From 2000-2018, rapid #urbanization in the #Guangdong–#HongKong–#Macao Greater Bay Area caused major land-use changes😲! A new framework and a three-level #Bayesian hierarchical model were used to distinguish the impacts of driving factors on newly formed and well-developed urban

This looks potentially useful for junior scholars. "The Research Paper Playbook: A PhD Student's Guide to Writing and Presenting"

Tutorial about Land Use Land Cover Classification using Machine Learning || Google Earth Engine for LULC mapping Tutorial Link: youtu.be/OdmD6kppBkQ?si… #LandUseLandCover #LULCMapping #MachineLearning #GoogleEarthEngine #RemoteSensing #GISMapping #EarthObservation #Geospatial

Grok wins hands-down at coding. It wasn’t close.

Now available on the UEA webpage: slides and videos from the faculty presentations at our 2025 Summer School. urbaneconomics.org/workshops/summ…

I'm happy to share an open letter to the Israeli government from 23 professors of economics across the US and Europe (including myself): drive.google.com/file/d/1D_Sv3J…

Next-level

1.4 billion people are living on poisoned soil. A new global map reveals where:

I'm considering becoming a prompt-engineering influencer. Prompt: "Create an AI generated map of the US that doesn't look like it's AI generated" Result: Flawless

🚨 DHS Surveys are now back online. Thanks to a grant from the Gates Foundation, we can now start requesting DHS data again.

Thank you so much Kristalina Georgieva ! I was delighted to talk with IMF about the far-reaching effects of taxes and innovation.

Great work by the @Grok team!

Does industrial policy work? I cover the theory and evidence behind it. My takeaway? The theory is sound, but the evidence is lacking — so lacking that I think it is wildly inappropriate to cite many of these papers. However, what we do have is enough — industrial policy works.

Almost a decade ago I was the Harvard economist that said that bitcoin was more likely to be worth $100 than 100k. What did I miss? I was far too optimistic about the US coming to its senses about sensible cryptocurrency regulation; why would policymakers want to facilitate tax

GPT-5 just casually did new mathematics. Sebastien Bubeck gave it an open problem from convex optimization, something humans had only partially solved. GPT-5-Pro sat down, reasoned for 17 minutes, and produced a correct proof improving the known bound from 1/L all the way to

Rosyna Keller

This seems like a wake-up call both for grad students and faculty in economics (talking my own book here a little bit...): share of economics papers that is ABOUT or USES AI increased 10X to 5% in 5 years and growth is basically vertical. Curricula should adjust accordingly...

Luis Ramos 🇻🇪 🇩🇪 Not true, GPT-5 can produce new insights and knowledge.

Mr Kodama 🇺🇦🇬🇧🇺🇸 It will be able to do that in a few years. We need a lot more compute. At the current rate AI doubles task time compute every couple of months. Some people don’t understand exponentials.