Transcript source
Using Artificial Intelligence To Reduce Plastic WasteTranscript
[Image appears of a world globe with disposable cups pouring over it, and text appears: How big is the plastic pollution problem globally?]
Dr Denise Hardesty: How big is the plastic pollution problem globally?
[Image changes to show multiple plastic bottles surrounding text: Plastic production will double by 2040]
We anticipate the plastic production will double by 2040.
[Images move through to show plastic rubbish floating in water, plastic in a rubbish dump, and a close view of floating plastic bags]
We’re losing thousands of metric tons of plastic pollution to the ocean each and every year.
[Images move through to show a pristine ocean view, and pop up symbols of cigarette butts and takeaway containers appear in the foreground]
We find everything from cigarette butts, takeaway containers, plastic cutlery, lids, bottle caps.
[Image changes to show a photo of Sydney Harbour, and rubbish bins appear falling down the screen, and bins, a rubbish bag and a juice carton pop up in the foreground, and text appears: 3500 cubic metres of plastic is lost to the harbour each year]
In Sydney Harbour alone it’s estimated that 3500 cubic metres of plastic pollution are lost to the harbour each and every year.
[Image shows the whole of the harbour bridge being filled up with bags of rubbish, and bags and bins of rubbish continuing to appear in the harbour, and text appears: 44,000 wheelie bins of rubbish lost each year]
To put that into context 3500 meters of plastic going into Sydney Harbour is equivalent to around 44,000 wheelie bins full of trash each and every year dumped into our waterways.
[Images move through to show a shag surrounded by floating rubbish, a fairy penguin, a turtle, and then a white wading bird surrounded by rubbish]
We find plastic being eaten by seabirds, marine mammals, turtles and almost every species that has been looked at.
[Image changes to show a split screen showing a dead bird on the right with plastic rubbish next to it, and then a live bird surrounded by rubbish, and text appears on the left: More than 700 species of marine wildlife have interacted with plastic, Typically, by mistakenly eating it or getting tangled in it]
To date we have found more than 700 species of marine wildlife have interacted with plastic typically by mistakenly eating it or getting tangled up in it.
[Image changes to show Denise Hardesty talking to the camera, and text appears: Dr Denise Hardesty, Senior Principal Research Scientist, CSIRO, So, what can we do about this massive problem?]
So, what can we do about this massive problem?
[Images move through to show a close view of various sensor technologies being held in the hand, and then the image changes to show Denise talking to the camera]
Well at CSIRO we’re working using Smart sensor technology, cameras and myriad other tools to help solve plastic pollution, preferably before it gets out into the environment.
[Images move through to show a sensor being cable tied to a cement bollard, and then the photo of rubbish on the harbour bridge being removed at the touch of the screen, and text appears: Smart, Safe, Cost effective]
Using technology is a smart, safe cost-effective way for us to fundamentally change the dial on plastic pollution in Australia and beyond.
[Image changes to show a scan of floating rubbish, and text appears: Quantifying and identifying floating plastic in our waterways]
One thing that we’re doing is quantifying and identifying floating plastic in our rivers, along our waterways.
[Images move through to show a sensor being cable tied to a walkway over the water, workers assembling the sensor, and a stormwater drain, and text appears: Smart sensor technology that communicates over wireless network, When and where our assets are full, And need to be emptied]
The other main technology that we’re using is Smart sensor technology that communicates over the wireless network so that we can understand when and where our stormwater assets are full…
Digital voice: I am full.
Dr Denise Hardesty: … and need to be emptied.
[Image changes to show Denise talking to the camera, and then the image changes to show a large bucket of rubbish being removed from a stormwater opening by a truck]
Well after working on the problem more than 15 years I realise the importance of stormwater drains and our stormwater assets in helping us to resolve this issue.
[Image changes to show a computer animation in the foreground showing a bottle on the screen, and text appears: Computer vision, Machine learning]
Our team at CSIRO is using computer vision and machine learning algorithms by which we are training a computer to recognise floating objects.
[Image changes to show an animation of a person working on a computer watching a scanning tool on the screen showing rubbish moving through stormwater, and text appears inside a rubbish bag: Pretty cool, right?]
We use people to train the computer model and that allows us then to process thousands to millions of images much more quickly and much more cost effectively than we could having a human look at each of millions of images.
[Images move through to show a camera below Sydney Harbour Bridge, cameras below various other bridges, Denise talking to the camera, and a scanned bottle image, and text appears: Better estimate and understand the types and amounts of floating plastic in our waterways]
We can put cameras out at bridges, on rivers and waterways around the country, around the world and then use the images that we get back to better estimate and understand the types and amounts of floating plastic that are coming through our waterways.
[Images move through to show a camera being installed on a waterway, and scanner images of the water moving through with the rubbish highlighted as it moves through the scanner]
We’re able to use inexpensive wildlife cameras that we set at a timelapse interval to take these images of trash floating down our waterways.
[Images move through to show a computer screen showing various types of rubbish labelled, and then a plastic knife and fork on the screen, and text appears: 14,000 different objects in 35 different categories, What problematic items are lost into the environment most often?]
Our team right now is focusing on a catalogue of images that include over 14,000 different objects that are categorised into around 35 categories, bottle caps, lids, cardboard, cutlery, containers, polystyrene, all these different categories so that we can identify what are those particularly problematic items that are lost into the environment most regularly.
[Images move through to show Denise talking, rubbish on a stormwater drain, people picking up trash, a bag of rubbish at a beach, water running into a stormwater drain, and Denise talking]
If we as a global community change our relationship with plastic, if we think about what we use and how we use it, if we identify those particularly problematic items that are lost into the environment most often and we know which of those result in the most harm, we can target interventions, we can target solutions much more effectively, much more efficiently.
[Music plays and image changes to show a pristine waterway, and the image shows the Subscribe button being selected, and text appears: Thanks for watching, YouTube.com/CSIRO]