, land classes, and so on (Mac Aodha et al. Citation2019; Yan et al. Citation2019; Mai et al. Citation2020). Note: This is an idea I’ve had for a while and would be good to check some of these references to see how they approach it. Although modern foundation models were not yet on the horizon in the early 2010s, it was already clear that the era of custom, single-purpose models was slowly giving way to workflows developed around reuse and transferability. This shift raises a key question for GeoAI research: how can we distinguish progress driven by GeoAI-specific innovation from improvements mostly gained through the application of transfer learning (and related methods) from general-purpose models?

The successful combination of few-shot, prompt engineering, and transfer-learning methods on top of powerful general-purpose models raises the old question again: is spatial really special?

we can roughly classify the existing GeoFM-related research into the following categories: 1) adapting existing FMs on geospatial tasks via prompt engineering and task-specific fine-tuning; 2) developing advanced LLM agent frameworks for geospatial tasks; and 3) developing novel geo-foundation models via geo-aware model training and fine-tuning.

we further classify the current GeoFMs in four categories based on the data modalities they support and their application scenarios: geospatial language foundation models, geospatial vision foundation models, geospatial graph foundation models, and geospatial multimodal foundation models.

three major ways of realizing GeoFM or using generalist FM

For now, it is unclear whether one of the paths is preferred to approach the vision of generally capable GeoFM so that the research community could consolidate our efforts, or if this is task-dependent, and, hence, varying paths should be taken for different types of tasks.

Designing architectures that can jointly process such heterogeneous data, scale to large datasets, and accomplish effective cross-modality alignment remains a major open challenge.

A fundamental question is whether those subjective and complex human experiences should become part of GeoFM.

this raises concerns about GeoFM misrepresenting geography, be it by introducing bias or by learning representations that do not align with those of groups or societies.

spatial priors should ideally be incorporated into the pre-training of GeoFM […] those priors change across scale, resolution, modality, and so forth, and it is presently not clear how to best handle those. For instance, should they be explicitly engineered or implicitly learned?

Without co-evolving our data and benchmarks, the true potential of GeoFMs will remain constrained.

most present work on AI alignment does not account for regional, e.g., cultural, differences. However, as geographers, we know that the aforementioned societal goals, values, and norms vary greatly across geographic space and time – without any being inherently superior to others.

skills that help us better interact with such agents, critically think about their outputs, align AI with societal goals, and so on, will increase in importance.

Wed, 17 Sep 2025 11:57:29 +0100

🎧New episode of the #GLaDpodcast 🎧 Everything you ever wanted to know about mobile phone data in social science and never dared to ask, answered neatly in an entertaining™️ conversation. Check it out here, or wherever you get your podcasts:

🔗 Mission Critical -- Satellite Data is a Distinct Modality in Machine Learning

Tue, 02 Sep 2025 20:50:15 +0100

Some of the arguments made here would ring obvious to traditional spatial analysts, others to traditional remote sensers and, I suppose, many might seem “bread and butter” for the ML crowd. But it is not each individual argument that is the point here; it is putting them together, now, and in a contemporary and fresh framework that makes this paper worth a read. Well worth it indeed.

Metadata

Authors: Esther Rolf, Konstantin Klemmer, Caleb Robinson, Hannah Kerner Category: article URL: arxiv.org/abs/2402….

🔗 Why We’re Talking About a Centralized Vector Embeddings Catalog Now

Sun, 31 Aug 2025 15:59:32 +0100

The white paper mentioned below is well worth a read. It puts in much more eloquent words many of the reasons why I’m very excited about the new generation of satellite foundation models and the potential embeddings have to make satellite data more useful, useable, and used! A lot of food for thought and great argumentation for why we need to think about satellite images more and more like abstract tables than like images of pixels.

