Summer Research Kick-Off

It’s an exciting time around the office. We’ve finalized our summer research program and added a couple of new faces—interns Brian Wong from Duke University and Flynn Robinson from West Virginia University—to help us expand our skill set and cover more ground.

Brian is going to be helping us improve our mountaintop removal (MTR) mining work. We’ve already mapped the footprint of MTR in 74 counties in Kentucky, West Virginia, Tennessee and Virginia. Our analysis used 30-meter resolution images from the Landsat satellite, and it computed mining footprints on an annual basis. But thanks to an exciting partnership with Planet, we now have access to satellite imagery collected daily with a resolution less than 5-meters. This is a game-changer. This new imagery will let us calculate more accurate and timely impacts of MTR in the Appalachians, and we’re excited to have Brian leading this work!

Flynn will be helping us improve our natural gas flaring work. We’ve already mapped the distribution of natural gas flaring across the globe. But the data set that we’ve developed isn’t able to account for clouds or other natural “noise” that can throw off the sensor and create false detections. Yet. But we’re excited to have Flynn leading the effort to validate our flaring data set using the newly available imagery from Planet! We’ll be able to identify flaring events with much greater confidence and, if everything goes to plan, send out ‘Flaring Alerts’ so that people can know when a new well is coming online near them.

We’re also very fortunate to have Brady Burker stay with us through the summer. Brady will also be helping us to improve our MTR work. He’ll be adapting the approach that we developed in the Appalachians to map the impact of coal mining in Wyoming’s Powder River Basin. Brady’s work will also help deepen our understanding of mining reclamation. Using the data that he creates, we’ll be evaluating the effectiveness of reclamation – looking at whether the environment is able to return to its previous level of ecological health and productivity. As far as we know, our research will be the first to use a remote-sensing approach to measure reclamation effectiveness, and we’re excited that Brady will be leading this effort!   

Monitoring for offshore oil spills and tracking the impact of hydraulic fracturing will round out our research priorities this summer. We’re excited about the opportunities to create and share these powerful data sets, apply them to real-world conservation problems, and generate public and policy engagement that can make meaningful change. Thanks for staying around, Brady, and welcome to SkyTruth, Brian and Flynn!

-Ry Covington, PhD

Big Data Brings Big Transparency to Indonesia’s Fisheries

Indonesia is leading the way towards a new era of transparency in fisheries management by making its Vessel Monitoring System (VMS) data available to Global Fishing Watch (GFW). This is an unprecedented move.

Traditionally, VMS data is kept secret and used only by government agencies like Indonesia’s Ministry of Maritime Affairs (KKP) and affiliated enforcement agencies. The head of the KKP, Susi Pudjiastuti, referred to as “Minister Susi” by nearly everyone, is a champion of sustainable fishing in Indonesian waters, and has taken major steps to crack down on illegal, unreported and unregulated (IUU) fishing. Her policy of publicly blowing up and sinking (empty) vessels caught fishing illegally in Indonesian waters has been wildly popular. Now that Minister Susi has partnered with GFW, anyone with a browser and internet access will be able to see Indonesia’s VMS data on the GFW map, beginning in June.

People photographing an illegal fishing vessel being intentionally sunk by Minister Susi at Morela village on Ambon Island, April 1, 2017. Antara Foto/Izaac Mulyawan/via REUTERS

Data Scientist Aaron Roan is taking the lead at SkyTruth to integrate Indonesia’s VMS data into Global Fishing Watch. A former Googler, Aaron joined the SkyTruth team officially in January, but he has been involved in the GFW project for a while, on loan from Google as a volunteer. Like many SkyTruthers, Aaron works remotely, usually from San Francisco. However, this project means that lately he’s traveling regularly to Indonesia.

SkyTruthers Aaron Roan (left) and Paul Woods sightseeing in Jakarta during The Economist World Ocean Summit 2017.

Aaron is in charge of integrating VMS data into Global Fishing Watch. Naturally, there have been some interesting challenges and adventures along the way, starting with some pretty big differences between AIS data, which GFW is currently using, and VMS data.

AIS is a well-established and standardized open system developed to keep ships from running into each other, while VMS systems are custom-created specifically to allow government fishing agencies to privately monitor and communicate with vessels. Ships using AIS are essentially just chirping their locations to the world (“I’m here, I’m here!”) using public radio airwaves. VMS systems are more like text-messaging systems on phones, sending and receiving encrypted, privacy-protected information.

