SkyTruth identified the bulk carrier Lumoso Aman as the likely polluter via AIS and satellite imagery.
On October 10, 2019, SkyTruth discovered yet another likely bilge dumping incident in Southeast Asian waters. At 10:25:26 UTC (Coordinated Universal Time), Sentinel-1 Imagery captured this oily pollution during routine monitoring of the Makassar Strait. Lingering off the southwest coast of Sulawesi, Indonesia, this oil slick measures approximately 33 kilometers long. The slick and the suspected responsible vessel (circled in red in Figure 1 below) appear roughly 100 kilometers west of the coast of Makassar, the capital of Sulawesi. Makassar is a port city with active commerce and tourism.
Figure 1: A vessel suspected of bilge dumping.
We identified the potential culprit through AIS (Automatic Identification System) broadcasts from the Lumoso Aman (Figure 2), a bulk cargo carrier operating under the flag of Indonesia.
Figure 2: A picture of the Lumoso Aman, courtesy of Vessel Finder.
Bilge dumping is the disposal of waste water from a ship’s lower hull. Bilge water is supposed to be treated before it’s discharged, but sometimes vessel operators will bypass the pollution control equipment and flush oily, untreated bilge into the ocean – in direct violation of international marine pollution law. You can learn more about this ongoing source of ocean pollution, and how SkyTruth identifies perpetrators, in our recent post about bilge dumping in Southeast Asia.
Our motto at SkyTruth is “If you can see it, you can change it.” We tirelessly monitor the ocean with this vision in mind, to be watchdogs and defenders of our Earth’s waters. No matter how remote these areas of pollution appear to be, we can see them with satellite images. These seemingly remote bodies of water are connected to waters throughout the world. Just as air pollution migrates between contiguous countries or states, oil pollution can find its way to any coastline and harm coastal environments and communities. With continued monitoring, we hope that nations, communities, and enforcement agencies can hold ship operators accountable, making it clear that bilge pollution is an unacceptable threat to the world’s ocean ecosystems.
Figure 3: SkyTruth intern Tatianna Evanisko tracks polluting vessels around the world from the SkyTruth offices in Shepherdstown WV. Photo credit: Johnna Armstrong.
https://skytruth.org/wp-content/uploads/2019/10/LUMOSO.AMAN_crop.jpg423640Tatianna Evanisko/wp-content/uploads/2016/08/test_logo.pngTatianna Evanisko2019-10-30 16:32:062019-11-19 12:42:53Bilge Dumping Caught in Indonesia - Again!
Updated data means anyone can see where, and how much, natural gas is being flared in their area.
SkyTruth has updated its Annual Flare Volume map to include 2017 and 2018 data. We first launched the map in 2017 to provide site specific estimates of the annual volume of gas flared during oil and gas production worldwide.
What is flaring?
Flaring is the act of burning off excess natural gas from oil wells when it can’t economically be stored and sent elsewhere. Flaring is also used to burn gases that would otherwise present a safety problem. But flaring from oil wells is a significant source of greenhouse gases. The World Bank estimated that 145 billion cubic meters of natural gas were flared in 2018; the equivalent of the entire gas consumption of Central and South America combined. Gas flaring also can negatively affect wildlife, public health, and even agriculture.
What can I do?
SkyTruth’s map allows users to search the data by virtually any geographic area they’re interested in, then easily compare and download flare volume totals from 2012 through 2018 to observe trends. In addition, it separates flaring into upstream (flaring of natural gas that emerges when crude oil is brought to the Earth’s surface), downstream oil (refineries) and downstream gas (natural gas processing facilities). Residents, researchers, journalists and others concerned about gas emissions in their city or study area can easily determine the sources of the problem using the latest data available, and how much gas has been flared.
VIIRS Satellite Instrument and the Earth Observation Group
The data we use in the SkyTruth map is a product of the Visible Infrared Imaging Radiometer Suite (VIIRS) satellite instrument, which produces the most comprehensive listing of gas flares worldwide. VIIRS data has moved to a new home this year at the Earth Observation Group in the Colorado School of Mines’ Payne Institute for Public Policy. SkyTruth also uses the VIIRS nightfire data in its popular flaring visualization map.
Thanks to the Earth Observation Group for continuing to make the nightfire data freely available to the public! They have authored the following papers for those interested in the VIIRS instrument and how the flare volume is calculated.
https://skytruth.org/wp-content/uploads/2019/10/flarephoto-1030x533_crop.jpg423640Dan Cogswell/wp-content/uploads/2016/08/test_logo.pngDan Cogswell2019-10-22 09:26:342019-10-22 13:00:00New Oil and Gas Flaring Data Available
Mapping stationary structures in the ocean helps us track fishing vessels and monitor pollution more effectively.
We’re all accustomed to seeing maps of the terrestrial spaces we occupy. We expect to see cities, roads and more well labeled, whether in an atlas on our coffee table or Google Maps on our smartphone. SkyTruthers even expect to access information about where coal mines are located or where forests are experiencing regrowth. We can now see incredibly detailed satellite imagery of our planet. Try looking for your house in Google Earth. Can you see your car in the driveway?
In comparison, our oceans are much more mysterious places. Over seventy percent of our planet is ocean, yet vast areas are described with only a handful of labels: the Pacific Ocean, Coral Sea, Strait of Hormuz, or Chukchi Sea for example. And while we do have imagery of our oceans, its resolution decreases drastically the farther out from shore you look. It can be easy to forget that humans have a permanent and substantial footprint across the waters of our planet. At SkyTruth, we’re working to change that.
Former SkyTruth senior intern Brian Wong and I are working to create a dataset of offshore infrastructure to help SkyTruth and others more effectively monitor our oceans. If we know where oil platforms, aquaculture facilities, wind farms and more are located, we can keep an eye on them more easily. As technological improvements fuel the growth of the ocean economy, allowing industry to extract resources far out at sea, this dataset will become increasingly valuable. It can help researchers examine the effects of humanity’s expanding presence in marine spaces, and allow activists, the media, and other watchdogs to hold industry accountable for activities taking place beyond the horizon.