Metadata

Author: Nathan Zimmerman
Category: article
URL: element84.com/machine-l…

Highlights

our team published a detailed white paper in which we make the case for how Earth Observation (EO) data providers such as NASA can dramatically improve access to their data by creating a centralized vector embeddings catalog

Wed, 13 Aug 2025 15:59:16 +0100

We gave in to the hype and did one #GLaDpodcast episode on how we use AI, for Geography, Life, Geography Life, and data…

Wed, 02 Jul 2025 09:34:57 +0100

New PhD, a collab between IBM Research, SDR-UK’s own Geographic and Imagery Data Services to explore using vision foundation models & high resolution imagery of the Liverpool City Region. If this sounds like you (or a friend!), all info here!

Fri, 13 Jun 2025 12:14:40 +0100

Getting excited for ESA’s Living Planet Symposium, to happen in Vienna in just over a week! I’ll be there Sunday to Thursday, who else is coming? hit me up if you’d like to talk all things Imago or just catch up!

The case for satellite imagery in social science and policymaking: A sketch from my talks in China

Thu, 29 May 2025 23:26:29 +0100

Last week I came back from ten days in China on a research project. It was a whirlwind tour with five cities, and lots of opportunities to interact with both the, academic and otherwise, Chinese world. It was fascinating. At many levels, it felt like a peek into the future.

As part of the trip, I had the opportunity to give two talks, one at the Chinese Academy of Sciences (CAS) in Beijing and another at Southwest University in Chongqing. Both were titled “Making satellite imagery more useful, usable, and used in Social Science and policymaking”, and both had a very similar structure. The CAS talk was a bit longer, and it allowed me to illustrate practically many of the ideas I talked about in the first part using our ongoing EuroFab. Here I want to focus on the more conceptual bit, which aligns very much with the motivation behind Imago.

The talk tries to build the case for paying more attention and interest to satellite imagery as a source of data and information in the context of social science and policymaking. I structured this argument in four acts¹: the value proposition, the promise, the reason, and the gap.

Start with the value proposition. We’re at the confluence of three trends that make this a unique moment to look at satellite imagery with “untraditional” eyes. One, there’s never been more and better satellite(s and) imagery available. Launching stuff into space is becoming dramatically cheaper than it used to be. As Econ 101 would predict, you lower the price of something, more of that is bought, and we have more and more satellites being placed on orbit (more data). These are also benefitting from the revolution in consumer electronics of the last few decades, so the sensors on board are able to capture much more than before (better data). Second, we have better ways of extracting information from such imagery. Images contain a lot of useful information but it’s all encoded in pixels that don’t mean anything in themselves. To make something useful, you need a “magic decoder” that turns pixels into buildings, roads, land uses, etc. Well, the last fifteen years of progress in computer vision have delivered just that. From the first deep learning models of the early 2010s, into the more advanced neural nets of the end of the decade to contemporary foundation models for vision, how we teach computers to see things has undergone nothing short of a revolution. And third, which seems less relevant but it’s the piece that makes it all possible, the technology stack required to access such algorithms and operate on such data has been dramatically democratised. Compute is cheap(ish) and software is free(ish). It’s a brave new world.

Now the promise. What the confluence of the three trends above means for social researchers and policymakers is we can now do at least two things we couldn’t before. One, to measure things we haven’t been able to measure (at scale); and two, to measure better, sooner and/or more often things we’re now measuring slowly, late and sparsely. Both are, in some ways, the two sides of the same coin. They capture how the same “opening up” of new sources of information affect different status quo. In some cases (e.g., temperature, air quality, certain features of the built environment such as solar panel installations), we have not been able to measure certain phenomena that are relevant for social processes at the scale and detail required to consider them seriously in our work. In others, we do have a current solution, but it is lacking in many ways and we use it because it’s better than nothing, not because it’s good. For many of these cases, I think satellite imagery is poised to redefine what we consider acceptable for data feeding into research and policy.