Vessel congestion is often an issue for AIS: the satellites that collect AIS broadcasts from vessels have a circular “footprint” 3,000 miles wide (more than the width of the United States) and the system can only receive an AIS ping once every 27 milliseconds, or 2,250 per minute. If there is a lot of vessel traffic in one location, smaller vessels using the weaker class B AIS systems get throttled in preference to larger class A vessels. This means that it’s possible for a vessel to be chirping its location frequently, but when there are a lot of ships in the area, pings may only be infrequently received.

VMS systems can handle a lot more signals than AIS, and better manage problems like colliding messages from multiple ships. However, the cost per message is relatively expensive, so government agencies often dial the systems back to receive fewer messages from ships in a given time period. According to Aaron, if Aesop were still around, he would call VMS the tortoise, and AIS the hare.

Despite these differences, initial integration test results have been positive, with the VMS data adding a tremendous amount of new data to GFW. Below, you can see the difference between Global Fishing Watch with and without the VMS data. AIS data is shown in green and the new Indonesian VMS data in white:

You can see it here in full-screen mode:

We are lucky to have Imam Prakoso, our “on-the-ground” guy in Indonesia, working on this project. With his engineering background, he provides support to the analysis and helps out with language translation. He’s been pivotal in terms of being able to meet regularly with KKP staff and in navigating the ministry’s organizational structure.

Brian Sullivan, Paul Woods, Imam Prakoso and Aaron in Jakarta

Chris Wilcox‘s team at CSIRO, currently consulting with the KKP, has been hugely helpful as well. With our data and algorithms, and his analytical acumen, we believe we’re in a strong position to help out multiple teams within the KKP.

None of this would have been possible without Minister Susi’s innovative approach to fighting IUU fishing, and the generous financial support of the David and Lucile Packard Foundation and Walton Family Foundation.

Transparency in commercial fishing benefits everyone (with the possible exception of those engaging in illegal activities). More accurate data in commercial fishing will allow for better regulation, management, and sustainability of an important food and job source in the future. We hope that other governments will follow Minister Susi’s bold initiative and make their own fishing data transparent. With Aaron on the team now, we’re ready to help!

Fracking, Mountaintop Mining, and More…My Summer at SkyTruth

 Hi, my name is Jerrilyn Goldberg.  Over the course of  two months last summer I worked as an intern at SkyTruth. In September I started my junior year at Carleton College in Northfield, Minnesota, majoring in environmental studies and physics. Over the course of my internship I contributed to SkyTruth’s Mountaintop Removal (MTR) research by creating a mask to block out rivers, roads, and urban areas that could be confused with mining activity by our analytical model. I also helped classify many of the ~1.1 million control points that allow us assess the accuracy of our MTR results.

To analyze the accuracy of the MTR results we obtained through our Earth Engine analysis, we dropped 5,000 randomly distributed points at each of 10 sample areas for each year between 1984 and 2016. These points were manually classified as being `mine` (if it overlapped a user IDed mine location) or `non-mine` (if it overlapped anything other than a mine). A subset of those manually classified points were then used to assess the accuracy of the output from our Earth Engine analysis

In addition to the MTR project, I created a story map illustrating the development of Marcellus Shale gas drilling and hydraulic fracturing (fracking) in Pennsylvania, and discussing the environmental and public health consequences fracking is having on some rural Pennsylvania communities. Check it out here. Through my research for the story map, I learned about the hydraulic fracturing process. I also learned about many of the political and social complexities surrounding the fracking industry in Pennsylvania, including conflicts between economic and community interests. Our goal with this story map is to present an accessible and accurate narrative about the fracking industry in Pennsylvania, which begins with understanding what’s actually going on now.

Click the image above to visit Jerrilyn’s interactive story map.

I started by learning about SkyTruth’s FrackFinder Pennsylvania data and methodology from the 2013 project. I read through our GitHub repository and figured out why the FrackFinder team chose their methodology and what the results represented. (While I was familiar with the general concept of the project, I did not know much about the specifics beforehand.) With this in mind, I set out to update the dataset with well pads built after 2013.

 

I quickly realized that this task presented many questions such as, which of the many state oil and gas datasets actually contained the information I sought. I selected the Spud Data, which contains all of the individual locations where operators have reported a drilling start-date for a permitted well. I filtered to include only unconventional horizontal wells drilling for natural gas and excluded those reported as ‘not drilled.’ To account for some missing drilling locations which I noticed while reviewing the latest Google base map imagery, I also download the Well Inventory Dataset which includes all permitted oil and gas wells along with their status. From here I filtered out all the spuds and wells not listed as drilled in 2014, 2015, or 2016 and joined the files. After joining the layers, I formed a well pad dataset by creating a 150 meter buffer around the wells, dissolving overlapping areas, then locating the centers of each buffer. This step effectively says ‘create a 150 m radius circle around each point, but when these overlap, clump them into one circle, then find the center of that new circle.’ Finally, I found all the buffers that overlapped with FrackFinder drilling locations from 2013 and earlier, and eliminated all of those centroids.