What We’re Doing
Brian is now an employee at the Marine Geospatial Ecology Lab (MGEL) at Duke University. But nearly two years ago, at a Global Fishing Watch research workshop in Oakland, he and I discussed the feasibility of creating an algorithm that could identify vessel locations using Synthetic Aperture Radar (SAR) imagery. It was something I’d been working on on-and-off for a few weeks, and the approach seemed fairly simple.
Image 1. SkyTruth and Global Fishing Watch team members meet for a brainstorming session at the Global Fishing Watch Research Workshop, September 2017. Photo credit: David Kroodsma, Global Fishing Watch.
Readers who have been following SkyTruth’s work are probably used to seeing SAR images from the European Space Agency’s Sentinel-1 satellites in our posts. They are our go-to tools for monitoring marine pollution events, thanks to SAR’s ability to pierce clouds and provide high contrast between slicks and sea water. SAR imagery provides data about the relative roughness of surfaces. With radar imagery, the satellite sends pulses to the earth’s surface. Flat surfaces, like calm water (or oil slicks), reflect less of this data back to the satellite sensor than vessels or structures do, and appear dark. Vessels and infrastructure appear bright in SAR imagery because they experience a double-bounce effect. This means that — because such structures are three-dimensional — they typically reflect back to the satellite more than once as the radar pulse bounces off multiple surfaces. If you’re interested in reading more about how to interpret SAR imagery this tutorial is an excellent starting point.
Image 2. The long, dark line bisecting this image is a likely bilge dump from a vessel captured by Sentinel-1 on July 2, 2019. The bright point at its end is the suspected source. Read more here.
Image 3. The bright area located in the center of this Sentinel-1 image is Neft Daşları, a massive collection of offshore oil platforms and related infrastructure in the Caspian Sea.
Given the high contrast between water and the bright areas that correspond to land, vessels, and structures (see the vessel at the end of the slick in Image 2 and Neft Daşları in Image 3), we thought that if we could mask out the land, picking out the bright spots should be relatively straightforward. But in order to determine which points were vessels, we first needed to identify the location of all the world’s stationary offshore infrastructure, since it is virtually impossible to differentiate structures from vessels when looking at a single SAR image. Our simple task was turning out to be not so simple.
While the United States has publicly available data detailing the locations of offshore oil platforms (see Image 4), this is not the case for other countries around the world. Even when data is available, it is often hosted across multiple webpages, hidden behind paywalls, or provided in formats which are not broadly accessible or useable. To our knowledge, no one has ever published a comprehensive, global dataset of offshore infrastructure that is publicly available (or affordable).
Image 4. Two versions of a single Sentinel-1 image collected over the Gulf of Mexico, in which both oil platforms and vessels are visible. On the left, an unlabelled version which illustrates how similar infrastructure and vessels appear. On the right, oil platforms have been identified using the BOEM Platform dataset.
As we began to explore the potential of SAR imagery for automated vessel and infrastructure detection, we quickly realized that methods existed to create the data we desired. The Constant False Alarm Rate algorithm has been used to detect vessels in SAR imagery since at least 1988, but thanks to Google Earth Engine we are able to scale up the analysis and run it across every Sentinel-1 scene collected to date (something which simply would not have been possible even 10 years ago). To apply the algorithm to our dataset, we, among other things, had to mask out the land, and then set the threshold level of brightness that indicated the presence of a structure or vessel. Both structures and vessels will have high levels of reflectance. So we then had to separate the stationary structures from vessels. We did this by compiling a composite of all images for the year 2017. Infrastructure remains stationary throughout the year, while vessels move. This allowed us to clearly identify the infrastructure.
Image 5. An early version of our workflow for processing radar imagery to identify vessel locations. While the project shifted to focus on infrastructure detection first, many of the processing steps remained.
Where We Are Now
Our next step in creating the infrastructure dataset was testing the approach in areas where infrastructure locations were known. We tested the algorithm’s ability to detect oil platforms in the Gulf of Mexico, where the US Bureau of Ocean Energy Management (BOEM) maintains a dataset. We also tested the algorithm’s ability to identify wind turbines. We used a wind farm boundary dataset provided by the United Kingdom Hydrographic Office to validate our dataset, as well as information about offshore wind farms in Chinese waters verified in media reports, with their latitude and longitude available on Wikipedia.
Image 6. Wind farms in the Irish Sea, west of Liverpool.
Our results in these test areas have been very promising, with an overall accuracy of 96.1%. The methodology and data have been published by the journal Remote Sensing of Environment. Moving beyond these areas, we are continuing to work with our colleagues at MGEL to develop a full global dataset. What started as a project to identify vessels for GFW has turned into an entirely different, yet complementary, project identifying offshore infrastructure around the world.
Image 7. This animated map shows the output of our offshore infrastructure detection algorithm results (red) compared to the publicly available BOEM Platform dataset (yellow).
In addition to helping our partners at Global Fishing Watch identify fishing vessels, mapping the world’s offshore infrastructure will help SkyTruth more effectively target our daily oil pollution monitoring work on areas throughout the ocean that are at high risk for pollution events from oil and gas drilling and shipping (such as bilge dumping). This is also the first step towards one of SkyTruth’s major multi-year goals: automating the detection of marine oil pollution, so we can create and publish a global map of offshore pollution events, updated on a routine basis.
