This week in in Spain for South Summit
My first time to visit the phi-week conference at the European Space Agency.
Where the coffee is really great!
I am at a future of mobility event in Berlin this week.
I stopped at Malmo a couple of days ago in the evening enroute from a #geodesign workshop.
As a part of working with Geodesign and Geodesignhub, I am involved in many side projects, some commercial work and some just as a hobby. I recently got involved in a very interesting and challenging side project around machine learning, port operations with significant implications for marine environments and I thought I will share my experience.
Ports play a major role in the modern economy. Often times these ports are near cities and major land based transport network and also in close proximity to valuable marine environments, river basins and drainage ecosystems. Coastal management and “coastal geodesign” is a area that interests me personally. Coastal areas are interesting becuase of the mix of environmental, economic, natural systems that are at play here. In addition, a integrated management of land and marine assets is something we do often at Geoesignhub in the context of fisheries, flood water drainge etc. Till now however, I did not really touch port operations, it is something that is critical given the large increase in ship traffic.
Airbus recently announced a machine learning / image recognition challenge. They have launched a new generation of satellites and stratospheric drones that caputre movement of ships near ports in near realtmie. The challege was to build a machine learning model to identify ships in a image with reasonable accuracy. I was immidiately intrigued, I have worked on machine learning models in Agriculture, I will share my experiences about it at a later date.
Start from zero
I have been using Python extensively for the past number of years and I have built machine learning algorithms to do various things inside Geodesignhub. Eg. see how we use it from a earlier blog post. Image recognition has been used extensively in various fields and slowly is coming into geo-sciences. For e.g. look at onesoil.ai and others. I had heard a lot about neural networks etc. and I wanted to understand it deeper beyond the marketing hype and buzzwords.
Given my responsitibiltes with Geodesignhub and GUTMA, I am plenty busy but I challenged my self to see if I can stretch to do this as side project. Generally, I spend half a day every week working on a bunch of ideas around geodesign. Some become products (e.g. geoforage.io), some just demonstrators like this that lead to something bigger. This is also a company policy: when you work for Geodesignhub, a part of your time will be spent on developing open source tools or contributing to them.
Anyway, as a total newbie I jumped in, it is a great feeling to not know anything about a subject and try to learn it from scratch. I looked up how image recognition is done in medcial sciences and came across UNET and decided to try it out. I created a small repository and started to play with model parameters, image processing and model performance. I also looked up some of the other newer model techniques like R-CNN mask, Fast CNN etc. I settled on the Unet model because I thought it would be a great first step to see and test. The others seemed to be slightly complicated and linked to ImageNet. I dont think I understand everything about them but I got a good introdcution on how they work.
Take a look a the model on the Kaggle page and scroll to the bottom, you will see the input image and the output predictions. This is in no way going to win a prize or be in the top 100, in fact the competition winner has a accuracy of .85 and my kernel as a accuracy of .7160. There is a long way to go still, none the less I am very happy that I was able to take on a challenge, commit my self to it, not give up and have a submission in time. There is much to learn, I still dont understand exactly how these different models work. Or why some models are faster than others and how to tweak the training set. Why GPU processsing is so much faster for machine learning or how Kaggle can offer cutting edge GPUs for free to the public to test models. They are so expensive! In hindsight, I would recommend just to use Kaggle and forget about what I did: setup my own repository and server.
Why it matters
Geodesignhub provides solutions to help manage problems of design and geo-management. You can think of it as project management for geo-problems. Our software supports negotiations and execution of these negotiated outcomes. The model described above will only get better and we will continue developing it to use as a part of our offering for coastal managment solutions. How to optimize port operations? How to manage flow of ships in a critical marine environments? How do decide collectively in a marine / littoral context? Using our open API system we can link this type of work into the decision making and operations management. As I and the company develops deeper expertise in this field, we are confident that we can help ports, marine and littoral organizations in their management using the absolute cutting edge technologies.
I plan to take on challenges like these every six months to never be complacent, develop deep expertise and push the my personal boundaries.