Why, beyond “just because we can”, should we try to realise such promise? The short version is we’ve never needed new, timely and accurate data more than now. The world is becoming more unstable and unpredictable (e.g., climate change, spatial inequalities). We can’t “wait for the next Census” (which might not even happen in some places!) to know how society and the built environment are changing. Decisions need to be made before then and, for those to be meaningful, there’s a whole lot of understanding we need to unlock first. And, by the way, this is not a clash between traditional sources of data like the Census and newer ones like satellites. We need both of them, separately, but particularly in tandem: satellites can “stretch” the value of Censuses by, for example, providing additional context; and most of the value held by imagery relies almost entirely on our ability to relate them to existing measurements of phenomena we want, of labels. Our best shot at that “labelling” in the social realm are traditional sources.

And, finally, why aren’t we already realising this promise? This is what I called The Gap. Again, three main reasons in my view. One, imagery is big. If nothing else, there is a lot of it and it takes a lot of space on storage disks. To a point that changes how you have to think about working with it (this is the “it doesn’t fit in your laptop” problem). Two, imagery is hard. The problem is not only that managing a large volume is challenging in itself, it’s that it is also non-trivial to make something useful out of images. Something something, magic decoders, something, something. And, yes, these have become much more accessible, but it’s still the case the science underpinning all of this is tricky. And, three, imagery is different. We don’t train social scientists to work with images. Local government officers and government analysts don’t know where to start to make sense of it all. This is in contrast to other disciplines where imagery is front and centre, their bread and butter. Social sciences have, for a long time, spent all of their training allowance on other skills and techniques that are fundamentally different.

So that’s it, my 20 minutes² to convince you are up. If you’re interested in these ideas and in acting on them, stay tuned for everything we’re doing at Imago. It’s still early days so much of what we’re focused on is on getting started. Like any big ship, getting momentum takes a lot of energy and time. But once you’re going…

An unwelcome departure from my beloved “rule of three” but, in this case, I do think it was warranted ↩︎
That’s what it took me in the talk, Firefox says this should take you 6 minutes to read. ↩︎

🔗 OSMlanduse a dataset of European Union land use at 10 m resolution derived from OpenStreetMap and Sentinel-2

Thu, 08 May 2025 23:54:34 +0100

Metadata

Author: Michael Schultz, Hao Li, Zhaoyan Wu, Daniel Wiell, Michael Auer, Zipf Alexander
Document Tags: paper
URL: https://www.nature.com/articles/s41597-025-04703-8

This is a very interesting one, where a standard (CORINE) classification is mimicked with OSM where enough good data is available, and then sparser areas are filled in with satellite data and standard ResNet’s. A useful pattern that’d be interesting to see if it works in less standard setups as well.

Highlights

large-area fusion of OpenStreetMap and Copernicus data at a spatial resolution of 10 m or finer and can be applied globally.

land use labels from OpenStreetMap and remote sensing data to create a contiguous land use map of the European Union as of March 2020.

Country-specific deep learning convolutional neural networks and Sentinel-2 feature space composites of 2020 at 10 m resolution were employed. The overall map accuracy is 89%, with class-specific accuracies ranging from 77% to 99%. The data set is available for download from https://doi.org/10.11588/data/IUTCDN and visualization at https://osmlanduse.org.

LULC products benefitted most notably by the use of remote sensing, its proliferation through open data policies4 and artificial intelligence5. Currently the further accelerated use of such technology is primarily limited by the availability of sufficient thematically labelled data

Given the fragmented availability of OSM data and opportunistic availability of thematic content and depth, resulting LULC products are consequently incomplete in terms of spatial coverage. Such gaps in unlabelled LULC data can be addressed by performing basic classification of remote sensing data, using known areas as training data

Copernicus Sentinel 2 (S2) 10 m multi spectral feature space processed through Food and Agriculture Organization (FAO) sepal.io system. Note: This is an interesting project, note to explore further. Feature space was a best pixels medoid composite of Sentinel 2 bands red, green, blue (RGB) and near infrared (NIR) at 10 m of the past three years as of April 2020.