Be sure to keep an eye out for more updates, as we will be publishing the full datasets once we complete the publication cycles.
https://skytruth.org/wp-content/uploads/2019/10/Oil_Rocks-1030x728_crop.jpg452640Christian Thomas/wp-content/uploads/2016/08/test_logo.pngChristian Thomas2019-10-10 10:00:382019-10-10 11:22:10What About the Oceans? Mapping Offshore Infrastructure
Teri Biebel was drained and exhausted. Not just from a long shift at the casino where she worked, but from 24 years in the casino industry. She was ready for a change. So one afternoon Teri called her friend Holly at Shepherd University to see if there were any job openings at the school. There weren’t. But Shepherdstown, West Virginia is a tight-knit community, and Holly had spoken with SkyTruth Board Member Paul Woods at a recent Rotary Club meeting. Paul had mentioned that SkyTruth was looking for an office administrator.
“We both didn’t know what SkyTruth did,” Teri says now. “Holly said something like ‘they use radar to do stuff. Let me contact Paul.’” Paul told SkyTruth President John Amos that someone was interested in the job. When John called Teri to see if she wanted to meet. Teri said, “absolutely. I hate what I’m doing.”
Teri grew up in Wildwood, New Jersey, on the beach and not far from Atlantic City. She and her husband Don both worked at the casinos, and Don also served in the Navy Reserve (after a six-year career in active duty). Soon after he returned from his deployment to Kuwait in 2005-2006, Teri and Don took a much-needed vacation together in Hawaii. It was there that they got the call: The casino was downsizing. Don had lost his job.
Both of them soon found work at the casino in Charles Town, West Virginia and settled in nearby Shepherdstown. With two young daughters, they worked alternate shifts. But Teri became tired of taking people’s money. She remembers one customer who won a million dollars, but then gambled it all away and ended up losing everything: his home, his job, and his million dollars.
When John met Teri he was impressed with her professional experience, but also her recent personal accomplishments: Teri had just run her first marathon and lost 60 pounds in the process. “She had a lot of responsibility in her previous jobs at the casinos,” says John. “And we needed someone who could handle that level of responsibility. I was still the only SkyTruth employee at that point, so I needed someone I could depend on.“ The fact that she had trained for and run a marathon “said a lot about her,” according to John, and what she could accomplish.
Teri started in December 2010 and has watched SkyTruth grow from two employees to 10 or more now. She recalls that on her first or second day she attended a SkyTruth board meeting to take notes. That was when she first saw John in action. “When John talks he commands attention,” she says now. “You want to hear more. I never knew this stuff existed, that you could use satellite imagery to track oil spills or anything.” She likes her job at SkyTruth because she learns so much. In addition to her office administration duties, Teri has tracked oil pollution in the ocean using imagery, including the years-long spill at the Taylor Energy site in the Gulf of Mexico. (Thanks to SkyTruth’s dogged tracking of this spill, the Coast Guard finally ordered the company to fix the leak last year.) “This is my ninth year at SkyTruth and I’m still fascinated with all the things that we can see and do and change,” she says.
Perhaps even more importantly, “I feel like we’re helping people. We’re providing this data to help people see what’s going on around them… It’s a huge contrast” from her old job she says. “I feel like I’m doing good now.”
The Biebel family selfie
The move to Shepherdstown has also been good for Teri’s daughters Jenn and Amanda. Both are now students at West Virginia University and are skilled musicians. The band program in the local high school “is second to none,” according to Teri and both her girls benefited greatly from the experience. In fact, Jenn, who plays trumpet, was nominated by her band director in high school, and accepted, into the US Army All American Marching Band. The Army flew her and 124 other American high school students to San Antonio, Texas for a week. They toured the Alamo and the San Antonio River Walk, and then marched at the Army All-American High School Bowl Game (comprised of high school seniors from around the country). “I’m not sure they would have had that [band] experience if we stayed in New Jersey,” says Teri. She wrote about one of her own profound experiences during the San Antonio trip for her blog Snarkfest (a blog she describes as “thoughts from a totally snarkastic Mom”).
And despite a few lapses to raise her girls, Teri has kept running. So far, she has run three full marathons, 21 half marathons and two Tough Mudders. Tough Mudders are 10-mile races with two or three obstacles each mile. Later this month she’ll be running the Marine Corps Marathon in Washington D.C. for the second time. With her daughters away at college, Teri has found time for long training runs again. She also has discovered that, as she puts it, “being an empty nester isn’t as bad as I thought. I miss all that [childhood] stuff….But my girls are where they need to be. It’s time for me now.”
Note: This post was updated 10/8/19 to correct Don’s time in the Navy.
https://skytruth.org/wp-content/uploads/2019/10/teri_crop.jpg423640Amy Mathews/wp-content/uploads/2016/08/test_logo.pngAmy Mathews2019-10-07 17:42:342019-10-08 13:55:17Teri Biebel Found Her Fit at SkyTruth
To analyze satellite data for environmental impacts, computers need to be trained to recognize objects.
The vast quantities of satellite image data available these days provide tremendous opportunities for identifying environmental impacts from space. But for mere humans, there’s simply too much — there are only so many hours in the day. So at SkyTruth, we’re teaching computers to analyze many of these images for us, a process called machine learning. The potential for advancing conservation with machine learning is tremendous. Once taught, computers potentially can detect features such as roads infiltrating protected areas, logging decimating wildlife habitat, mining operations growing beyond permit boundaries, and other landscape changes that reveal threats to biodiversity and human health. Interestingly, the techniques we use to train computers rely on the same techniques used by people to identify objects.
When people look at a photograph, they find it quite easy to identify shapes, features, and objects based on a combination of previous experience and context clues in the image itself. When a computer program is asked to describe a picture, it relies on the same two strategies. In the image above, both humans and computers attempting to extract meaning and identify object boundaries would use similar visual cues:
Colors (the bedrock is red)
Shapes (the balloon is oval)
Lines (the concrete has seams)
Textures (the balloon is smooth)
Sizes (the feet are smaller than the balloon)
Locations (the ground is at the bottom)
Adjacency (the feet are attached to legs)
Gradients (the bedrock has shadows)
While none of the observations in parentheses capture universal truths, they are useful heuristics: if you have enough of them, you can have some confidence that you’ve interpreted a given image correctly.