Here for #geodesign work this week. A unforgettable landscape!
- In this article, I argue that geodesign should be thought of as a process not a tool or a branded exercise.
- We are at a point where advances in tools and technology can be leveraged to have a collaborative, integrated a design and impacts analysis.
What is Geodesign?
Geodesign has been used (or misused) as a buzzword lately in social media, conferences and other forums. In recent years, there are has been a proliferation of academic courses and conferences organized around the topic. Critics argue that geodesign is not new or that it is an invented term used mostly for marketing. They argue that designing has been a activity that is carried on for thousands of years and essentially the movement of geodesign is just a continuation of that.
Geodesign is a workflow
While the critics are partially correct, there are some aspects of geodesign that make it fundamentally different from what we have experienced before. To understand this, we need to think about the following: Is Designing an art or science? Obviously, there is no absolutely correct answer to this in the context of geodesign, it is a mixture of both. A more nuanced question is the following: Is the process of designing art or science? When an architect designs a building or a home there is an inherent internal creativity that results in the form. In the same way when a climate scientist studies sea level rise, it is underpinned by solid scientific and technical theories and models. However, one cannot design a home using climate change models nor can a single person guided by their experience and creativity design a solution for sea level rise. The methods of designing a house do not work to design a plan for climate change (and vice versa). One of the reasons why these methods are not interchangeable is that as the scale gets larger collaboration between different disciplines of design and science plays a increasingly crucial role.
The process of geodesign is most useful and effective when it is used collaboratively not to design a single house or to design a climate mitigation system but in the scales that are in the middle: collection of buildings, neighborhoods, wards, cities, city regions, multiple counties. There are three different trends with collaboration technologies that converge to make geodesign relevant and powerful.
Firstly, there has been maturing of enabling technologies. The smartphone revolution, the relative ease at which broadband is available means that there are more people connected and engaged. This also has meant that the underlying infrastructure and technologies that power all the Apps and data the internet has finally matured and is capable enough to serve billions of users. The design community has become much more amenable to integrating technology into the design process over the past number of years. And that the increasing horsepower of technology allows for much more rapid and fluid design prototyping and analysis leading to better communication and iteration of ideas. As scientific progress is made, we have developed a deeper understanding of the delicate interconnections between nature and the built environment. The design professions are tasked with a leadership role to orchestrate the complex interconnected systems that are at play in a study area.
Secondly, there is a general understanding that the major problems facing our planet necessitate a collaborative approach to problem solving. Thus people from different disciplines and domains including people of the place need to bring in their expertise and knowledge to design solutions. This is sometimes enforced and mandated by legal frameworks such as the European Landscape Convention and others.
Thirdly, we are in the midst of a geospatial computing revolution with broad availability of open data and mapping technologies. And there is a small ecosystem of startups focused on mapping technologies that have attracted venture capital and are well on their way to success. (Startups like Azavea, Mapbox and CartoDB etc.). These trends open up an opportunity to build the next generation of design tools that enable collaboration, leverage open data and standards. Fundamental advances in general purpose software: such as version control, data analysis and processing, cloud computing also accelerate this trend.
In the case of design however methods play an critical role. The technological and societal changes also mean that design methods and experience that has worked for many years can be updated and modernized using software. What does this mean? It means that designs can be produced faster, they can be compared more efficiently (and rejected quicker), they also mean all analysis and feedback is done in near real time collaboratively. This is the essence of the geodesign process.
This makes geodesign fundamentally different: the process of design is different. There is no distinction between design and analysis it combined into one seamless operation that can be understood by people of different professions, experts and non-experts alike. All of this is powered by collaborative software that accommodates different design methods and scales.
What do you think makes geodesign different?
In the coming weeks, I plan to write a series of blog posts on the fundamentals of the geodesign workflow.
Geodesign Hub is a modern planning and analysis tool to collaboratively design better urban plans with the power of data. Creating and running geodesign projects is free for individuals and there is a comprehensive support portal to help you get started. For companies, we offer paid professional support and training.