Our decision to train separate classification models per country stems from the varying completeness and likely slightly different tagging cultures of OpenStreetMap data across Europe, may differ at national borders.

🔗 OSMnx Reference Paper Published

Tue, 06 May 2025 18:34:32 +0100

Metadata

Author: gboeing
URL: geoffboeing.com/2025/05/o…

Highlights

Keep on keeping on… congrats Geoff!

This year will mark the 10th anniversary of my work on the OSMnx project. It recently reached version 2.0 with a slew of new features and enhancements. If you haven’t used it before, OSMnx is a Python package to easily download, model, analyze, and visualize street networks and any other geospatial features from OpenStreetMap.

🔗 High-spatiotemporal-resolution mapping of global urban change from 1985 to 2015

Mon, 28 Apr 2025 09:23:40 +0100

Metadata

Author: Xiaoping Liu, Yinghuai Huang, Xiaocong Xu, Xuecao Li, Xia Li, Philippe Ciais, Peirong Lin, Kai Gong, Alan D. Ziegler, Anping Chen, Peng Gong, Jun Chen, Guohua Hu, Yimin Chen, Shaojian Wang, Qiusheng Wu, Kangning Huang, Lyndon Estes, Zhenzhong Zeng
Document Tags: data paper cities
URL: https://www.nature.com/articles/s41893-020-0521-x

There’s plenty of good stuff here. The thing that stuck with me was:

global urban extent has expanded by 9,687 km2 per year. This rate is four times greater than previous reputable estimates from worldwide individual cities, suggesting an unprecedented rate of global urbanization. The rate of urban expansion is notably faster than that of population growth

This one also struck a cord:

the global urban extent increased from 362,747 km2 to 653,354 km2 from 1985 to 2015, representing a net expansion of 80% […] During the same period (1985–2015), data from the United Nations show that urban population, an essential driver of urban area expansion, increased by 52% […] Thus, much of the newly developed urban lands were not used for housing but for other purposes (for example, commercial and industrial districts).

I’m not sure the last sentence follows from the previous ones. The economist in me probably thinks people consume more land per head (i.e., bigger houses, bigger plots, bigger cars that require bigger lanes). But, as they say, this is an empirical question…

Highlights

we map global annual urban dynamics from 1985 to 2015 at a 30 m resolution using numerous surface reflectance data from Landsat

global urban extent has expanded by 9,687 km2 per year. This rate is four times greater than previous reputable estimates from worldwide individual cities, suggesting an unprecedented rate of global urbanization. The rate of urban expansion is notably faster than that of population growth

our understanding of how cities change in space and over time is limited by the lack of spatially and temporally comprehensive urban land cover data at a high resolution6,7. Development of this information lags behind that of state-of-the-art non-urban landcover change data

The current understanding of urban growth is largely based on demographic (population) data rather than information describing the spatial and temporal patterns of urban land-cover change.

we defined the extent of urbanized land between 1985 and 2015 by fusing four available global urban-extent maps with similar spatial resolutions for 1985 and 2015 (that is, the Global Human Settlement Layer6,19, the Global Urban Footprint20, the Global Urban Land 7 and the Global Artificial Impervious Area16; Supplementary Table 1). We extracted cells from the two fusion maps that changed from non-urban in 1985 to urban in 2015. We then used an annual time series (1985–2015) of the normalized urban areas composite index (NUACI) to detect the year of urbanization and green recovery (vegetative regrowth or new plantings in built environments) for each pixel within this urbanized extent. Finally, we assessed the accuracy of all derived products over the past three decades Note: Approach the fused GAUD global urban extent maps are robust across different urban ecoregions and have relatively high mean accuracy.