Pixel Mask
If our objective is to make a computer program that can find the balloon in the picture above as well as a human can, then we first need to create a way to compare the performances of computers and humans. One solution is to task both a person and a computer to identify, or “segment,” all the pixels that are part of the balloon. If results from the computer agree with those from the person, then it is fair to say that the computer has found the balloon. The results are captured in an image called a “mask,” in which every pixel is either black (not balloon) or white (balloon), like the following image.
However, unlike humans, most computers don’t wander around and collect experiences on their own. Computers require datasets of explicitly annotated examples, called “training data,” to learn to identify and distinguish specific objects within data. The black and white mask above is one such example. After seeing enough examples of an object, a computer will have embedded some knowledge about what differentiates balloons from their surroundings.
Well Pad Discovery
At SkyTruth, we are starting our machine learning process with oil and gas well pads. Well pads are the base of operations for most active oil and gas drilling sites in the United States, and we are identifying them as a way to quantify the impact of these extractive industries on the natural environment and neighboring communities. Well pads vary greatly in how they appear. Just take a look at how different these three are from each other.
Given this diversity, we need to provide the computer many examples, so that the machine learning model we are creating can distinguish between important features that characterize well pads (e.g. having an access road) and unimportant ones that are allowed to vary (e.g. the shape of the well pad, or the color of its surroundings). Our team generates masks (the black and white pixel labels) for these images by hand, and inputs them as “training data” into the computer. We provide both the image and its mask separately to the machine learning model, but for the rest of this post we will superimpose the mask in blue.
Finally, our machine learning model looks at each image (about 120 of them), learns a little bit from the mask provided with it, and then moves onto the next image. After looking at each picture once, it has already reached 92% accuracy. But we can then tell it to go back and look at each one again (about 30 times), and add a little more detail to its learning, until it reaches almost 98% accuracy.
After the model is trained, we can feed it raw satellite images and ask it to create a mask that identifies all the pixels belonging to any well pads in the picture. Here are some actual outputs from our trained machine learning model:
The top three images show well pads that were correctly identified, and fairly well masked — note the blue mask overlaying the well pads. The bottom three images do not contain well pads, and you can see that our model ignores forests, fields, and houses very well in the first two images, but is a little confused by parking lots — it has masked the parking lot in the third image in blue (incorrectly), as if it were a well pad. This is reasonable, as parking lots share many features with well pads — they are usually rectangular, gray, contain vehicles, and have an access road. This is not the end of the machine learning process; rather it is a first pass through that informs us of a need to capture more images of parking lots and further train the model that those are negative examples.
When working on image segmentation, there are a number of challenges that we need to mitigate.
Biased Training Data
Predictions that the computer makes are based solely on training data, so it is possible for idiosyncrasies in the training data set to be encoded (unintentionally) as meaningful. For instance, imagine a model that detects a person’s happiness from a picture of their face. If it is only shown open-mouth smiles in the training data, then it is possible that when presented with real world images, it classifies closed-mouth smiles as unhappy.
This challenge often affects a model in unanticipated ways because those biases can be inherent in the data scientist. We try to mitigate this by making sure that our training dataset comes from the same set of images as those that we need to be automatically classified. Two examples of how biased data might creep into our work are: training a machine learning model on well pads in Pennsylvania and then asking it to identify pads from California (bias in the data source), or training a model on well pads centered in the picture, and then asking it to identify them when halfway out of the image (bias in the data preprocessing).
Garbage In, Garbage Out
The predictions that the computer makes can only be as good as the samples that we provide in the training data. For instance, if the person responsible for training accidentally includes the string of a balloon in half of the images created for the training dataset and excludes it in the other half, then the model will be confused about whether or not to mask the string in its predictions. We try to mitigate this by adhering to strict explicit guidelines about what constitutes the boundary of a well pad.
Measuring Success
In most other machine learning systems, it is useful to measure success as a product of two factors. First, was the guess right or wrong? And second, how confident was the guess? However, in image segmentation, that is not a great metric, because the model can be overwhelmed by an imbalance between the number of pixels in each class. For instance, imagine the task is to find a single ant on a large white wall. Out of 1000 white pixels, only 1 is gray. If your model makes a mask that searches long and hard and guesses that one pixel correctly, then it gets 100% accuracy. However, a much simpler model would say there is no ant, that every pixel is white wall, and get rewarded with 99.9% accuracy. This second model is practically unusable, but is very easy for a training algorithm to achieve.
We mitigate this issue by using a metric known as the F-beta score, which for our purposes avoids objects that are very small being ignored in favor of ones that are very large. If you’re hungry for a more technical explanation of this metric, check out the Wikipedia page.
Next Steps
In the coming weeks we will be creating an online environment in which our machine learning model can be installed and fed images with minimal human guidance. Our objective is to create two pipelines: the first allows training data to flow into the model, so it can learn. The second allows new images from satellites to flow into the model, so it can perform image segmentation and tell us the acreage dedicated to these well pads.
We’ll keep you posted as our machine learning technology progresses.
Update 2019-12-13:
In a major step forward, we set up Google SQL and Google Storage environments to house a larger database of training data, containing over 2000 uniquely generated polygons that cover multiple states in the Colorado River Basin. The GeoJSON is publicly available for download at https://skytruth-org.carto.com/maps. These data were used as fodder for a deep learning neural network, which was trained in this iPython notebook. We reached DICE accuracies up to 86.3%. The trained models were then used to run inference on sites that were permitted for drilling to identify the extent of the well pads in this second iPython notebook.
https://skytruth.org/wp-content/uploads/2019/09/edrece-stansberry-qGi-RZm6kCk-unsplash.jpg26724000Jona Raphael/wp-content/uploads/2016/08/test_logo.pngJona Raphael2019-09-30 05:00:102019-12-13 11:57:52Training Computers to See What We See
SkyTruth and/or its third party tools use cookies to monitor traffic in the aggregate on our websites and applications and to improve user experience. If you continue browsing, we'll assume you agree to the use of cookies. You can change your cookie settings at any time in your browser settings. Find out more in our privacy policy.
