Project avatar for The Plastic Tide

The Plastic Tide

We are finished. Please read our announcement in the Talk Section! Thanks everyone!

Results

Update August(ish) 2018:

Dear amazing taggers,
Thank you once again for all your efforts, we would not exist but for all those juicy tagging efforts. In particular those who have been tagging our most recent batch of fiendishly complex litter strewn imagery from Tregantle Bay, Cornwall. It is by far one of our most challenging imagery sets so far, but still incredibly valuable for the algorithm to pick out all the plastics/litter you see.

The team has been hard at work putting all your tagging efforts to use training our algorithm and we’re delighted to say that our 2nd Generation algorithm will be launched in September! The exact day is uncertain as we’re still hard at work finishing it off, but we will write an update as soon as it is. So stay tuned!

The Plastic Tide team has seen a preview of the 2nd generations capabilities and it is super exciting! Boosted by the amazing 1.5 million extra tags we have got as part of British Science Week and of course all the tags we’ve gotten from you throughout the year. We will reveal all in due course, sorry to tease! 😛

We also have another exciting announcement to come in October or September, it is the next step in our algorithm for our 3rd Generation algorithm. Stay tuned for another update in the next few weeks. 😄

This update is a little thin on the ground with details we know, but we think you’re really going to love the juicy updates coming your way in the next few months.

All of this we hope will satiate your tagging hunger well into 2019

Huge and massive thanks to you all

The Plastic Tide Team

Update June 2018:

The team has had a very busy 6 months since our last update! Please accept our apologies for the lack of updates. We have been crunching the massive influx of tags we got for British Science Week 2018 - it did not break records, it SMASHED them! And thanks to the efforts of our die hard taggers and the new joiners we have continued to see strong numbers since!

British Science Week initial figures:

  • 1.4 Million tags - nearly as much as we had in previous 10 months!
  • Smashed 250,000 target by nearly 6 times.
  • Most tags during UK School hours.
  • Articles featured in every major news outlet.

These have been a significant help in training the algorithm. I'm delighted to say that we should finally have some progress to report and indeed some exciting new developments too report in the coming month 😃

We have always recognised the need to keep you all informed of progress and admit we can do more. So ontop of maintaining monthly updates again, we hope to release some tech challenges that will hopefully lead cool ways to visualise your data tags. More on this to come.

Finally, please meet The Plastic Tide and Zooniverse Teams!

On Tuesday 3rd of July at the Royal Society in London The Plastic Tide and Zooniverse teams will be featuring in the "Science Needs You" area at Royal Society's Summer of Science Lates exhibition.

More information can be found here: https://royalsociety.org/science-events-and-lectures/2018/07/lates-science-needs-you/

If you live in the UK and are near London, please do come and meet us. It will be an opportunity to see the progress your hard work has made in person!

Happy Tagging

The Plastic Tide Team.

Update January 2018:

New Year Goodies! Tagging Stateside - US Beaches now live.
The Plastic Tide is delighted to announce brand new beaches for your tagging pleasure all the way from New Jersey, USA! Thanks to an exciting collaboration with Digital Drift LLC, find out why Digital Drifting is no ordinary drone company nor are these any ordinary drone surveys.


Typical surf fishing day in late November on Island Beach State Park (Courtesy Morris Enyeart)

As the late, low December sun says its final goodbyes to a wonderful day, it casts long shadows over the golden sands of Island Beach State Park, New Jersey. Morris Enyeart, cuts an isolated figure as he brings his drone in for a landing after one of many successful surveys. His back arched against a chill early evening wind sweeping in over the cold sea, “FFA Licensed Commercial Drone Pilot” set in black on his bright high vis jacket.


Morris Enyeart beginning a 100 yard drone survey on Island Beach State Park in December 2017. (Courtesy of Morris Enyeart)

But this is no ordinary drone pilot, nor is this any ordinary survey. At 71 years young, Morris is not your usual candidate for drone pilot nor a tech-savvy entrepreneur! But after a long successful career in Insurance Technology, he was not quite ready to put his boots-up. Instead, on fishing trips out in the ocean he witnessed something that re-awoke his passion for the environment - “Finding plastic in the stomach of fish and watching seagulls try to eat plastic …drove me to help find a solution to this problem”, he says.