A quick note about the imagery: USDA collects high resolution aerial imagery as part of the National Agriculture Imagery Program (NAIP), which at the time of my project was last collected for Pennsylvania in 2015. While I worked hard to eliminate inaccurate points, I was unable to verify all of these with the existing NAIP imagery. That said, I found that the other points accurately represented the general well pad locations and thus chose to include the points for the first half of 2016, even though I obviously couldn’t verify the existence of those recent drilling locations on the mid-summer 2015 NAIP imagery.

 

At the same time I found The Nature Conservancy’s (TNC’s) 2010 Energy Impact Analysis, which looked at the predicted development of wind, shale gas, and wood fuel usage in Pennsylvania. Part of TNC’s study identified three construction scenarios for how many wells and well pads could be built in Pennsylvania by 2030. With an assumption that 60,000 new wells would be drilled between 2010 and 2030, the study predicted between 6000 and 15000 new well pads would be built to host those wells. Each scenario featured a different distance between pads and a different number of wells per pad (because that number stays constant at 60,000 new wells). I found some data from TNC’s study hidden on an old SkyTruth backup with help from Christian and David. With the FrackFinder data, my update, and the ‘informed scenarios’ in hand, I started trying to figure out an appropriate way to synthesize the three datasets, to identify which TNC drilling scenario best fits what is actually happening..

 

One roadblock in conducting a thorough analysis and comparison was that TNC’s research makes a quantitative prediction about the possible volume of infrastructure development instead of a more tangible spatial prediction. The study distributes the predicted numbers of new well pads across the counties of Pennsylvania, which overlay the region of Marcellus Shale with ideal conditions for hydraulic fracturing for natural gas. All of the included counties now contain at least one well pad. I did notice that since 2010, about 1/3 of the well pads estimated by the low impact scenario (6000 well pads) have already been constructed. If the rate of development between 2010 and 2016 remains constant, Pennsylvania will surpass TNC’s low impact scenario.

An example of The Nature Conservancy’s “low” impact scenario for fracking well construction across a section of Pennsylvania.

The Nature Conservancy’s medium impact scenario for future fracking well construction across a section of Pennsylvania.

The Nature Conservancy’s high impact scenario for future fracking well construction over a section of Pennsylvania.

 

Fracking Pennsylvania” uses maps and other media to create a narrative of hydraulic fracturing and its consequences. While originally intended for the community members we work with in southern Pennsylvania, I hope this story map becomes a useful tool for many different communities grappling with fracking.

 

While I have my time in the Watchdog spotlight, I want to publicly thank everyone here for welcoming me into the awesome world of SkyTruth. I’m so grateful for the learning opportunities I had last summer and for all of the support I received. Special thanks to Christian for introducing me to SkyTruth and to John for helping me improve my Story Map even though he is definitely one of the busiest people in the office. I look forward to sharing my experience through the Carleton Internship Ambassador program this year.  

A Productive Week in Shepherdstown

With team members in three continents and four U.S. states, we at SkyTruth make extensive use of Slack and video conferencing. This form of remote working saves many hours on commute time and has allowed us to build this great tool from our spots all over the world — but sometimes there’s just nothing like meeting in person. Two weeks ago a number of us working on Global Fishing Watch, including a few colleagues from Oceana and Google,  met in Shepherdstown, WV (SkyTruth’s World Headquarters), for a week-long workshop.

Global Fishing Watch is at an exciting point it its history. We just launched our public-facing website at the U.S. State Department’s Our Ocean’s Conference. Over the next year, we hope to roll out more features to the website, undertake a series of analyses to better understand fishing around the globe, and publish more of our datasets for outside researchers and advocates to use. Stay tuned for more updates. Below are some pictures from the week.

Nate Miller Shares his Analysis on Transshipment

Nate Miller shares his analysis on transshipment with the Global Fishing Watch team.

Machine Learning Engineers Alex Wilson of Google and Tim Hochberg of SkyTruth

Machine Learning Engineers Alex Wilson of Google and Tim Hochberg of SkyTruth collaborate on an improved neural network to identify fishing vessels. Christian Thomas is at his computer in the background.

David Kroodsma at the Chalkboard, Outlining the Next Global Fishing Watch Projects

David Kroodsma, at the chalkboard, outlines the next Global Fishing Watch projects.