Bilge Dumping Caught in Indonesia – Again!
/in Bilge Dumping, Oceans, Offshore, See it, Change it /by Tatianna EvaniskoSkyTruth identified the bulk carrier Lumoso Aman as the likely polluter via AIS and satellite imagery.
On October 10, 2019, SkyTruth discovered yet another likely bilge dumping incident in Southeast Asian waters. At 10:25:26 UTC (Coordinated Universal Time), Sentinel-1 Imagery captured this oily pollution during routine monitoring of the Makassar Strait. Lingering off the southwest coast of Sulawesi, Indonesia, this oil slick measures approximately 33 kilometers long. The slick and the suspected responsible vessel (circled in red in Figure 1 below) appear roughly 100 kilometers west of the coast of Makassar, the capital of Sulawesi. Makassar is a port city with active commerce and tourism.
Figure 1: A vessel suspected of bilge dumping.
We identified the potential culprit through AIS (Automatic Identification System) broadcasts from the Lumoso Aman (Figure 2), a bulk cargo carrier operating under the flag of Indonesia.
Figure 2: A picture of the Lumoso Aman, courtesy of Vessel Finder.
Bilge dumping is the disposal of waste water from a ship’s lower hull. Bilge water is supposed to be treated before it’s discharged, but sometimes vessel operators will bypass the pollution control equipment and flush oily, untreated bilge into the ocean – in direct violation of international marine pollution law. You can learn more about this ongoing source of ocean pollution, and how SkyTruth identifies perpetrators, in our recent post about bilge dumping in Southeast Asia.
Our motto at SkyTruth is “If you can see it, you can change it.” We tirelessly monitor the ocean with this vision in mind, to be watchdogs and defenders of our Earth’s waters. No matter how remote these areas of pollution appear to be, we can see them with satellite images. These seemingly remote bodies of water are connected to waters throughout the world. Just as air pollution migrates between contiguous countries or states, oil pollution can find its way to any coastline and harm coastal environments and communities. With continued monitoring, we hope that nations, communities, and enforcement agencies can hold ship operators accountable, making it clear that bilge pollution is an unacceptable threat to the world’s ocean ecosystems.
Figure 3: SkyTruth intern Tatianna Evanisko tracks polluting vessels around the world from the SkyTruth offices in Shepherdstown WV. Photo credit: Johnna Armstrong.
New Oil and Gas Flaring Data Available
/in Natural Gas, Oil & Gas, See it, Change it /by Dan CogswellUpdated data means anyone can see where, and how much, natural gas is being flared in their area.
SkyTruth has updated its Annual Flare Volume map to include 2017 and 2018 data. We first launched the map in 2017 to provide site specific estimates of the annual volume of gas flared during oil and gas production worldwide.
What is flaring?
Flaring is the act of burning off excess natural gas from oil wells when it can’t economically be stored and sent elsewhere. Flaring is also used to burn gases that would otherwise present a safety problem. But flaring from oil wells is a significant source of greenhouse gases. The World Bank estimated that 145 billion cubic meters of natural gas were flared in 2018; the equivalent of the entire gas consumption of Central and South America combined. Gas flaring also can negatively affect wildlife, public health, and even agriculture.
What can I do?
SkyTruth’s map allows users to search the data by virtually any geographic area they’re interested in, then easily compare and download flare volume totals from 2012 through 2018 to observe trends. In addition, it separates flaring into upstream (flaring of natural gas that emerges when crude oil is brought to the Earth’s surface), downstream oil (refineries) and downstream gas (natural gas processing facilities). Residents, researchers, journalists and others concerned about gas emissions in their city or study area can easily determine the sources of the problem using the latest data available, and how much gas has been flared.
VIIRS Satellite Instrument and the Earth Observation Group
The data we use in the SkyTruth map is a product of the Visible Infrared Imaging Radiometer Suite (VIIRS) satellite instrument, which produces the most comprehensive listing of gas flares worldwide. VIIRS data has moved to a new home this year at the Earth Observation Group in the Colorado School of Mines’ Payne Institute for Public Policy. SkyTruth also uses the VIIRS nightfire data in its popular flaring visualization map.
Thanks to the Earth Observation Group for continuing to make the nightfire data freely available to the public! They have authored the following papers for those interested in the VIIRS instrument and how the flare volume is calculated.
Elvidge, C. D., Zhizhin, M., Hsu, F -C., & Baugh, K. (2013).VIIRS nightfire: Satellite pyrometry at night. Remote Sensing 5(9), 4423-4449.
Elvidge, C. D., Zhizhin, M., Baugh, K. E, Hsu, F -C., & Ghosh, T. (2015). Methods for global survey of natural gas flaring from Visible Infrared Imaging Radiometer Suite Data. Energies, 9(1), 1-15.
Elvidge, C. D., Bazilian, M. D., Zhizhin, M., Ghosh, T., Baugh, K., & Hsu, F. C. (2018). The potential role of natural gas flaring in meeting greenhouse gas mitigation targets. Energy Strategy Reviews, 20, 156-162.
What About the Oceans? Mapping Offshore Infrastructure
/in Gulf of Mexico, Oceans, Offshore, Oil & Gas, See it, Change it /by Christian ThomasMapping stationary structures in the ocean helps us track fishing vessels and monitor pollution more effectively.
We’re all accustomed to seeing maps of the terrestrial spaces we occupy. We expect to see cities, roads and more well labeled, whether in an atlas on our coffee table or Google Maps on our smartphone. SkyTruthers even expect to access information about where coal mines are located or where forests are experiencing regrowth. We can now see incredibly detailed satellite imagery of our planet. Try looking for your house in Google Earth. Can you see your car in the driveway?
