Michael The Lion

New EP on @soulclap with @AmyDouglasSings out today at all digital outlets PLUS 12” vinyl of extended remixes from @JohnTheMixer. Go to michaelthelion.bandcamp.com or any streaming site, digital retailer or vinyl outlet. We always put a message in our music, we hope it moves you

@yohaniddawela The level of bias in the detail and quantity of OSM data is a major concern. I have used these data in many modeling projects and often have had to question the usefulness results or reject the OSM approach because of the data quality issues.

Urban planning models just crossed 90% accuracy using free map data anyone can edit. A new paper builds a single deep learning pipeline that turns OpenStreetMap into a full urban intelligence system. Land use, buildings, traffic, and air quality all predicted together, not separately.  Most studies treat these as isolated problems. One model for land use. Another for traffic. Another for pollution. This one connects them. The system fuses three data layers: • OpenStreetMap for structure • Satellite imagery for surface detail • Environmental and demographic data for context  Then assigns each task a specialised model: • CNNs for land use • U-Net for building footprints • LSTMs for traffic • Hybrid models for air quality  Each model solves its own problem. The pipeline ties them into one view of the city. The results are pretty strong: • Land use classification: 91.6% accuracy • Building detection: 94.0% accuracy • Traffic prediction error: 3.6 vehicles per hour • Air quality prediction error: 2.3 µg/m³  These sit at the upper end of current GeoAI benchmarks. The improvement comes from integration. OpenStreetMap gives topology. Satellite data gives physical signals. Environmental data gives dynamics. Each fills gaps in the others. That reduces ambiguity where models usually struggle. Mixed-use zones. Dense urban cores. Noisy or incomplete maps. The system learns a more complete representation of the city. The workflow is quite simple: 1.Collect multi-source data 2.Align and standardise it 3.Train task-specific models 4.Combine outputs into urban indicators  Raw geodata in. Policy-relevant outputs out. The implications are practical. Traffic models identify congestion hotspots. Land use maps reveal missing green space. Building extraction supports infrastructure planning. Air quality forecasts guide mitigation.  All from largely open data. The constraint is compute. Training requires GPUs and careful preprocessing. Smaller cities may struggle to deploy this directly. Data quality also matters. OpenStreetMap varies by location. Even so, the direction is clear. Urban planning is shifting from static GIS layers to integrated, predictive systems. One pipeline. Multiple urban signals. Continuous updates. Cities are becoming modelled environments, not just mapped ones.Urban planning models just crossed 90% accuracy using map data that anyone can edit. A new paper builds a single deep learning pipeline that turns OpenStreetMap into a full urban intelligence system, predicting land use, buildings, traffic, and air quality together rather than treating them as separate problems.  Most existing work fragments the city into isolated tasks. One model classifies land use. Another extracts buildings. A third forecasts traffic. This paper links them into a single system. The key idea is simple. Combine three types of data that each see the city differently: • OpenStreetMap provides structure such as roads, buildings, and land use • Satellite imagery captures physical and spectral detail • Environmental and demographic data add temporal and social context  Each task is then handled by a model suited to its structure. CNNs for land use, U-Net for building footprints, LSTMs for traffic, and hybrid models for air quality. The novelty is that all outputs are combined into one coherent view of the city rather than analysed in isolation. The performance is strong across the board. Land use classification reaches 91.6% accuracy. Building detection hits 94.0%. Traffic prediction errors fall to 3.6 vehicles per hour, and air quality prediction to 2.3 µg/m³.  These results sit at the upper end of current GeoAI benchmarks, and the reason is not a single model improvement. It is the interaction between data sources. OpenStreetMap encodes topology but misses detail. Satellite imagery captures detail but struggles with semantics. Environmental data adds dynamics but lacks spatial structure. When combined, each compensates for the others, reducing ambiguity in dense or mixed-use areas where models typically fail. The workflow follows a clear pipeline. Multi-source data is collected, aligned, and standardised. Task-specific models are trained. Their outputs are then fused into multi-dimensional urban indicators that describe structure, function, mobility, and environment together.  This produces something closer to a live model of the city rather than a static map. The implications are practical. Traffic forecasts identify congestion hotspots. Land use maps reveal gaps in green space. Building extraction supports infrastructure planning. Air quality predictions guide mitigation strategies.  All of this is built largely on open data.

Where is the US Senate? NATO is a Senate-ratified treaty - it's the law of the land.

Carl Sagan's prediction of America, made 30 years ago.

This platform has become completely unusable, my whole feed is just dubious algorithmic content. Think I might be done here.

"A government of laws, not of men."

Upcoming - 4/25 - Earth Night @broadhallphl – Phila 5/8 - Rancho Deluxe show on @greatcircles 5/16 Hooked @DolphinPhilly – Phila 6/12 - Rancho Deluxe show on @greatcircles 6/18 - Dante's HiFi - Miami 7/3 - Bayleine - Cape Cod, MA

@kyle_e_walker Thanks Kyle - you are saving my bacon for my students' final projects.

Users of the tigris #rstats package: the Census website is acting up again, so the package installed from CRAN isn't working Install with `remotes::install_github("walkerke/tigris")`; I've got a new patch in place that will handle the errors for you github.com/walkerke/tigris

Franklin Roosevelt’s four freedoms- Freedom of speech, freedom of religion. Freedom from want and freedom from fear.

Censoring books.

Users of the tigris / tidycensus #rstats packages: The Census website has been blocking requests from tigris (and curl) since yesterday. (Don’t worry, the datasets are still there!) I’ve patched tigris, install with `pak::pak("walkerke/tigris@ftp-patch")` and it should work.

@kyle_e_walker Oh man. Picked today to sit down and make the final knit on a huge module for my class and the API goes boom.

The level of lawlessness, stupidity, cruelty, and vandalism .... just off the charts bad.

The view from Germany - "Forrest Gump is Dead."

What a nightmare of vandalism, stupidity, bigotry, and cruelty.

If you can, please make a donation to help fund the funeral for Andy Williams aka Yam Who? x gofund.me/199dcf1a

As I've written before: "Once a society starts accepting attacks on entire swaths of Jews—for being too liberal, too religious, too secular, too pro-Israel, too anti-Israel, too whatever—that acceptance will grow." theatlantic.com/ideas/archive/…

Trump cuts a Tesla ad at the White House, and Elon thanks him with a $100 million donation. Outright corruption.

One of the key tenets of American society is tolerance. Other people have a right to express views you find abhorrent. Support that right - especially when you disagree! If and when there comes a day when you're the one in the jackpot - you'll want your rights supported.

It's cool that I filed a report on this service about misinformation in the form of holocaust denial and got an email back like "that doesn't violate our terms." What a great internet website.