Better accuracy is mainly attributed to (1) our GAUD data having urban regions that are consistent in different urban products and (2) inconsistent regions being reclassified using a locally adaptive random forest classifier.

the global urban extent increased from 362,747 km2 to 653,354 km2 from 1985 to 2015, representing a net expansion of 80%

During the same period (1985–2015), data from the United Nations show that urban population, an essential driver of urban area expansion, increased by 52%

the rates of urbanization in Asia, Africa and South America accelerated during the 30 yr period but began to slow in North America, Europe and Australia

the bulk (~70%) of urban growth since 1992 occurred at the expense of agricultural land, followed by grasslands (~12%) and forests (~9%)

the dataset can be used to improve our understanding of how urban areas affect carbon cycles, a negative anthropogenic impact that has not been studied thoroughly30,31 because of the lack of accurate and continuous global urban extent maps. The GAUD data can also be used to study how urban expansion drives global changes in energy and water use and in turn triggers changes in water and energy fluxes between the land and atmosphere25,32. GAUD may also aid research into the impacts of rapid urban expansion on habitat and biodiversity loss or the extent that health risks arise from urban heat island effects.

"Geospatial AI for Land Use" (my talk at OECD's WPTI'25)

Sun, 27 Apr 2025 10:04:01 +0100

Last week, I contributed to the OECD’s 48th session of the Working Party on Territorial Indicators. Working Parties are a mostly internal affair where the different members of the OECD meet around specific topics to discuss progress, share experiences and coordinate. This is my second one, and they are a very interesting experience for an academic in that much of what is discussed is various forms of applied research, but the format and delivery is rather different than in a normal academic meeting.

I contributed a ten minute talk on geospatial AI for land use, and I thought I’d summarise here what I presented. I labelled it as an “opinionated version of our recent report on the topic”, and I stand by that definition. I tried to give an overview of the opportunities I see for (geospatial) AI to support the understanding, modelling and management of land use. Much of what I said is in the report (possibly in a slightly more eloquent and formal way), but I also mixed in some of the lessons we’ve learnt from our ongoing EuroFab project with OECD, Charles University and ESA.

To me, these are the three areas where (geospatial) AI intersects with land use:

More data
Better modelling
More intuitive interfaces

Start with data. Much of what modern AI/ML does is making data that traditionally were beyond the realm of computation, computable. Think of text, audio, or images. These are all sources of (unstructured) information that land use experts have only been able to access in a qualitative and manual way. Modern techniques such as foundation models for both text (LLMs) and image make it possible to treat these sources as quantitative data. And this is a big deal. Think of the amount of imagery that is coming from satellites, or how much data about, say, the planning system is locked in PDFs and word documents. Making these as accessible as a Census table will bring new sources on which to base evidence in a more timely fashion.

Then there’s modelling. Data in themselves are not information, insight, or knowledge. The bridge between them is often modelling. Modelling in land use is of course not new. But new advances in AI/ML are giving it a notable boost. We can both make better models with traditional data (e.g., a lot of the tree-based algorithms like random forests and XGBoost have revolutionised making predictions with structured data) and expand such models to accommodate the sources of data I mention above in a native way. In land use, this is also a pretty big advancement. Think of the full-fledged industry of land use regression models, where different outcomes (e.g., air quality, land use change) is explained as a function of land use characteristics. How that function is modelled and how land use is characterised/measured is poised to radically change in the coming years.

And then there’re interfaces. How much effect and impact the results from the modelling exercises in the previous paragraph can have is mediated by how they are presented and made available to the public. It’s 2025, so I don’t have to spend many words on how modern (Gen)AI is revolutionising human-computer interfaces. An example of how this could pan out is the chatbot interface we built on top of our DemoLand tool for exploring urban land use scenarios and that features in Section 2 of the report. This is of course not an area specific to land use, but I think land use is a good candidate to benefit particularly from this trend. The outputs from land use modelling are usually sophisticated and non-trivial to understand. At the same time, if we want them to have an effect, they need to be understood by non-technical folks such as policy makers, practitioners and the general public.