In comparison, our oceans are much more mysterious places. Over seventy percent of our planet is ocean, yet vast areas are described with only a handful of labels: the Pacific Ocean, Coral Sea, Strait of Hormuz, or Chukchi Sea for example. And while we do have imagery of our oceans, its resolution decreases drastically the farther out from shore you look. It can be easy to forget that humans have a permanent and substantial footprint across the waters of our planet. At SkyTruth, we’re working to change that.
Former SkyTruth senior intern Brian Wong and I are working to create a dataset of offshore infrastructure to help SkyTruth and others more effectively monitor our oceans. If we know where oil platforms, aquaculture facilities, wind farms and more are located, we can keep an eye on them more easily. As technological improvements fuel the growth of the ocean economy, allowing industry to extract resources far out at sea, this dataset will become increasingly valuable. It can help researchers examine the effects of humanity’s expanding presence in marine spaces, and allow activists, the media, and other watchdogs to hold industry accountable for activities taking place beyond the horizon.
What We’re Doing
Brian is now an employee at the Marine Geospatial Ecology Lab (MGEL) at Duke University. But nearly two years ago, at a Global Fishing Watch research workshop in Oakland, he and I discussed the feasibility of creating an algorithm that could identify vessel locations using Synthetic Aperture Radar (SAR) imagery. It was something I’d been working on on-and-off for a few weeks, and the approach seemed fairly simple.
Image 1. SkyTruth and Global Fishing Watch team members meet for a brainstorming session at the Global Fishing Watch Research Workshop, September 2017. Photo credit: David Kroodsma, Global Fishing Watch.
Readers who have been following SkyTruth’s work are probably used to seeing SAR images from the European Space Agency’s Sentinel-1 satellites in our posts. They are our go-to tools for monitoring marine pollution events, thanks to SAR’s ability to pierce clouds and provide high contrast between slicks and sea water. SAR imagery provides data about the relative roughness of surfaces. With radar imagery, the satellite sends pulses to the earth’s surface. Flat surfaces, like calm water (or oil slicks), reflect less of this data back to the satellite sensor than vessels or structures do, and appear dark. Vessels and infrastructure appear bright in SAR imagery because they experience a double-bounce effect. This means that — because such structures are three-dimensional — they typically reflect back to the satellite more than once as the radar pulse bounces off multiple surfaces. If you’re interested in reading more about how to interpret SAR imagery this tutorial is an excellent starting point.
Image 2. The long, dark line bisecting this image is a likely bilge dump from a vessel captured by Sentinel-1 on July 2, 2019. The bright point at its end is the suspected source. Read more here.
Image 3. The bright area located in the center of this Sentinel-1 image is Neft Daşları, a massive collection of offshore oil platforms and related infrastructure in the Caspian Sea.
Given the high contrast between water and the bright areas that correspond to land, vessels, and structures (see the vessel at the end of the slick in Image 2 and Neft Daşları in Image 3), we thought that if we could mask out the land, picking out the bright spots should be relatively straightforward. But in order to determine which points were vessels, we first needed to identify the location of all the world’s stationary offshore infrastructure, since it is virtually impossible to differentiate structures from vessels when looking at a single SAR image. Our simple task was turning out to be not so simple.
While the United States has publicly available data detailing the locations of offshore oil platforms (see Image 4), this is not the case for other countries around the world. Even when data is available, it is often hosted across multiple webpages, hidden behind paywalls, or provided in formats which are not broadly accessible or useable. To our knowledge, no one has ever published a comprehensive, global dataset of offshore infrastructure that is publicly available (or affordable).
Image 4. Two versions of a single Sentinel-1 image collected over the Gulf of Mexico, in which both oil platforms and vessels are visible. On the left, an unlabelled version which illustrates how similar infrastructure and vessels appear. On the right, oil platforms have been identified using the BOEM Platform dataset.
As we began to explore the potential of SAR imagery for automated vessel and infrastructure detection, we quickly realized that methods existed to create the data we desired. The Constant False Alarm Rate algorithm has been used to detect vessels in SAR imagery since at least 1988, but thanks to Google Earth Engine we are able to scale up the analysis and run it across every Sentinel-1 scene collected to date (something which simply would not have been possible even 10 years ago). To apply the algorithm to our dataset, we, among other things, had to mask out the land, and then set the threshold level of brightness that indicated the presence of a structure or vessel. Both structures and vessels will have high levels of reflectance. So we then had to separate the stationary structures from vessels. We did this by compiling a composite of all images for the year 2017. Infrastructure remains stationary throughout the year, while vessels move. This allowed us to clearly identify the infrastructure.
Image 5. An early version of our workflow for processing radar imagery to identify vessel locations. While the project shifted to focus on infrastructure detection first, many of the processing steps remained.
Where We Are Now
Our next step in creating the infrastructure dataset was testing the approach in areas where infrastructure locations were known. We tested the algorithm’s ability to detect oil platforms in the Gulf of Mexico, where the US Bureau of Ocean Energy Management (BOEM) maintains a dataset. We also tested the algorithm’s ability to identify wind turbines. We used a wind farm boundary dataset provided by the United Kingdom Hydrographic Office to validate our dataset, as well as information about offshore wind farms in Chinese waters verified in media reports, with their latitude and longitude available on Wikipedia.
Image 6. Wind farms in the Irish Sea, west of Liverpool.
Our results in these test areas have been very promising, with an overall accuracy of 96.1%. The methodology and data have been published by the journal Remote Sensing of Environment. Moving beyond these areas, we are continuing to work with our colleagues at MGEL to develop a full global dataset. What started as a project to identify vessels for GFW has turned into an entirely different, yet complementary, project identifying offshore infrastructure around the world.
Image 7. This animated map shows the output of our offshore infrastructure detection algorithm results (red) compared to the publicly available BOEM Platform dataset (yellow).
