2017 Frackfinder update

We’re excited to announce the 2017 update to our Pennsylvania FrackFinder data set.  Using the USDA’s most recent high-resolution aerial imagery for Pennsylvania, we’ve again updated our maps of the state’s drilling sites and wastewater impoundments.  Our revised maps show Pennsylvania’s drilling sites and wastewater impoundments as of October 2017.  

Our previous Pennsylvania FrackFinder projects identified the location of active well pads in imagery from 2005, 2008, 2010, 2013, and 2015. Our new dataset maps the drilling sites and wastewater impoundments that appeared on the landscape between October 2015 (the end of our last update) and October 2017 — the end of Pennsylvania’s 2017 National Agriculture Imagery Program (NAIP) flight season.  We are happy to add the 2017 update to this already rich data set.

 

Pennsylvania drilling sites, 2005–2017

 

The goal of our FrackFinder projects has always been to fill the gaps in publicly available information related to where fracking operations in the Marcellus and Utica Shale were taking place.  Regrettably, there are often discrepancies between what’s on paper and what’s on the landscape. Permits for individual oil and gas wells are relatively accessible, but the permits are just approvals to drill: they don’t say if a site is active, when drilling and fracking began or ended, or if development of the drill site ever happened at all.

 

Pennsylvania wastewater impoundments, 2005–2017

 

We compared permit locations against 2017 NAIP imagery to determine whether drilling permits issued since the close of our 2015 Pennsylvania FrackFinder project were active. There were more than 3,100 drilling permits issued in Pennsylvania during our study period (October 11, 2015 to October 4, 2017).  Many of the drilling permits issued were located quite close together. Ultimately, we ended up with roughly 701 unique “clusters” of drilling permits to investigate and map.

We look forward to seeing how the public will use these revised data sets.  We hope researchers, NGOs and community advocates can use these unique data sets to gain a better understanding of the impact of fracking on Pennsylvania’s environment and public health.

Visualizing the Expansion of Fracking in Pennsylvania: Part 1

This will be the first entry in a three-part series visually chronicling the expansion of natural gas drilling with hydraulic fracturing — fracking — across Pennsylvania. This series is meant to complement our work mapping setback distances and potential adverse public health consequences in Allegheny County, PA. For more about this work, please check out our blog post and the web app.

Hydraulic fracturing (otherwise known as “fracking”) is a controversial and disruptive process that has taken the Pennsylvania landscape by storm. The state has become prime real estate for the extraction of natural gas given its location above both the Utica Shale and Marcellus Shale formations, two of the United States’ most fruitful reservoirs of natural gas. Over the past decade, prospectors and entrepreneurs have come from near and far to grow the region’s natural gas industry. As a result, parts of the state have become riddled with fracking pads, which aim to break the precious resource out of pockets of porous rock under the Earth’s surface for harvesting. There are human health and environmental consequences coinciding with this process, but little regulation protects the state’s counties from these adverse impacts of fracking.

Allegheny County, home to the city of Pittsburgh and over one million residents, stands as both a case study and as a potential stronghold against the encroachment of natural gas drilling. Their main defense against fracking lies in zoning regulations which require a “setback” between drilling sites and “occupied structures.” The current minimum setback distance in the state is 500 feet, but that has not stopped well pad development from slowly creeping closer to homes (and vice-versa, as new home construction moves into areas of pre-existing drilling). In this post, we will look at some of these areas in Allegheny County and try to gain insight into the county’s current state as it pertains to natural gas development.

 

This first area, located directly south of the Pittsburgh International Airport (PIT), shows some of this development.  In just four years, we see three new drilling sites pop up along a bend in I-376, as well as a drilling-related fluid retainment pond.  Notice the close proximity of the southernmost drilling site to these neighborhoods. A 500-foot setback distance may not be enough to protect these residential areas from potential health consequences linked to the fracking process:  recent research suggests that living within two miles (3.2 km) of a natural gas drilling site could subject you to adverse health effects.

 

This 3D image of the drilling site seen at the bottom left-hand of the scene in the gif above (courtesy Google Earth) shows just how close these drilling sites can get to residential areas.

 

This second set of images comes from the Forward Township, located on the Monongahela River along the border of Allegheny and Washington County.  Though not as heavily trafficked as the area surrounding PIT, the farms which lease their property to drilling companies could be putting their neighbors at risk.  Located near this well development is the William Penn School, a K-5 school, and several homes and farms. These residents might be facing potential threats without even having had a say in what is developed near them.

 

This example is located to the northwest of the towns of Tarentum and Brackenridge.  This is another demonstration of gas drilling in the county, with the pads appearing between 2010 and 2017.