 

 

 

How SkyTruth Works: David Kroodsma

SkyTruth isn’t your ordinary organization. Of course, everyone says that, so we thought we’d give you a glimpse into what makes us unique. With a little inspiration from Lifehacker’s “How We Work,” we’ve asked our staff to answer a few insider questions that reflect who we are and what makes us tick. . .

Name: David Kroodsma
Job title: Research Program Manager, Global Fishing Watch
Location (at the moment): Oakland, CA

David came to SkyTruth after cycling 30,000 miles through 28 countries to talk about climate change. He says the hardest part of his journey came after the peddling when he decided to sit down and write a book about it. Today he applies his education in environmental science and physics to keeping the wheels in motion at Global Fishing Watch.

  1. Describe yourself in one to three words.
    Energetic, optimistic
  2. What are you working on this week?
    I am working with our research partners to help move a number of research projects forward. I’m working on the crowdsourcing app that we use to verify different types of fishing boats and identify different types of fishing. I’m also learning how to use Google’s Earth Engine platform which allows us to do global-scale calculations on extremely high resolution data.
  3. Do you have a set routine for your workday?
    I get up at 6:20 am and join the 6:30 am office call. It’s a daily check-in meeting for the development team at SkyTruth to share their priorities and goals for the day. It’s at 9:30 am Eastern Time, but since I’m based on the West Coast, it means I start the day at 6:30 am. I like to join that because it helps me focus for the day and it’s great to stay connected to what is a pretty dispersed team. After the meeting I like to spend some time responding to emails and getting organized for the day. Then I drop my son off at the nanny. After that it varies day to day, but usually I end up having a lot of calls, especially to help coordinate our research team. It’s nice that by the end of my day, a lot of people on the East Coast have stopped working. If I’ve gotten most of my stuff done, I can finish early in the day because I start at 6:30. But usually, that’s a good time to work on projects that don’t require a lot of interactions with other team members. Things like coding or more open ended analytic projects.
  4. Coffee or tea?
    Coffee, anything will do, really, although there’s a Philz coffee very close by.
  5. What does your workspace look like right now?
    DavidK's work space
  6. What do you consider the most creative part of your job?
    The most creative part is figuring out how to best host a research workshop: what’s the best way to organize a day such that our research partners will get the most out of it and feel the most engaged and want to contribute to the program? There’s kind of an art to setting up a meeting. In some ways that’s the most creative.
  7. What are you most excited about doing at SkyTruth?
    I am most excited about making discoveries that matter. So really what we are doing is getting access to datasets no one has had the chance to analyze before, and we’re trying to say meaningful things with them. It’s about helping interpret this amazing resource of environmental observations and making it useful for people. That’s what really excites me about this work.
  8. What’s been the biggest challenge in your professional life?
    Finding that balance between research and advocacy. I’ve kind of done both in a sense, so it’s just trying to figure where I fit on that spectrum. Because I’ve done some activist-related things, but at heart, I really love science and research. I think that’s why I was originally drawn to this organization. For me it’s the right balance of seeking both truth and change.
  9. What apps are you using to accomplish the work?
    Slack, Chrome and iPython Notebooks.
  10. In your personal life are there any apps or devices you could not live without?
    Strava. It’s an app for tracking your exercise, and mapping your runs or rides.
    Strava screenshot
  11. Of the places in which you’ve lived, or places you’ve visited what would be most interesting viewed from a satellite, and why?
    I swam in the Aral Sea in 2014, and it would be very interesting to watch how that is changing. It used to be the world’s fourth largest lake, but in the last 30 years it has declined in size by over 90 percent due to the overuse of water in Central Asia. It’s now one tenth the size it used to be.

    Satellite imagery of the Aral Sea in 1998 and 2008

    Aral Sea in 1998 and 2008

    We had to drive across the empty lake bed for many, many miles to get to the edge of the water, and it continues to recede every year. As water has drained from the lake the salinity has risen to several times that of seawater, which makes it easy to float.

    Photo of David floating in the Aral Sea

    David challenging the theory of specific gravity in water several times saltier than the ocean.

  12. What superpower do you bring to the project, even though you don’t like to brag?
    Power napping. I can grab ten minutes or twenty minutes of sleep anywhere.
  13.  If you weren’t at SkyTruth, how would you be changing the world?
    Through making sure my five month old son gets his sleep. That would be world-changing for me.
  14.  What’s inspiring you this today or this week?
    Animated gifs.
    Animated gif of dog hanging head out of car window