In addition to helping our partners at Global Fishing Watch identify fishing vessels, mapping the world’s offshore infrastructure will help SkyTruth more effectively target our daily oil pollution monitoring work on areas throughout the ocean that are at high risk for pollution events from oil and gas drilling and shipping (such as bilge dumping). This is also the first step towards one of SkyTruth’s major multi-year goals: automating the detection of marine oil pollution, so we can create and publish a global map of offshore pollution events, updated on a routine basis.
Be sure to keep an eye out for more updates, as we will be publishing the full datasets once we complete the publication cycles.
Teri Biebel Found Her Fit at SkyTruth
/in SkyTruth Spotlight /by Amy MathewsDoing Good Through SkyTruth
Teri Biebel was drained and exhausted. Not just from a long shift at the casino where she worked, but from 24 years in the casino industry. She was ready for a change. So one afternoon Teri called her friend Holly at Shepherd University to see if there were any job openings at the school. There weren’t. But Shepherdstown, West Virginia is a tight-knit community, and Holly had spoken with SkyTruth Board Member Paul Woods at a recent Rotary Club meeting. Paul had mentioned that SkyTruth was looking for an office administrator.
“We both didn’t know what SkyTruth did,” Teri says now. “Holly said something like ‘they use radar to do stuff. Let me contact Paul.’” Paul told SkyTruth President John Amos that someone was interested in the job. When John called Teri to see if she wanted to meet. Teri said, “absolutely. I hate what I’m doing.”
Teri grew up in Wildwood, New Jersey, on the beach and not far from Atlantic City. She and her husband Don both worked at the casinos, and Don also served in the Navy Reserve (after a six-year career in active duty). Soon after he returned from his deployment to Kuwait in 2005-2006, Teri and Don took a much-needed vacation together in Hawaii. It was there that they got the call: The casino was downsizing. Don had lost his job.
Both of them soon found work at the casino in Charles Town, West Virginia and settled in nearby Shepherdstown. With two young daughters, they worked alternate shifts. But Teri became tired of taking people’s money. She remembers one customer who won a million dollars, but then gambled it all away and ended up losing everything: his home, his job, and his million dollars.
When John met Teri he was impressed with her professional experience, but also her recent personal accomplishments: Teri had just run her first marathon and lost 60 pounds in the process. “She had a lot of responsibility in her previous jobs at the casinos,” says John. “And we needed someone who could handle that level of responsibility. I was still the only SkyTruth employee at that point, so I needed someone I could depend on.“ The fact that she had trained for and run a marathon “said a lot about her,” according to John, and what she could accomplish.
Teri started in December 2010 and has watched SkyTruth grow from two employees to 10 or more now. She recalls that on her first or second day she attended a SkyTruth board meeting to take notes. That was when she first saw John in action. “When John talks he commands attention,” she says now. “You want to hear more. I never knew this stuff existed, that you could use satellite imagery to track oil spills or anything.” She likes her job at SkyTruth because she learns so much. In addition to her office administration duties, Teri has tracked oil pollution in the ocean using imagery, including the years-long spill at the Taylor Energy site in the Gulf of Mexico. (Thanks to SkyTruth’s dogged tracking of this spill, the Coast Guard finally ordered the company to fix the leak last year.) “This is my ninth year at SkyTruth and I’m still fascinated with all the things that we can see and do and change,” she says.
Perhaps even more importantly, “I feel like we’re helping people. We’re providing this data to help people see what’s going on around them… It’s a huge contrast” from her old job she says. “I feel like I’m doing good now.”
The Biebel family selfie
The move to Shepherdstown has also been good for Teri’s daughters Jenn and Amanda. Both are now students at West Virginia University and are skilled musicians. The band program in the local high school “is second to none,” according to Teri and both her girls benefited greatly from the experience. In fact, Jenn, who plays trumpet, was nominated by her band director in high school, and accepted, into the US Army All American Marching Band. The Army flew her and 124 other American high school students to San Antonio, Texas for a week. They toured the Alamo and the San Antonio River Walk, and then marched at the Army All-American High School Bowl Game (comprised of high school seniors from around the country). “I’m not sure they would have had that [band] experience if we stayed in New Jersey,” says Teri. She wrote about one of her own profound experiences during the San Antonio trip for her blog Snarkfest (a blog she describes as “thoughts from a totally snarkastic Mom”).
And despite a few lapses to raise her girls, Teri has kept running. So far, she has run three full marathons, 21 half marathons and two Tough Mudders. Tough Mudders are 10-mile races with two or three obstacles each mile. Later this month she’ll be running the Marine Corps Marathon in Washington D.C. for the second time. With her daughters away at college, Teri has found time for long training runs again. She also has discovered that, as she puts it, “being an empty nester isn’t as bad as I thought. I miss all that [childhood] stuff….But my girls are where they need to be. It’s time for me now.”
Note: This post was updated 10/8/19 to correct Don’s time in the Navy.
Training Computers to See What We See
/in Tech Tools /by Jona RaphaelTo analyze satellite data for environmental impacts, computers need to be trained to recognize objects.
The vast quantities of satellite image data available these days provide tremendous opportunities for identifying environmental impacts from space. But for mere humans, there’s simply too much — there are only so many hours in the day. So at SkyTruth, we’re teaching computers to analyze many of these images for us, a process called machine learning. The potential for advancing conservation with machine learning is tremendous. Once taught, computers potentially can detect features such as roads infiltrating protected areas, logging decimating wildlife habitat, mining operations growing beyond permit boundaries, and other landscape changes that reveal threats to biodiversity and human health. Interestingly, the techniques we use to train computers rely on the same techniques used by people to identify objects.
