A. Exploratory research

I. Digimarc Barcode project

  1. Project carriers
    2. Digimarc corporation which offers enterprises software and services for banking, retail, entertainment, media and several other industries.

  2. Beneficiaries
    3. citizens, land, water, soil, natural resources (water, petroleum, natural gas, coal, crude oil, electricity), landfill space

  3. Users
    4. Major retailer companies, consumer brands, Global banks, U.S. state government departments, film companies, professional sports teams and other organizations

  4. Need
    5. easily and more accurately identify recyclable plastics so they don't end up in landfills or incinerators.

  5. Principle
    6. Digimarc invented a new technology which makes data included in digital watermarks of product packaging and retail labels detectable by enabled devices such as phones, computers and barcode scanners. With the Digimarc barcode, scanners can identify multiple types of plastic containers such as food-grade and non-food-grade containers, and Digimarc barcode also enable identification of flexible packaging with multiple layers of plastic for proper separation and sorting.

  6. Main technologies involved
    7. Digimarc barcode including top-ranking identification technology and Digimarc Discover software for barcode scanning and image recognition.

  7. Sources
    8. https://www.digimarc.com/solutions/retail/recycling
    https://hk.prnasia.com/story/247525-2.shtml
    https://www.digimarc.com/about/technology
    https://en.wikipedia.org/wiki/Digimarc
    https://blog.impactplastics.co/blog/sustainability-in-the-workplace-5-major-benefits-of-plastic-recycling

II. SavingFood project

  1. Project carriers
    2. SavingFood is a two years CAPS project funded by H2020 and icoordinated by ViLabs.

  2. Beneficiaries
    3. Foodbank, Gleaning Group, Charity, Donor (retail, shops, supermarkets, restaurants), Citizen/volunteer, Grassroot Food surplus Redistribution initiatives

  3. Users
    4. Foodbank, Gleaning Group, Charity, Donor (retail, shops, supermarkets, restaurants), Citizen/volunteer, Grassroot Food surplus Redistribution initiatives

  4. Need
    5. reduce food waste and fight hunger; make the redistribution of food surplus to charities more efficient and effective.

  5. Principle
    6. SavingFood developed a CAPs platform to build a bridge between "donors" and "charities". When a donor donnate food, the first charity who react to that message can claim the donation, and an appointment will be made between these two parties to finish food redistribution.

  6. Main technologies involved
    7. Frontend - REACT JS
    Backend - Django REST
    Backend extension - Django CMS

  7. Sources
    8. https://savingfood.eu/the-project/

III. Felix project

  1. Project carriers
    2. Felix project was founded by a United Kingdom charitable organization set up by entrepreneur, Justin Byam Shaw. The project aims to saves excess food from suppliers and redistributes it to charities and other organizations.

  2. Beneficiaries
    3. Children, young people, old people, charities, Voluntary Bodies

  3. Users
    4. Charities, schools, individuals

  4. Need
    5. Redistribute food to reduce food surplus.

  5. Principle
    6. The Felix Project redistributes food that supermarkets, wholesalers and other suppliers are unable to sell for various reasons; with the help of company's staffs and volunteers, it sorts and delivers food for free directly to local kitchens, charities, schools, community halls including older adults, homeless people, people with mental health issues, refugees, families and children.

  6. Main technologies involved
    7. Cloud-based solution as well as data analytics used for the optimization of cataloged locations, driver allocations, routes and delivery activities.

  7. Sources
    8. https://en.wikipedia.org/wiki/The_Felix_Project
    https://thefelixproject.org/
    https://www.avanade.com/en/media-center/press-releases/cloud-data-analytics-transform-the-felix-project

IV. The Ocean Cleanup

  1. Project carriers
    2. Ocean cleanup is a non-profit engineering environmental organization founded by Boyan Slat. The organization developed technology to take plastic pollution from the ocean and intercept it in rivers before reaching the ocean.

  2. Beneficiaries
    3. tourism, fisheries, marine species, human beings

  3. Users
    4. Ocean

  4. Need
    5. Get rid of the world’s oceans of plastic.

  5. Principle
    6. Ocean cleanup creates an artificial coastline comprising of a U-shape barrier to concentrate the plastic. By maintaining relative different speed to plastic, the plastic can be gathered successfully.

  6. Main technologies involved
    7. Smart steering (Active steering and computer modeling) enabling Ocean cleanup to identify plastic hotspots (higher concentration of plastic) and storm prediction modeling to predict storms, avoiding the loss of vessels.

  7. Sources
    8. https://theoceancleanup.com/oceans/
    https://en.m.wikipedia.org/wiki/The_Ocean_Cleanup

B. Deepening

I. Selected project - Ocean cleanup


  1. Carriers and actors of the project
    2. Ocean cleanup is a non-profit engineering environmental organization founded by Boyan Slat. The organization developed technology to take plastic pollution from the ocean and intercept it in rivers before reaching the ocean. Following pictures are the list of part of company's partners (for all partners, please refer to company's website):

  2. Research question
    3. How can we reduce plastic waste in ocean through advanced capture technology?

  3. The reason of selecting this project
    4. The reason of choosing this project is based on three dimensions: Environment, Economy, and Health.
    Plastic waste in the world's oceans has become one of the biggest environmental challenges of our era, affecting almost 700 marine species. Besides, according to a research developed by Deloitte, annual economic costs related with ocean plastic pollution reached nearly between $6-19 billion which comes from the effects of plastic pollution on tourism, fisheries and aquaculture. Moreover, toxic pollutants brought by plastic pollution into the food chain not only influence sea life, but also hugely threaten the health of us human beings.

II. User scenario

  1. Users
    2. Ocean

  2. Persona
    3. Since the Ocean is identified as the User, it is also defined as Persona.

  3. Key features
    4. Capture plastic waste
    Target plastic hotspots
    Monitor weather situation
    Adjust navigation speed
    Recycle plastic waste

  4. UX storyboard

III. Technical analysis

  1. General principle
    2. Ocean cleanup uses smart steering to accurately target plastic hotspot and adjust relative speed difference to capture plastic waste in ocean.

  2. Technical overview - AI version
    3. Two major technologies are identified in this project: smart steering and storm prediction modeling. Both of these technologies are used AI and both will be illustrated below in detail.
    In this project, smart steering is considered to use in situ monitoring and satellite monitoring. In situ observations are in situ plastic samples or measurements collected at multiple locations over a period of time. This measurement can calibrate plastic particle tracking models and satellite measurements. For satellite monitoring, Ocean Color can detect the radiance of water leaving. Machine learning algorithms are also used to analyze the images pixel by pixel and see how many different signals of plastic and natural debris that each pixel contained. Therefore, it can be utilized to target plastic hotspots by displaying large plastic patches on the ocean surface.



    Storm prediction modeling used by Ocean cleanup are based on weather prediction model. It mainly collect data of the current state of the atmosphere(temperature, humidity, wind...). With the help of this model, Ocean cleanup can wisely set navigation route and avoid storm. The technology mentioned above are based on supervised learning; it belongs to SGD Regressor in the type of Regression algorithms and considering of the programmed languages in smart steering and storm prediction modeling, Python programming language and Fortran are respectively used in these two technologies.

  3. Added value thanks to Artificial Intelligence
    4. the supports offered by Artificial intelligence hugely boost the operational effectiveness of this project: Without smart steering, Ocean cleanup will find targeting plastic hotspots in ocean difficult; failure of predicting storm events will also lead to unnecessary loss for cleaning vessels, making the whole cleaning process extremely unefficient.