Thursday, 24 November 2016

Citizen Science and Google Earth Outreach

Part of the slick mapping project we are working on for the iCRAG Marine Spoke is to develop a method for locating, classifying and quantifying slicks in Irish Coastal Waters. We use remote sensing to find the slick and measure the spatial extents - but to help with the classification element - i.e. is it a natural or anthropegenic seep, what material is it - we can really benefit from having additional contextual GIS information to combine with the spectral information in the satellite imagery. There is a wealth of GIS data that we can use, giving environmental, meteorological, geological, legal, petroleum industry, fisheries layers etc and this has all been brought into the MAROBS platform that we are developing for spatial analysis. What we do not have is free access to the automatic identification system (AIS) on vessels, so if we find a seep we cannot check that against the mapping and position of shipping at the time the slick was sighted to see if it is possible pollution, blowing tanks, etc. We can pick up ships in the Sentinel 1 SAR imagery, but it is just a snapshot and we do not know the direction of travel - so the AI would be really useful. This is particularly useful when looking at motion of slicks in the spatial tests because if a slick recurs in a single location over time, it is very possibly a seep, and not a spill.

Example plot with AIS data included for Dublin port approaches
So in the course of my search for a similar, free, GIS-friendly dataset I was interested to see on the news recently that Leonardo DiCaprio launched a citizen science platform for tracking fishing vessels and monitoring illegal fishing.

Interpolated heatmap of fishing activity for a week in Irish coastal waters
I signed up, followed the link and it seems that this and are other excellent examples of citizen science being undertaken by the Google Earth Outreach team - one looking at fishing and the other looking at deforestation. The goal is to have citizens help monitor fishing vessels that are fishing where they shouldn't be, or illegal logging in forests around the world. The users can also help contribute in the machine learning part of the project - helping to calibrate the algorithm, as each method has more than a simple yes/no when the feature is spotted.

More information here


10 comments:

  1. This is another very interesting post. It is very useful to have citizens involved in the monitoring process. I am just curious to know how would the general public know if a boat is fishing?

    ReplyDelete
    Replies
    1. Its part of the machine learning apparently - they can identify when a ship is mobile or static for too long. But considering some ships fish when stopped and other fish by dredging/trawling - i can see some problems there for the algorithm. I suppose if a ship is even in an off-limits zone that's also a red flag, like that super trawler that was heading towards Irish waters recently.

      Delete
  2. Conor would drone technology come in useful. Once a slick is identified using your system, could a drone sample the surface water? Also using a drone to video a vessel that appears to be the source of the slick?

    ReplyDelete
    Replies
    1. It could - have a look at this poster from the recent Atlantic Ireland conference at Fig 1. We use a data wedge approach

      http://www.pip.ie/download.php?fragment_id=6413&group_id=1185&page_id=376&requested_page_id=376

      - so when the weather is poor (i.e. cloudy) we use SAR to find the slick. When we find it, we use multispectral satellite to classify it (slicks have different spectral signatures depending on type, age and thickness). The next step would be to use light aircraft with our sensor pod or drone to inspect it. Given the time delay between finding the slick and processing the data, then sending the drone out, we would not be able to respond in time to catch the polluter in the act (hence the need for the AIS) but a drone certainly could sample the oil in the water and there are a number of hybrid VTOL drones that can land in water and then take off again already on the market and in development.

      Delete
  3. Brilliant Conor I enjoyed your poster it filled in a lot of the gaps in my knowledge of how developed this technology has become. It's great to see academic research providing such a valuable tool for society.

    ReplyDelete
  4. http://jrnl.ie/3117750
    Conor the above news report highlights just how much ships could be polluting the sea and how your technology could help highlight the problem.

    ReplyDelete
    Replies
    1. Good example Patrick - I suppose two issues come to mind - whether the dumping of waste sits on the surface of the water and can then be mapped in the coastal environment using slick mapping techniques (i.e. the oily waste certainly sounds like a slick) and also what sort of revisit time would you need to spot this. It certainly should be doable - unfortunately no S1a images available before 2014 so 2013 is a bit too soon for free SAR data otherwise i would check.

      Delete
  5. Very interesting initiative. There's a bit of a grey area where 'illegal fishing' is concerned however. Fishing is a highly regulated activity now, decided at eu level by quotas, and this substantially affects his fishing is done. But the big trawlers that are the winners in this are not the best environmentally or for the long term sustainability of fishing- as opposed to smaller scale local fishermen. The film 'the Atlantic' (on tv this week) and Patrick Bresnihan's work on the fisheries offer good examples of this contradiction. I know it's a bit off the point but I'm wondering which practices constitute 'illegal fishing ' in the google citizen science model? Large trawlers dumping unprofitable fish back into the sea or smaller fishermen fishing where they don't technically have quotas? I think this also raises a bigger question about the possibly technocratic approache of companies like google to citizen science, which tends to take politics out of the equation. Cian

    ReplyDelete
    Replies
    1. I like the technocratic point Cian - this is one to watch for sure. Looking forward to The Atlantic on Thursday.

      Delete
  6. Some more info here that popped up in my inbox

    http://blog.globalfishingwatch.org/2016/12/deciphering-suspicious-behavior-not-always-what-it-seems.html

    ReplyDelete

About Me

My photo
My name is Conor. I am a PostDoc and Lecturer. These few lines will (hopefully) chart my progress through academia and the world of research.