Seagull eating a bit of plastic during one of our surveys. (Courtesy of Morris Enyeart)

One of the most accessible places for cleaning oceans of plastics is our millions of miles’ coastlines. In 2016, Morris’ search for a solution led him to ask what makes the most effective use of beach cleaning efforts? He knew it would be key to know when and where plastic and marine litter accumulates on beaches. Realising the potential drones offered helped answer this question, Morris founded Digital Drift LLC and set about creating a new methodology for conducting beach litter surveys using drones to photograph the beach in a systematic way so the process could be used by non-technical coordinators for litter abatement assessments. He also knew that Machine Learning offered a potential solution to offer real-time detection of litter in a way that manual reviews of the survey data could not.


Morris Enyeart doing his pre-flight equipment check before heading to the beach. (Courtesy of Morris Enyeart)

Through Morris’s research, he contacted Peter Kohler, Founder of The Plastic Tide, in 2017 where the potential for collaboration was clear. In particular, the New Jersey Parks Service approved Digital Drifting application conduct a visual beach litter survey in the Island Beach State Park using a drone. This offered Digital Drifting and The Plastic Tide a fantastic base for collaboration; Digital Drifting could now carry out beach scans and cleans until June 2018 and beyond of the same place.


Letting people know what is going on. (Courtesy of Morris Enyeart)

The drone surveys allow us to build up a picture of the rates of accumulation and even the sizes and types that wash-up, thanks to your tags! Combined with Digital Drifting’s work with New Jersey Clean Communities and New Jersey Parks Services, will help develop new and groundbreaking methodologies for beach surveying.

Happy tagging!

The Plastic Tide Team

Update November 2017:

Going Global: Tagging Down Under
The Plastic Tide are delighted to announce the addition of Australian beaches for our citizen scientists like YOU to tag!

You can choose your country now!

OR

Jump to tagging now!

Partnering with two amazing Aussies, Martin Leahy of Australian UAV and Jackie Dujmovic and her team at Hover UAV has made this possible. Both Martin and Jackie are passionate about drones and plastic pollution in our oceans and are using their skills to capture images of beaches for our citizen science portal!


Jackie Dujmovic, Hover UAV


Martin Leahy, Australian UAV

We’re excited to say this launch was marked with a fantastic beach clean with the Tangaroa Blue Foundation, Surfrider Foundation and Jack Johnson’s All At Once community on Nov 12th at the gorgeous Port Kembla beach clean-up, just south of Sydney.


View of Port Kembla looking south from Wollongong Lighthouse, Australia.


Learning at play, kids getting involved in the beach clean.

Jackie is delighted to say the beach clean resulted in;

  • A whopping 135 Volunteers
  • Nearly 400 drone survey images
  • 85kg of waste removed,
  • Broken down by:

    Chart breaking down litter found.


The Haul.

This collaboration with Jackie and Martin means The Plastic Tide can use their expertise in drone operation and local beaches to capture valuable images from Austrailia. These images add yet more variety to the beach imagery for tagging, a key part of helping improve the algorithm accuracy. The variety will mean the algorithm has wider repertoire of background beaches to help it distinguish plastics.

Jackie and Martin also do great work in engaging with local communities and use beach cleans and online tagging with The Plastic Tide to raise awareness and change behaviours to fight rising tide of plastics!


Tagging with two screens - productive!

The first set of drone images are live here. Get Tagging!

We're excited about future drone surveys from Hover UAV and Australian UAV and from around the world. The Plastic Tide is talking with a number of different individuals and organisations around the world about collaborating on drone images - the next could be in the New Jersey Area!

Watch this space!

Update October 2017:

In just 6 short months we are now a few thousand tags away from our first citizen science milestone; 50% or 90,000 of the 160,000 drone survey images completed!

We’ve been overwhelmed with the ongoing effort of our amazing Zooniverse taggers! Reaching 1.4 million tags in such a short period of time, especially amazing considering each of the nearly 90,000 images are tagged by 15 different people!

We'll very soon be uploading new batches of drone images for your tagging pleasure, more on this later in the week!

The benefit of this data will be a great help to training efforts for our Algorithm. To put it into context our prototype algorithm, completed in July, was trained to detect 25% of plastics successfully using around 450,000 tags that were available then. We now have extra 1 million tags generated to this point, this will help boost the detection rate of up to our target 80%.