And that, pretty much, covered my ten minutes! It was fun to think of how to present results from our research to folks who are not academics but deeply care about the topic. This year, I had to participate online, but I hope I have future opportunities to come in person and meet participants over coffee breaks (or even during the timetabled cocktail!).

Tue, 22 Apr 2025 22:49:07 +0100

Headed to GISRUK’25. Not presenting, chairing, paneling or anything official, just taking it all in as a consumer this time. Hit me up if you want to talk Imago, satellites, cities… or just say hi! 👋

🔗 Generative AI

Wed, 16 Apr 2025 23:19:51 +0100

Metadata

Author: Michael Batty
URL: https://journals.sagepub.com/doi/full/10.1177/23998083251332093?mi=ehikzz

Highlights

new technologies are now invented so quickly that it is no longer useful to separate them out from one another. They crowd into each other, disrupting what already exists, only for many of them to come back to regenerate and rekindle what has already been invented.

These systems are moving science from being theory-led to data-led, from deduction to induction, although this does not mean that theory is being dispensed with, only that new ideas can emerge and converge from any or both of these directions.

generative AI is uniquely suited to designing solutions which improve the human condition, in our own case the quality of life, the sustainability and the prosperity associated with cities. In a previous editorial (Batty, 2024b), I sketched out how generative AI was an early theme in the development of configurational statistics, shape grammars, design methods, pattern languages, and related optimisation models which we published in this journal. In fact, this is likely to herald a revival in ideas about design coming from this area in the next decade.

🔗 Satellites are getting too good for forest carbon?

Sun, 06 Apr 2025 14:22:34 +0100

Metadata

Author: Anil Madhavapeddy (anil@recoil.org)
URL: anil.recoil.org/notes/for…

Highlights

There’s a letter in Science today from a bunch of well known remote sensing researchers that make the unusual point that modern satellite resolution is getting too good to be accurate for forest carbon estimation.

but this resolution (0.3-5m) is too high for mapping forest carbon. Forest carbon has a natural resolution constraint: the size of an individual tree.

This is a great reminder that, sometimes, good spatial thinking trumps “better” technology. The insight applies much more widely than forest carbon estimation.

🔗 Formalising the urban pattern language: A morphological paradigm towards understanding the multi-scalar spatial structure of cities

Sat, 05 Apr 2025 23:30:18 +0100

Metadata

Author: sciencedirect.com
Category: article
Document Tags: paper
URL: https://www.sciencedirect.com/science/article/pii/S0264275125001544?via%3Dihub

Highlights

urban patterns, the recurring configurations or arrangements of urban elements (Marshall, 2004), to reduce complexity and summarise the characters of the urban form.

pattern language represents a set of guidelines or solutions for reoccurring design problems derived from historic and contemporary urban environments.

urban landscape as a series of patterns of different urban elements at varying scales

The urban pattern language conceptual framework is built upon two fundamental hypotheses

firstly, that distinct patterns of different urban elements exist at various scales are not arbitrary but follow specific rules,

and secondly, the rule or relationship between the diverse patterns is unique with potential as a reflection to the cities' particular background and needs.

it is important to identify the scales of these patterns, whether the focus is on an overarching city blueprint or the intricate design of a specific neighbourhood

The language could be interpreted as the rule or the relationship between the patterns coming together to form the solution.

Note: This is an interesting way of summarizing the information on metrics across scales and the two cities.

The quest to correlate urban form with emergent dynamic data has taken centre stage over the past decade.

[Note: Good set of references of papers linking urban form with other phenomena to follow.]

