Last week I attended a training about using open data provided by ESA’s Sentinel program.
Last week I attended a training about using open data provided by ESA’s Sentinel program.
I describe a plugin that performs Discounted Cash Flow Analysis on project ideas. The goal of this plugin is to provide slightly more advanced financial analysis and calculations at the design stage beyond just calculating the area and multiplying with the construction cost.
When I first started with geodesign, design and finance seemed two different worlds. In the most simple form of financial analysis, the area of a project is multiplied by a per hectare or per acre construction cost. This type of simplistic analysis does not work in the real world and even though everyone understands this, it is very prevalent in design practice especially in the early stages. There are no simple tools to perform slightly sophisticated financial analysis on an idea.
Generally design and finance work in silos even though their work is intricately connected. One way to improve the financial capability of a non-finance professional is to provide simple tools to gently introduce financial analysis. A good technic to assess the “fair value” of a project or idea is the Discounted Cash Flow Analysis. I am not going to get into the details of it but it is quite straight forward to understand. I set about to build a plugin with the goal to provide slightly more sophisticated financial analysis for individual project ideas in Geodesign Hub. Of course it cannot replace professional financial assessments but it can be used to educate users on how implementation can work and how decisions are made in the real world away from simplistic calculations.
You can play with the plugin by clicking on the link here and a brief explanation is below
As with a lot of things finance related, there are a number of limitations of the technique. A good blog post about the limitations is here. But this can provide a good understanding of how prospective investors think and what drives their decision.
You can use the API provided by Geodesign Hub to build your plugins and models that integrate directly with the workflow. In fact, you can build paid plugins and microservices and get paid for access. I will share more details about the Store and paid plugins shortly. All of this is open source and you can see it in action on Geodesign Hub and also see the code on the Github repository.
This article is a part of a series that I call as “Geodesign Advances” where I talk about how Geodesign Hub uses state-of-the-art computing technologies to help the process of collaborative design. In this article, I will describe how we implement machine learning algorithms to help people who design to collaborate and interact with each other.
Geodesign Hub is a platform for collaborative designing. With Geodesign Hub, a number of people can simulteanously design and negotiate complex geo-planning problems. We usually have anywhere from 15-60 people from different disciplines and professional specialities and even ordinary citizens working simultaenously on a project. A project can be anything from designing a city, making a evacuation plan, preparing for dramatic change in a neighbourhood etc. Geodesign Hub is easy to understand and get started, we usually have been able to train people on the capabilities within 30 minutes.
Geodesign Hub works especially well on early stages of a design problem and is used with a group of people doing the design activity togther. To begin with, people get together and draw simple diagrams on a map to communicate their idea for improving the current state. Below is a diagram drawn on the tool. It describes a Marsh Restoration project. People add a lot of diagrams and usually a project has many diagrams: usually more than 200 some shown in the picture below.
These diagrams are drawn indiviually by different people in real time. We use the power of modern computing and machine learning tools to aid people when they draw diagrams.
Machine Learning, Aritificial Intelligence and Deep Learning are used interchangably now-a-days. Bascially, Arthur Samuel described it as: “the field of study that gives computers the ability to learn without being explicitly programmed.”
Machine learning is very prevenlant and used in a number of things that you use everyday. For e.g. when Netflix makes movie suggestions or Gmail filters spam or Amazon recommends similar products, they are using machine learning algorithms that get better over time as they analyze more data.
I dont want to get too much in to Machine learning specifics but basically machine learning algorithms fall into two main categories (there are others as well):
In supervised learning, the “right answer” is given by the algorithm based on previous data that it analyzes: i.e. a algorithm predicting a sale price for a house; or if a email is spam or not.
In unsupervised learning, there is no “training data”. Data is fed into the algorithm and the algorithm then analyzes the data to find patterns. This technique is used commonly for example in Google news, when different news articles are grouped together under the same title. The alogrithm understands that all the articles are talking about the same event without it having any understanding of the event itself. This technique has other applicaitons: it can also be used to segment customers in marketing.
Brief aside: I am currently enrolled in a the brilliant Machine Learning Course in Coursera by Prof. Andrew Ng. If you are interested in this topic and want to learn more about this, I would highly recommend this course. I learnt all of the above from there.
At Geodesign Hub we use both supervised and unsupervised learning algorithms to help in the design process, I will write about how we use supservised learning in another article but for this one, I will focus on how we use unsupervised machine learning to help designers.
As I described in the beginning of the article, the participants in a project are drawing different design ideas and interventions to “improve” the problem that a area is facing. Frequently, given the diverse participants, many people have different ideas for the same place: someone might say a empty lot should be converted into a public park, others may think it is better to have parking, while others may think that it is better to build mixed use spaces there. This is what people are drawing in diagrams.