PARTNERSHIP WITH THE BRITISH SCIENCE WEEK 2018!

We have seen the interest in The Plastic Tide citizen science tagging going from strength to strength! With our latest big announcement today; The Plastic Tide will be featured as the main citizen science project for the British Science Week (BSW) on 10-19th March 2018!

We have seen the interest in The Plastic Tide citizen science tagging going from strength to strength! With our latest big announcement today; The Plastic Tide will be featured as the main citizen science project for the British Science Week (BSW) on 10-19th March 2018!

British Science Week is a 10 day of celebration of Science, Technology, Engineering Maths (STEM) through events and activities to support and engage teachers, STEM professional, science communicators and the public to get involved with STEM subjects.

See how you, your, family, your school or your community can get involved here: https://www.britishscienceweek.org/plan-your-activities/citizen-science/

Stay tuned for further news and announcements on the drone image sets and our exciting partnership with British Science Week…

Thanks again for all your awesome efforts!

The Plastic Tide Team!

Update September 2018:

Come check out The Plastic Tide events!

**Ocean Plastics Lab **- 27th Sept - 7th Oct
If you're around Turin, Italy check us out at Ocean Plastics Lab by The German Federal Ministry of Education and Research, a public awareness showcase of what Europe is doing to combat Plastics - read more! Find us in Container 4 BUILD Co Solutions, see where The Plastic Tide is contributing to the solution. Social Media gurus use #oceansplasticlab and #VisionFromTheSkies

Note: Founder, Peter Kohler, will be attending the Paris event on November 4th -17th November - Dates TBC! Come see us!

Natural History Museum - Science Uncovered - 29th Sept
In London, England and looking for an awesome FREE Friday night? Join us for the Natural History Museum for Science Uncovered night! Say 'hi' to founder, Peter Kohler, Drone Pilot, Ellie Mackay and plastics expert, Arturo Castillo Castillo! You can also speak to other leading scientists and find out what other research efforts are being conducted to counter plastic pollution! Read more here. For those social media savvy use #SU2017 and #VisionFromTheSkies

UPDATE August 2017:

Measure, Clean, Predict, Prevent: The Next Steps of The Plastic Tide.

What an amazing few months! On the 31st of March 2017 we set out to survey and clean 30 beaches around the UK to build an algorithm that will revolutionise our understanding of the growing plastic tide choking our coastlines!

First and foremost, we to give a huge THANK YOU and recognition to those that have helped us complete our first phase and continue to support us. These people include all those 4,500 + people that have helped and continue to help us surpass 1 million tags!

Not to mention all those that donated on our Crowd Science page, joined us on beaches cleans, our team of scientists and engineers - Stefan, Erik, Kayleigh, Dirk and Ben for all their efforts. Even more thanks to friends and family and to the strangers that helped behind the scene and a massive thank you to Ellie for her drone piloting and mission director expertise!

Today, 5 months on, The Plastic Tide team have traveled over 4,200 miles, picked up 1 tonne of rubbish from 30 beaches with the help of over 80 volunteers around the UK while collecting over 12,000 drone images! Further still, since the launch of our Citizen Science project at the end of April, YOU, or over 4,500 of you, have made over 1 million classifications to teach our algorithm to find plastics!

SUCCESS! VERSION 1 OF OUR ALGORITHM.

The team are super excited about the completion of the first version of our algorithm! Ben Hahn, our engineer, has worked hard with your tagging data and has succeeded at getting the algorithm to detect a very impressive 25% of litter in images. What is mind boggling is that these are images that the algorithm has not 'seen' before! In other words, it is drawing on what it has been taught by you, our Citizen Science volunteers, to identify plastics in images. Dr. Stefan Leutenegger, Ben Hahn's supervisor and Science Adviser to The Plastic Tide, sums up the results in his fantastic blog post here.

BEHAVIOURAL INSIGHTS

Dr. Kayleigh Wyles, Environmental Psychologist also Science Adviser to The Plastic Tide, is studying the impact that tagging imagery with plastics and litter on beaches and online has on our well being. Dr. Wyles conducted a scientific survey into these impacts online that we're excited to say is now finished. We managed to achieve in excess of 700 responses, far bigger than the 200 we had anticipated originally! Dr. Wyles is very excited about this, however, it will take some time to crunch the data. Regardless, she believes the data set is an excellent and very robust dataset providing a great cross section of society. Watch this space for her blog on this at the start of September!