Common Strategies for Detecting Objects
Photo by Edrece Stansberry on Unsplash
When people look at a photograph, they find it quite easy to identify shapes, features, and objects based on a combination of previous experience and context clues in the image itself. When a computer program is asked to describe a picture, it relies on the same two strategies. In the image above, both humans and computers attempting to extract meaning and identify object boundaries would use similar visual cues:
While none of the observations in parentheses capture universal truths, they are useful heuristics: if you have enough of them, you can have some confidence that you’ve interpreted a given image correctly.
Pixel Mask
If our objective is to make a computer program that can find the balloon in the picture above as well as a human can, then we first need to create a way to compare the performances of computers and humans. One solution is to task both a person and a computer to identify, or “segment,” all the pixels that are part of the balloon. If results from the computer agree with those from the person, then it is fair to say that the computer has found the balloon. The results are captured in an image called a “mask,” in which every pixel is either black (not balloon) or white (balloon), like the following image.
However, unlike humans, most computers don’t wander around and collect experiences on their own. Computers require datasets of explicitly annotated examples, called “training data,” to learn to identify and distinguish specific objects within data. The black and white mask above is one such example. After seeing enough examples of an object, a computer will have embedded some knowledge about what differentiates balloons from their surroundings.
Well Pad Discovery
At SkyTruth, we are starting our machine learning process with oil and gas well pads. Well pads are the base of operations for most active oil and gas drilling sites in the United States, and we are identifying them as a way to quantify the impact of these extractive industries on the natural environment and neighboring communities. Well pads vary greatly in how they appear. Just take a look at how different these three are from each other.
Given this diversity, we need to provide the computer many examples, so that the machine learning model we are creating can distinguish between important features that characterize well pads (e.g. having an access road) and unimportant ones that are allowed to vary (e.g. the shape of the well pad, or the color of its surroundings). Our team generates masks (the black and white pixel labels) for these images by hand, and inputs them as “training data” into the computer. We provide both the image and its mask separately to the machine learning model, but for the rest of this post we will superimpose the mask in blue.
Finally, our machine learning model looks at each image (about 120 of them), learns a little bit from the mask provided with it, and then moves onto the next image. After looking at each picture once, it has already reached 92% accuracy. But we can then tell it to go back and look at each one again (about 30 times), and add a little more detail to its learning, until it reaches almost 98% accuracy.
After the model is trained, we can feed it raw satellite images and ask it to create a mask that identifies all the pixels belonging to any well pads in the picture. Here are some actual outputs from our trained machine learning model:
The top three images show well pads that were correctly identified, and fairly well masked — note the blue mask overlaying the well pads. The bottom three images do not contain well pads, and you can see that our model ignores forests, fields, and houses very well in the first two images, but is a little confused by parking lots — it has masked the parking lot in the third image in blue (incorrectly), as if it were a well pad. This is reasonable, as parking lots share many features with well pads — they are usually rectangular, gray, contain vehicles, and have an access road. This is not the end of the machine learning process; rather it is a first pass through that informs us of a need to capture more images of parking lots and further train the model that those are negative examples.
When working on image segmentation, there are a number of challenges that we need to mitigate.
Biased Training Data
Predictions that the computer makes are based solely on training data, so it is possible for idiosyncrasies in the training data set to be encoded (unintentionally) as meaningful. For instance, imagine a model that detects a person’s happiness from a picture of their face. If it is only shown open-mouth smiles in the training data, then it is possible that when presented with real world images, it classifies closed-mouth smiles as unhappy.
This challenge often affects a model in unanticipated ways because those biases can be inherent in the data scientist. We try to mitigate this by making sure that our training dataset comes from the same set of images as those that we need to be automatically classified. Two examples of how biased data might creep into our work are: training a machine learning model on well pads in Pennsylvania and then asking it to identify pads from California (bias in the data source), or training a model on well pads centered in the picture, and then asking it to identify them when halfway out of the image (bias in the data preprocessing).
Garbage In, Garbage Out
The predictions that the computer makes can only be as good as the samples that we provide in the training data. For instance, if the person responsible for training accidentally includes the string of a balloon in half of the images created for the training dataset and excludes it in the other half, then the model will be confused about whether or not to mask the string in its predictions. We try to mitigate this by adhering to strict explicit guidelines about what constitutes the boundary of a well pad.
Measuring Success
In most other machine learning systems, it is useful to measure success as a product of two factors. First, was the guess right or wrong? And second, how confident was the guess? However, in image segmentation, that is not a great metric, because the model can be overwhelmed by an imbalance between the number of pixels in each class. For instance, imagine the task is to find a single ant on a large white wall. Out of 1000 white pixels, only 1 is gray. If your model makes a mask that searches long and hard and guesses that one pixel correctly, then it gets 100% accuracy. However, a much simpler model would say there is no ant, that every pixel is white wall, and get rewarded with 99.9% accuracy. This second model is practically unusable, but is very easy for a training algorithm to achieve.
We mitigate this issue by using a metric known as the F-beta score, which for our purposes avoids objects that are very small being ignored in favor of ones that are very large. If you’re hungry for a more technical explanation of this metric, check out the Wikipedia page.
Next Steps
In the coming weeks we will be creating an online environment in which our machine learning model can be installed and fed images with minimal human guidance. Our objective is to create two pipelines: the first allows training data to flow into the model, so it can learn. The second allows new images from satellites to flow into the model, so it can perform image segmentation and tell us the acreage dedicated to these well pads.
We’ll keep you posted as our machine learning technology progresses.
Update 2019-12-13:
In a major step forward, we set up Google SQL and Google Storage environments to house a larger database of training data, containing over 2000 uniquely generated polygons that cover multiple states in the Colorado River Basin. The GeoJSON is publicly available for download at https://skytruth-org.carto.com/maps. These data were used as fodder for a deep learning neural network, which was trained in this iPython notebook. We reached DICE accuracies up to 86.3%. The trained models were then used to run inference on sites that were permitted for drilling to identify the extent of the well pads in this second iPython notebook.