 

This image, taken from the above scene, again shows just how close these drilling sites are being built to people’s homes.  This development is nearby where their children play and where people enjoy their time outside, as evidenced by the swimming pools which can be seen in the above image.  Though development in the county is sparse as of now, the groundwork is in place for a significant expansion of drilling in Allegheny County if setback distances are not strictly enforced or extended.

 

This 3D image (courtesy Google Earth) is from a farm immediately adjacent to the Pittsburgh Mills Mall in Tarentum. Notice that there are several houses that are extremely close to being within 500 feet towards the bottom left-hand of the scene; in fact, the house directly north of the drilling site is within 500 feet of the drilling site. This could be the landowner’s house, signifying that they have waived the minimum setback requirement for their home.

To see SkyTruth’s analysis of the effect that setback distances can potentially have on natural gas development in Allegheny County, please follow the link provided here.  And stay tuned for part two of this series, where we’ll look at fracking in Susquehanna and Bradford counties over the last decade.

Mapping Potential “Drillout” Scenarios in Allegheny County, Pennsylvania Webinar

SkyTruth is hosting a webinar at 1:00p EDT this Thursday, May 9th, to talk about our new app illustrating potential natural gas drilling scenarios in Allegheny County, Pennsylvania. The SkyTruth team will walk through how to use the app, and we will show how implementing a range of setback distances and well spacings can lead to very different futures for southwestern Pennsylvania.

Allegheny County Drilling App Receives Its First Update

The SkyTruth app that maps potential drillout scenarios across the landscape of Allegheny County, PA has officially received its first update! In an effort to make the experience more user-friendly, explanatory text and tips have been added. Our app has also been updated to remove from the drillout scenario areas such as major highways and the Pittsburgh International Airport, where drilling would obviously not take place.

A screenshot of the app when first initialized.

At the request of some users, we’ve also tabulated the results for the potential drillout scenarios by municipality.  See the results in this table showing the number of occupied structures within two miles of a hypothetical drilling site, based on a given setback distance (in feet) and drilling site spacing (in acres), for every township and borough.  

We were also asked to calculate the number of occupied structures located within 500 feet, and within two miles, of existing Marcellus Shale drilling and fracking sites. According to our analysis, 78 occupied structures fall within 500 feet of an active drilling site in Allegheny County and 67,673 occupied structures sit within two miles of an active drilling site.  Recent scientific research has found human health impacts for people living within 2 miles of a drilling site.

Be sure to check out these insightful new updates for yourself.  Give the app a try and let us know what you think by contacting Brendan at info@skytruth.org with any feedback you might have!

Using machine learning to map the footprint of fracking in central Appalachia

Fossil fuel production has left a lasting imprint on the landscapes and communities of central and northern Appalachia.  Mountaintop mining operations, pipeline right-of-ways, oil and gas well pads, and hydraulic fracturing wastewater retention ponds dot the landscapes of West Virginia and Pennsylvania.  And although advocacy groups have made progress pressuring regulated industries and state agencies for greater transparency, many communities in central and northern Appalachia are unaware of, or unclear about, the extent of human health risks that they face from exposure to these facilities.  

A key challenge is the discrepancy that often exists between what is on paper and what is on the landscape.  It takes time, money, and staff (three rarities for state agencies always under pressure to do more with less) to map energy infrastructure, and to keep those records updated and accessible for the public.  But with advancements in deep learning, and with the increasing amount of satellite imagery available from governments and commercial providers, it might be possible to track the expansion of energy infrastructure—as well as the public health risks that accompany it—in near real-time.

Figure 1.  Oil and gas well pad locations, 2005 – 2015.

Mapping the footprint of oil and gas drilling, especially unconventional drilling or “fracking,” is a critical piece of SkyTruth’s work.  Since 2013, we’ve conducted collaborative image analysis projects called “FrackFinder” to fill the gaps in publicly available information about the location of fracking operations in the Marcellus and Utica Shale.  In the past, we relied on several hundred volunteers to identify and map oil and gas well pads throughout Ohio, Pennsylvania, and West Virginia.  But we’ve been working on a new approach: automating the detection of oil and gas well pads with machine learning.  Rather than train several hundred volunteers to identify well pads in satellite imagery, we developed a machine learning model that could be deployed across thousands of computers simultaneously.  Machine learning is at the heart of today’s companies. It’s the technology that enables Netflix to recommend new shows that you might like, or that allows digital assistants like Google, Siri, or Alexa to understand requests like, “Hey Google, text Mom I’ll be there in 20 minutes.”