So, in short, a summary of our Objectives as on Our Mission page thus far:

  • Algorithm - Version 1 completed and work started on Version 2!
  • Public Engagement & Citizen Science - 1 million tags from 4,500+ volunteers online and 1 tonne of litter removed thanks to over 80 volunteers helping us on the beaches! Our message reaching potentially hundreds of thousands thanks to the media interest in our work - see our In the Media page.
  • Open Data & Collaboration - This will fall into Phase II, once we have got the algorithm detection rate up and can package it we release it, the images, and the framework behind the machine learning together under an Open Data license (license type TBC).
  • Human Impacts - Dr. Wyles study has had over 700 responses, 500 or 250% increase, from a very representative slice of the UK population from many different backgrounds and geographic locations.

Next Steps:

We're all very excited about the performance of the first version of the algorithm and progress so far, but there is still much work to do! With the results of Phase I we are fine tuning the detail of Phase II and now approach collaborators and potential funders. A sneak peak at what is planned is provided below;

THE ALGORITHM; VERSION 2.

Dr. Leutenegger sums up the next steps in his blog here, but in short, the main focus of the next phase is to substantially increase the detection accuracy ideally into the order of 70-80% correct detections and maximally missing 10-20% of pieces. This is a complex task and will involve studying the labeled images, including more tags and tweaking the algorithm parameters. Even so, we may find we need to collect more data or make changes to how the data is collected and/or labeled.

But the coolest and most exciting capability is developing the ability for the algorithm to calculate the volume and mass of litter on any beach the drone images. This would lead to the revolutionary capability of the algorithm to detect, measure and monitor the volume and weight of litter as well as the number of litter pieces! For example, it could quantify the effectiveness of beach cleans and assist in planning more effective cleans by knowing the mass of litter washing up. It could also help land owners, such as Local Government, to baseline litter accumulation to commission more cost effective beach cleaning.

PLASTICS RESEARCH

Our plastics Science Advisors Dr. Erik Van Sebille and Dr. Arturo Castillo are exploring exciting research in two key areas that our algorithm opens up.

The Missing 99%: This problem highlights our lack of knowledge of what happens to litter when it enters our ocean. For Dr. Van Sebille, as our algorithm develops in Phase II, it will allow the first opportunity to measure the litter washing up on our coastlines efficiently, cost effectively and rapidly. This is the first step to coordinating more efficient beach cleans and measuring their effectiveness. It will also allow us to identify areas where the litter might impact on sensitive wildlife and even where it could be a hazard to us! But the research doesn't stop there, in the long term we hope to predict where litter will build up and understand how it accumulates on the seabed too!
Plastics: The work in distinguishing between types of plastic will allow Dr. Castillo to eventually identify both the type of litter and the type of plastic it is made of. Armed with this knowledge, repeat offenders could be identified, for example, and preventative action formulated by focusing plastic design and better packaging, but also by evidence basing local anti-litter policies.

OPEN PLATFORM

By the end of Phase II, version 2 of the algorithm will be completed and packaged up for anyone to download and run on their own drone images of beaches under an Open Software license.

The results can then be uploaded upload to our online map allowing anyone to see the quantity of litter washing up on our beaches and when. An online database will also allow anyone to download this data to study and share.

We also aim to modify existing drone apps to be able to perform the type of survey required to get maximum results from our algorithm.

CITIZEN SCIENCE & PUBLIC ENGAGEMENT

We are looking forward to running further beaches with YOU to gather more data and test our algorithm. In fact, we envisaged setting up a series of trials for a fixed period of time at selected sites to test the robustness of the algorithm as it develops.

However, an idea we're particularly excited about is combining the beach cleaning and litter tagging elements by 'gamifying' it. In otherwords creating a game app, our thoughts are something similar to the wildly popular 'Pokemon Go' but for litter picking! Users would be rewarded for identifying and picking up litter with prizes and trophies. All this data could build a robust algorithm for not only beaches but also waterways, lakes and even streets and roads! It could also be used to help coordinate local beach or perhaps even road cleans. Coordinators could post news about cleaning events that might attract extract points, with the algorithm being used to do a before/after and estimating the effectiveness!

