0:03 All right. Hi. We are Urban Futures Lab. I am Julia and this is Ben. We are trained as architects. So we worked as computational designers in architecture firms and then we veered in slightly different directions. I went more into urban data science and urban governance and Ben went more into design and ecological computing now and when we were working as architects we felt that we were a little bit in the past.

0:47 We were analyzing old data. We were attempting to solve some some really old problems and we were attempting to use this really innovative tools that we saw today. But as we also heard the architecture construction center was always a bit behind. So we try to see how to apply the tools we saw today onto qualitative metrics and our regular clients are essentially municipalities and we help cities to deal with uncertainty.

1:30 And we do it through a few ways, a few tools. We’re going to show an overview today and then we’re going to do a deep dive into one of them that I think you’ll find interesting. So we do essentially trend snapshots where we try to analyze what is coming up in a few sectors. So it is society society, economy, culture, technology development etc. We also use them then to plan scenarios.

2:02 A few of them that you can see in the next slide. Thank you. A few of them. One of them for instance is how tech companies are actually investing in their own energy solutions in order to power upcoming data centers. Another one for example is the fact one about is for example when we try to optimize the the environment of cities cities tend to become test beds for algorithms but it’s not all tech that we look at we also observed for example how how for example climate change would turn entire areas into uninsurable unins uninsurable un uninsurable we looked at it around the LA fires and how it’s going to impact for example communities but not all trends happen at the same time so they have a wave tendency so they begin they gain momentum they they reach a certain peak and then they fade out.

3:19 So for us to know what happens when and how to deal with it, it’s also important to know when everything would fall on the timeline. And to do that, we work with something that we call the vibe track. So so to check the vibes really, we analyze sentiments around certain topics in certain areas. We use essentially our own tools that to go deeper into I will give the microphone to Ben.

3:56 Hi, thanks so much. So as computational designers and architects and also industrial designer that work in urbanism a lot of people don’t get to see the tools that we’re going to show you today. The main thing that we do that one of the first thing we do is this urban vibe check but we use our favorite Swiss pocket knife sorry knife which is grasshopper of course. So the basic thing we do this is something that we don’t show our clients.

4:22 This is something that especially for this symposium. So the first thing we do is we scrape social media. There’s a few ways to do it. We’ll go into how kind of we do it. But the most important thing in scraping social media for this urban vibe check for urban design, urban analysis is the geo tag, the image and the context. That’s where we get where it is, what it is, and what is the vibe basically.

4:50 So how do we do this urban vibe check in the computational design matter? So first of all we have this geotag meta metadata from social media platform mostly Twitter and Instagram Facebook’s kind of winning out so we have the spatial identification of geoloccation and we have the tone that we can divide keywords from we have this aggregated se segment aggregated sorry sentiment for each point so geotag point and we have this positioning inside of the urban context model we show you how we built in a few slides.

5:24 And then we have this aggregated sentiment of the our case area which is where the local municipalities hired us want us to work in. So the first thing we do is we build a model of spatial data on which we interpret all the scraping models from. So the first thing we do is we call it GS scraping spatial data. We pull that out from various APIs. It’s either OSM we work with Mapbox for a bit.

5:52 Sometimes we pull it from other sources but the the Grasshopper scripts change but this logic remains the same. We have the spatial data we segment it into buildings, streets and amenities and we pull the metadata from each of them OSM and GIS they all all those APIs have a lot of metadata in them and that how we construct this 3D model. The buildings have a height. So we can construct geometry of the building.

6:22 The amenities have data. So we can tag the geometry of the building using that metadata tag. And also the metadata of the streets, the curves and also the surfaces sometime meshes but not not mostly mostly surfaces and curves. They also have these tags of data which is pedestrian path, bicycle path, bus lane, bus stops, inner city roads and so on and so forth. So once we have this constructed geospatial model in Grasshopper, we can take our scraping which is we use a few of our own custom scripts because I don’t know if you’ve done social media scraping, they it’s like keep chasing them because they always change the algorith from from scraping.

7:07 Used to do be a command line community- based open- source tool. This used to be a Grasshopper plugin. Now we build our own tools constantly to to to chase Instagram and and Twitter. But we scrape the data and we pull out three different things geoloccation images and caption. And that geoloccation is being mapped onto the previous model that we’ve made. So that in this geospatial geometry model of the city there’s already tagged with data.

7:40 We’re extra adding another scraping data of this spatial analysis of of Instagram of social media and then we get a sentiment location and we have this superposition of all the sentiment locations what people feel about them and the actual geometry of the city which gives us stuff that looks like this where we can analyze points points of interest and also the vibes of the city which is geoloccated inside the geometry of these very simple breps of buildings.

8:16 We also use it to do a lot of mobility analysis tools include the vape check. So where we can go, what you can see there, how you can get to it and how might you feel about it when you go in. This is also a pure Grasshopper screenshot. So everything we do is inside of Grasshopper. Talk about this for a second. We also we also use this to see what would an area need.

8:44 So this is something that was done around a small area in Germany when we try to see what kind of different additives amenities are actually needed and where to put them to get the optimal amount of essentially there it was revenue for the investor but also to like to essentially understand would people use it would they want it and why. So essentially we don’t look at the shortest path but like the joyful path to get to places in order to like really understand how a human being would see it.

9:30 I think this is it on our end. So if you would like to know more you can catch us at a coffee break or set a talk with us. We would be happy to tell you more about what we’re doing and where we want to take this and yeah. Yeah, that’s it. Thank you so much. To learn more about the CDFM computational design symposium series, to see the archives of previous presentations and to learn about future events, visit CDFAM.com.