Sun, 30 Mar 2025 16:39:54 +0100

New episode of the #GLaD podcast just dropped, Time (mis)management. Everything you always wanting to know (or not) about why we’re always late, and maybe that’s OK…

gladpodcast.podbean.com/e/episode…

Sun, 23 Mar 2025 05:45:34 +0100

Headed to Detroit for the #AAG2025. Excited to spend a week with fellow Geography nerds in one of the most interesting urban stories of the XXth Century! Catch me at the sessions (image via Rachel, thanks!) we’re organising w/ Rachel Franklin, Elizabeth Delmelle and Isabelle Nilsson. Come say hi!

Wed, 19 Mar 2025 11:25:52 +0100

Imago the SDR-UK Imagery Data Service, is looking for a lead Research Software Engineer to help us design, build and run the tech platform that’ll power the service. Join us to make satellite data more useful, usable and used! https://jobs.ncl.ac.uk/job/Newcastle-Senior-Software-Engineer/1182366701/

FutureBuild'25

Thu, 06 Mar 2025 15:53:36 +0100

Earlier this week, I participated in a [panel on the Land Use Framework](Edge Debate 179) at FutureBuild'25. This was curated by Edge, and co-panelists included Baroness Young of Old Scone (Chair), Maya Singer Hobbs, Carolyn McKenzie, and Stephen Hill. Each of us spoke for 5-7minutes and then the chair opened for questions from the floor.

In my talk, titled “Land use data to inform decision making - How it could work”, I tried to make three clear points:

Good decisions are linked to the “state” of land, and this is too complex to understand without direct evidence. (Good) data provide the context for (good) decisions.
We need data that changes “at the speed of decisions”. This context needs to reflect the current state of affairs, which changes much more rapidly than we have been able to gather data from in the past.
There’s a lot of very cool stuff happening in the world of data to support this view of the world. For example, and I may be biased here, the single most exciting development of the last ten years is the ability to make increasingly more abundant imagery from satellites computable so it can feed into these decisions.¹

Given the prompt to talk about “how it could work”, I gave a shout to our DemoLand project, as an illustration of how to combine data and AI to support land use decisions.

I closed the intervention with an afterword, two points I really wanted to make but couldn’t elegantly squeeze in the previous part:

Data (as well as the models and, eventually, digital twins they feed into) are best thought of as human augmentation rather than replacement. As much as some might like it that way, I don’t think any of this is about the robots taking over the job of the planners, it’s about super-charging planners!
Urban land is land! This is by now one of my hobby horses. Much of the land discussion (be it on modelling, understanding or affecting it through policy) is focused on “most of the land”. This makes sense to a certain extent. After all, cities are about 5% of the land. However, if we’re serious about curving emissions and building a better home for most of the population, this 5% clearly punches above its weight (e.g., about 75% emissions come from cities whom, in a country like the UK, house about 80% of the population).

This is in part why we launched Imago, to bring all this good stuff to the social sciences, public health, and policymaking arenas. ↩︎

🔗 The Guardian reviews Nord

Wed, 05 Mar 2025 19:43:59 +0100

www.theguardian.com/food/2025…

It’s part Austin Powers shag palace, part Mos Eisley Cantina from Star Wars. It really is groovy, baby.

🔗 JupyterGIS

Tue, 04 Mar 2025 11:42:17 +0100

blog.jupyter.org/real-time…

Baking a bit of geo right on top of Jupyter “ is a great idea for both the Jupyter and geo worlds. Plenty of room to leverage the geo data science py-stack!

Sun, 02 Mar 2025 22:11:51 +0100

🗞️ Making Satellite Data Mainstream: Gaps, challenges, and opportunities for remote sensing experts [Industry Profiles and Activities] URL

By Aravind Ravichandran on IEEE Geoscience and Remote Sensing Magazine (11 December 2024).

Plenty of interesting points here. My favorite one is the focus on the boring but necessary aspects required to push adoption beyond the “usual suspects”. Very much an Imago theme.