When you have so many diagrams, it can be hard to figure out what is the content of every diagram. If I am working on the downtown area, I am only concerned about what other people think should happen in the downtown and I should be shown only the diagrams (among the 200+) that are relevant to downtown. We use supervised learning to show diagrams in a area in realtime. This is shown in the video below.
We start in a broad study area and as I zoom and pan to the area of my interest, the “nearby diagrams” is constantly updated. The algorithm understands where you are in the study area and then shows ideas that other people have for this place so you know beforehand the ideas and encourages you to discuss your idea with the others to see if both can work.
Observe as I pan the map, “diagrams nearby” changes and updates. What is going on in the backend is that the platform is running a machine learning algorithm to figure out where you are on a map and it shows relevant diagrams nearby having analyzed in realtime all the 200+ diagrams. This is kind of like Netflix recommendations or Amazon related products except you are shown other design ideas. Now that we know that there are others who have suggestions for this place, I can go and discuss their ideas and hopefully accomodate them in my plan.
I just demonstrated how we use unsupervised learning to analyze existing diagrams drawn in a place and then show them so that the person drawing a new one knows what idaes others had. This enables smooth negotiation and more importantly better understanding of what ideas others have for a place. There are many things that I can discuss reagrding the technical aspects of this, let me know if you would like me to show that as well. All of this state of the art technology is available for free in Geodesign Hub.
In the next article in the series I will show how we use supervised machine learning to help infer the intent of a diagram.
In this article, I will describe a API for the geodesign workflow, the goals and the recent progresses we have made at Geodesign Hub to achieve this.
If all you have is a hammer, everything looks like a nail.
In most creative and professional fields, this quote is relevent. I have come across many professionals whose thinking is shaped by the tools being used. In some cases, the tool and its capabilities guides the solution. But how would design and planning look like if it were agnostic to the tools being used? What sort of level of abstractions would such a design process require?
Geodesign is a process of design. I have written earlier about the differences between geodesign and “traditional” design. I built Geodesign Hub and it represents this new class of software that works quite differently from existing planning support tools. Prof. Uri Avin of the National Center for Smarth Growth describes this quite nicely in the following diagram, the right most diagram is how Geodesign Hub works.
Therefore, Geodesign Hub is essentially a workflow that enables interoperability between different models and tools seamlessly while enabling the core task of collaborative design.
This software model assumes different systems working independently of each other without a requirement or necessity to have a particular specialized software installed. Given the interdisciplinary nature of geodesign, this inclusive structure works better and enables tools and people from industries and domains that you would not traditionally associate with design and planning to participate as a equal citizen in the process of design. It works well with free or paid, old or new, simple or complex, properitary or open source software.
I have had a number of discussions with Dr. Stephen Ervin about the goal of a geodesign API. Dr. Ervin is one of pioneers in the field of geodesign and has been actively involved in the development of theoritical foundations of the discipline. The outcome of our discussions can be summarized by the following:
“The goal of a Geodesign API is to develop a extensible specification and format for describing GEODESIGN MODEL(s) – algorithmic processes that take one or maps as input and produce output in some specified format (one or map(s), number(s), data structure(s), etc.), to be incorporated within geodesign processes.“
This is quite amibitious but it also encapsulates the challenge in planning and design: the ability to describe the world from vastly different lenses in a way that other people can understand and make decisions. By using the lanugage of datastructures, maps and numbers we are ensuring broad inclusivity and agnostic to the tools where this data is created. When I set about building Geodesign Hub API, this was the goal.
The API documentation can be accessed at: https://www.geodesignhub.com/api/
The API fairly simple and straightforward structure and it enables you to take out all data and also submit data in the form of maps and numbers. They There are four main APIs:
And thats it!
There are many things that can be built using a API like this:
A full list of growing plugins is here: https://www.geodesignhub.com/plugins/
All of existing models and tools should have no problems in interacting with the design process. All are welcome as equals to the design process.
In addition, in the next few months, I am focusing on building a new Financial Analysis plugin for geodesign and also pushing the envelope to link deep learning and other modern Artificial Intelligence technologies to the problem of design.
We host regular webinars and tutorials about this API, please feel free to drop me a email to pre-book a place in the next one in the next month.
In this article, I will describe a simple and fast demand based Landuse Allocation model.
Recently, I have been working quite a bit with OSMBuildings, the awesome library that lets you visualize OpenStreetMap buildings in 3D in a browser. My interest is in planning and design and it got me thinking as to how OSMB can be used to visualize planning and design ideas.