TIMELINES

We're working out the details of this as it will depend on how quickly we can get funding, but we hope that Phase II maybe completed by the end of 2018. In the longer term we are looking at this project to develop a series of 4 or more phases over 3 years. But more to come on that later!

How can you help?

Keep checking in and tagging to read the latest updates that YOUR work is enabling!

Many Thanks

The Plastic Tide Team

UPDATE July 2017:

Detection and Mapping of Plastics on Beaches using MAVs

By Dr Stefan Leutenegger, Lecturer in Robotics at Imperial College London, scientific advisor to The Plastic Tide.

During the past months, I have been working with my student Ben Hahn at Imperial College London, on developing algorithms and software for The Plastic Tide to automatically detect and map plastic and marine litter on coastlines using drone imagery. Ben deserves the bulk of the credit, as he carried out most of the work described below for his final year project.

The drone images gathered by The Plastic Tide are uploaded to Zooniverse, a citizen science website where thousands of citizen science volunteers created hundreds of thousands of tags of what is and is not plastic litter. Ben used this unprecedented dataset to train the machine learning algorithm, specifically a type called a Convolutional Neural
Network (CNN). The network uses these thousands of training examples of labeled plastic pieces – such that it will finally be able to tell what is a plastic piece and what not in an unseen image all by itself.

We have furthermore developed a second algorithm, it is implemented in a piece of software that refines the position (roughly known from GPS) and orientation from which the drone images were taken. This is achieved by exploiting the fact that characteristic features of the environment are observed across several images of the same beach. This image registration technique allows us to know where the drone was and what exact direction it was facing, allowing us to precisely map the detected pieces of plastic in geographic coordinates. This means that not only can we use the CCN to identify plastics; we can accurately locate the items on beaches.

Below, we show some examples of the detection that the CCN outputs – remember, it has not seen these images before, but relies on the “memory” of similar-looking tagged training images. In other words it has learned, from the citizen science inputs, where to find the plastics!

Above, a version of the network is used, that simply detects plastic pieces, without any discrimination of the exact type. Note that the results are not perfect: the network detects the same piece twice at different sizes in the left two images. It also detects something very small in the left image – which by closer inspection might not be a mistake, but an actual small piece of green-ish plastic that’s quite hard to spot even for a trained human!

The next set of test images shows a version, where the network was trained to distinguish seven different classes of plastics: plastic fragments; ropes, strings, fishing gear; plastic drink bottles; all other types of drink bottles; all other plastics or litter items; uncertain. It is certainly a harder task for the algorithm output correct predictions in this setting. In fact, we observed that people tagging the images disagree very often.

However, we are quite satisfied with these example results, given the difficult nature of the task. By closer inspection, we find a mistake in the bottom right image above: on the right, a transparent plastic part was missed. Also, the object class labels in the bottom middle image are incorrect, whereas the detections of plastic parts as such are correct.

We conducted an extensive quantitative analysis, reporting the results here would go beyond the scope of a blog post. While the algorithm on its default parameter setting, on average, outputs about twice as many erroneous or inaccurate detections as correct ones, it does accurately detect around 25% of the pieces of plastic, which we find very promising initial results given the very challenging nature of the task

In the foreseeable future, we suggest to further improve these results and extend our algorithms and software in numerous ways. First of all, we need to rigorously analyse the dataset from Zooniverse in an automated manner: we need to make sure the tagging is consistent, cross-check, filter and merge the bounding boxes and labels in each image as provided by the several annotators. We would also like to evaluate the accuracy of the “human plastic detector” – in order to have a baseline for our algorithms.

Furthermore, since this training and evaluation, the dataset has massively grown to nearly 1 million tags on many more images. We thus anticipate that using the largely increased number of training examples will further boost the accuracy of the CNN detections.

We are also very excited about further developing mapping infrastructure: it should finally allow us to exactly geo-locate and quantify the plastics in terms of number of pieces, and also generate approximate volume and mass predictions of plastics and litter on beaches!

The framework we’re working hard on we’ll share openly and hope that others will use it to detect plastics and litter themselves using their own imagery, and perhaps to improve it themselves too!