Report on AI and Land Use

Thu, 14 Nov 2024 01:00:00 +0100

Geospatial AI for Land Use, by The Alan Turing Institute. Independent Report from The Alan Turing Institute - URL

How geospatial AI can help inform our land use choices. Blog post from the Geospatial Commission on the report - URL

TODAY, the Geospatial Commission released the report we¹ prepared for a project we have been working over the last year in collaboration with them. The work builds on our earlier contribution to the National Land Data Programme² last year, and the document puts in writing much of what we presented to the minister for AI and intellectual property last March. There is also an accompanying blog post Mehul and his team at the Commission put out.

Most of the report is a summary of what we learned in two specific exercises and a series of engagement events. I’ll give you the two-sentence version of each here but, if you are interested, you really should grab the report as it covers them much more comprehensively. In one, we took our initial DemoLand app, a tool that helps users explore different land use scenarios and their effect on areas such as air quality or house prices, and embedded a chat interface powered by a large language model. The original tool provided access to a lot of data and modelling that would be hard to access for non-technical audiences otherwise, but it still required the user to “know their way around”. With the new chat-based interface, exploring the results is a much more conversational experience that can reach larger even audiences. In the second exercise, we digged into the guts of the models that power land use applications such as those in DemoLand. Typically, many of these require data that is collected and released more slowly than ideally required for decision making (e.g., Census or building cadasters). We explored complementing, or even replacing, these by widely available satellite imagery. Satellite data is definitely not a new thing, we’ve had metal boxes orbitting the Earth since at least the 1950s, but there are a few recent things that make them more appealing. The revolution in computer vision (and what is now also termed AI) we have seen in the last 15 years has changed what we are able to do with imagery, even that of limited spatial resolution. In this exercise, we explore foundation models for vision (a bit like the GPT in ChatGPT but for satellite data) to see how far we could push them. The result is a series of what I consider extremely exciting results but others might see as largely dry performance scores tables. You can get a summary of those in the report. In addition to these two exercises, we also ran consultation events (at AI UK'24 and online) with experts to get a broader view on the potential, challenges and immediate opportunities of geospatial AI for land use. I could summarise those, but I won’t do a better job than the report, so head over to its “Section 3” for that.

What will probably (I hope!) catch most attention is the “Recommendations” section. Here is where we brought together everything we learnt in these exercises to propose concrete steps forward. In particular, we mention five:

1/ Identify additional areas of opportunity for satellite data to build the value case for geospatial AI.

2/ Develop a Geospatial AI Toolkit for LLMs.

3/ Expand the conversation on national foundation models to land use and geospatial.

4/ Improve access to key computational and data resources.

5/ Promote knowledge sharing and cross-discipline collaboration.

Some are self-explanatory and I suspect few will disagree with them (who is against more knowledge sharing?). Others bring to the front discussions that we think deserve more attention than they’re currently receiving. LLMs, for example, are not very good at geography (there is a reason why the second L is not a G!). Before we jump in and take them off-the-self, we think there is work to do to develop the “Geography curriculum” we’d like these models to know when they help folks on spatial domains. And others seem more obvious than they actually are. Suggesting in 2024 that satellite data be used for land use change may cause unreparable eye-rolls among land use experts who’ve been doing this in an academic context for several decades. Yet there is still very little of it that has made it into “production” at scale, particularly in non environmental and physical domains such as cities and society³. So think twice before sending your eyes upwards.

Above all, and ironically given that it summarises past work, we hope this becomes a conversation starter. There is so much exciting stuff that is happening in the world of AI that could have tremendous implications for land use modelling and management. What exactly and, specially, how are debates we have just begun and are far from done. But we think they are worth having and actioning on. To work.

The team on this project spanned folks at the Commission and Urban Analytics@Turing. At Turing, Barbara Metzler and Stuart Lynn did most of the heavy lifting, and I was the lucky one to “see early demos and present it around”. ↩︎
Geospatial Commission (2023). Finding common ground: Integrating data, science and innovation for better use of land - URL ↩︎
This is one of the core ideas that made Imago a winning proposition, so watch this space. ↩︎