I built Geodesign Hub to enable rapid early stage planning and design. Most design problems are “wicked” in that there is no obvious answer and the tradeoffs are not apparent. In essence, given that design is a creative activity, one could have almost infinite design solutions to a problem. One of the characteristics of a “wicked” problem is that they are rarely solved by a individual, they are best addressed when solved collaboratively in a multi-discipline team. A interesting Quora answer about this here.
Geodesign Hub helps team of people to build plans and designs, rapidly iterate on them and in the process eliminate design ideas that don’t work and focus on the ones that do. What this does is it enables teams to go from a solution space that has literally trillions of designs to one that has about six or seven. Then they negotiate over these six or seven designs to come to one or two final ones that have broad consensus and acceptability. All of this is done very rapidly using technology we have built.
Since we deal with early stage designing, visualization is not that important, what is more important is that different ideas are tested in isolation and also how they work together. However, as the teams get closer and closer to a negotiated design visualizing a design in 3D becomes important. Geodesign Hub is a open system where all data is entered from outside and can be taken out of the system for further work using the API. I have been fascinated with the progress Jan has made with the OSMB library and decided to hack on a link.
Geodesign Hub enables you to take out as GeoJSON (and Shapefiles) all data into the system including the designs. So I took out a design from our sample project as GeoJSON, essentially it is a FeatureCollection with some polygons and linestrings that depict a plan for a place. On a side note, there is a Python client for the API. So I went about writing code that downloads GeoJSON that then can be pasted on the tool to generate streets and buildings. And the output looks like the following:
Admitted this is a very basic scene but here is what is going on, the script takes a GeoJSON polygon, checks if it should be extruded by checking the “height” property. It can be either ‘ag’, ‘ug’ or 0, where ag means above ground (therefore needs to be extruded), ug means underground and 0 means on ground.
Once the script encounters a ‘ag’ property in the JSON, it extensively uses turf.js library to create a point grid for the extent of the polygon, then get the points within the polygon, then create buildings of random height, clustered together. The ‘reqtag’ property has the building type information from Geodesign Hub, where ‘SMB’ means small and medium buildings, ‘LAB’ means large buildings etc.
Once these buildings are created, if the user checks the road generation property, we create orthogonal streets so that every second building has access to a road. Admittedly, this is primitive but it works for small urban scale. I was talking to Filip Biljecki and he pointed me to two terrific papers for road generation here and here and for larger regional polygons these methods are more relevant. I have the basic code in place for this building heatmaps and clustering buildings on the heatmap. My plan is to test this a bit more.
Once the streets are generated, I remove the buildings on the streets and create send the GeoJSON back to the browser to be rendered in OSM Buildings.
The colors are specified by Geodesign Hub and they represent a system, in this case the red may be a commercial / industrial area, the orange housing and green agriculture. These color codes are inherited from Geodesign Hub.
Obviously, this is a very basic scene but it can be useful to show early stage design ideas in planning. I am going to add more buildings types, make it more realistic in sync with capabilities of OSMB in addition to making it faster.
I would love any feedback, or thoughts or opportunity to collaborate on this.
At a recent DLA conference, I gave a presentation and after the presentation there was a panel of all the presenters afterwards and there was a question from the audience where everyone on the panel was asked: “What is geodesign good for?”
Most design projects are complex with multiple issues and agendas in place. Additionally, there are a number of other factors: social, economic and physical phenomenon in place on the study area that are intricate, subtle and complex at the same time. With this context, geodesign brings the following in the context of large urban or regional planning projects:
Collaboration: Geodesign is inherently a collaborative activity where the end product: the design (or designs) are the result of actions and inputs of the various stakeholders. Geodesign provides a template to systematically organize the project in systems, stakeholders, actions and the design itself. Thus, Geodesign has the potential to bring together wildly different people who have a shared interest in the place. Geodesign provides a blueprint for professionals, scientists and non-scientists and people of the place together to do the design activity collaboratively. This collaboration accommodates conflicting view points, contrary agendas and different methodologies seamlessly.
Negotiation: A key benefit of the geodesign process, is its power in a negotiation. By going through a process of collaborative design, there is a shared understanding and a shared language that is built around the design problem. This facilitates negotiation and compromise. The use of simple diagrams in the process further simplifies this negotiation since the diagrams act as the currency in the compromise process. There have been many studies around design compromise and I intend to highlight a couple later in other posts.
Understand the problem at hand: Given that most design problems at regional scale are extremely complex, sometimes one has to produce a design to understand the questions at hand. Indeed, this is the most contrary and unintuitive thing about the geodesign process. The process highlights keys questions that are not obvious (or may be obvious) supported by data and analysis. The process geodesign helps in clarifying assumptions, brings the stake holders on the same page buy building a shared understanding of the problem at hand.
Do you have others? Would love to hear more about it from you.