Examples are at the core of machine learning.  Rather than try to “hard code” all of the characteristics that define a modern well pad (they are generally square, generally gravel, and generally littered with industrial equipment), we teach computers what they look like by using examples.  Lots of examples. Like, thousands or even millions of them, if we can find them. It’s just like with humans: the more examples of something that you see, the easier it is to recognize that thing later. So, where did we get a few thousand images of well pads in Pennsylvania?  

We started with SkyTruth’s Pennsylvania oil and gas well pad dataset. The dataset contains well pad locations identified in National Agriculture Imagery Program (NAIP) aerial imagery from 2005, 2008, 2010, 2013, and 2015 (Figure 1).  We uploaded this dataset to Google Earth Engine, and used it to create a collection of 10,000 aerial images in two classes: “well pad” and “non-well pad.” We created the training images by buffering each well pad by 100 meters, clipping the NAIP imagery to the bounding box, and exporting each image.

The images above show three training examples from our “well pad” class. The images below show three training examples taken from our “non-well pad” class.

We divided the dataset into three subsets: a training set with 4,000 images of each class, a validation set with 500 images of each class, and a test set with 500 images of each class.  We combined this work in Google Earth Engine with Google’s powerful TensorFlow deep learning library.  We used our 8,000 training images (4,000 from each class, remember) and TensorFlow’s high-level Keras API to train our machine learning model.  So what, exactly, does that mean? Well, basically, it means that we showed the model thousands and thousands of examples of what well pads are (i.e., images from our “well pad” class) and what well pads aren’t (i.e., images from our “non-well pad” class).  We trained the model for twenty epochs, meaning that we showed the model the entire training set (8,000 images, remember) twenty times.  So, basically, the model saw 160,000 examples, and over time, it “learned” what well pads look like.

Our best model run returned an accuracy of 84%, precision and recall measures of 87% and 81%, respectively, and a false positive rate and false negative rate of 0.116 and 0.193, respectively.  We’ve been pleased with our initial model runs, but there is plenty of room for improvement. We started with the VGG16 model architecture that comes prepackaged with Keras (Simonyan and Zisserman 2014, Chollet 2018).  The VGG16 model architecture is no longer state-of-the-art, but it is easy to understand, and it was a great place to begin.  

After training, we ran the model on a few NAIP images to compare its performance against well pads collected by SkyTruth volunteers for our 2015 Pennsylvania FrackFinder project.  Figures 4 and 6 depict the model’s performance on two NAIP images near Williamsport, PA. White bounding boxes indicate landscape features that the model predicted to be well pads.  Figures 5 and 7 depict those same images with well pads (shown in red) delineated by SkyTruth volunteers.

Figure 4.  Well pads detected by our machine learning algorithm in NAIP imagery from 2015.
Figure 5.  Well pads detected by SkyTruth volunteers in NAIP imagery from 2015.
Figure 6.  Well pads detected by our machine learning algorithm in NAIP imagery from 2015.
Figure 7.  Well pads detected by SkyTruth volunteers in NAIP imagery from 2015.

One of the first things that stood out to us was that our model is overly sensitive to strong linear features.  In nearly every training example, there is a clearly-defined access road that connects to the well pad. As a result, the model regularly classified large patches of cleared land or isolated developments (e.g., warehouses) at the end of a linear feature as a well pad.  Another major weakness is that our model is also overly sensitive to active well pads.  Active well pads tend to be large, gravel squares with clearly defined edges. Although these well pads may be the biggest concern, there are many “reclaimed” and abandoned well pads that lack such clearly defined edges.  Regrettably, our model is overfit to highly-visible active wells pads, and it performs poorly on lower-visibility drilling sites that have lost their square shape or that have been revegetated by grasses.

Nevertheless, we think this is a good start.  Despite a number of false detections, our model was able to detect all of the well pads previously identified by volunteers in images 5 and 7 above.  In several instances, false detections consisted of energy infrastructure that, although not active well pads, remain of high interest to environmental and public health advocates as well as state regulators: abandoned well pads, wastewater impoundments, and recent land clearings.  NAIP imagery is only collected every two or three years, depending on funding. So, tracking the expansion of oil and gas drilling activities in near real-time will require access to a high resolution, near real-time imagery stream (like Planet, for instance).  For now, we’re experimenting with more current model architectures and with reconfiguring the model for semantic segmentation — extracting polygons that delineate the boundaries of well pads which can be analyzed in mapping software by researchers and our partners working on the ground.

Keep checking back for updates.  We’ll be posting the training data that we created, along with our initial models, as soon as we can.