Happy Near Year from the Snapshot Wisconsin team!
2018 brought a year of tremendous growth for Snapshot Wisconsin, and we couldn’t have done it without you! Since the statewide launch in August this year, the project has reached every Wisconsin county with over 1500 volunteers. We cannot thank you enough for your help making Snapshot Wisconsin the success that it is today. Happy New Year, and we can’t wait to see what 2019 brings!
“Hoppy” Holidays from the Snapshot Wisconsin team!
One of the most incredible things about studying wildlife is that, no matter how much you think you know, something new and surprising will appear. Recently, I had the opportunity to review thousands of photos for an exciting project involving machine learning (which you can read more about in this blog post). A subset of the photos on my plate for review were of Virginia opossums (Didelphis virginiana).
Some might not draw a line between the words “exciting project” and “opossum,” but they truly are an interesting species. For starters, they are North America’s only marsupial, meaning females carry their offspring in a pouch, especially when the young are newly born (see the photo above). Additionally, those of us who live where ticks are a concern can thank opossums for consuming a fair number of these pests.
The first thing I learned about opossums from my time examining the photos is that they can vary widely in color. Above is a small collage of opossums that range in color from almost entirely white (known as leucism) to predominantly dark grey, although the animal pictured in the middle is more representative of Wisconsin’s majority.
Morphology, or the set of physical characteristics an animal displays, is not easily disguised in trail camera photos when compared to something fleeting, like behavior. Often, animals captured in the photos simply appear to be moving across the frame. This expectation is what led me originally to overlook a fascinating opossum behavior. As I flipped through the images, I noticed an infrared trigger in which the animal seemed to have debris stuck to its rear half. I imagined that it had gotten stuck in mud, but when I saw the phenomenon a second time – this time in daylight – I realized that this was no accident. In fact, these opossums were using their prehensile tails intentionally to carry bunches of leaves and twigs.
After doing some research on this behavior, I discovered that this has been documented before, albeit rarely. The consensus on the reason for this behavior is that opossums take their hauls to a temporary den site to use as bedding material. Of the over 3,000 opossum triggers that I was sorting, I only encountered nine in which this behavior was displayed. If I were to randomly choose a photo from the set, I would be more than twice as likely to encounter a raccoon misclassified as an opossum than I would be to have selected a photo of an opossum carrying leaves with its tail. Nine instances do not constitute a large enough sample size to do any major analyses. However, according to this photo set, there does not seem to be any obvious seasonality, with photos spread somewhat evenly from January 2017 through June 2018. Only one trigger was taken during the daytime – likely a product of opossums being primarily nocturnal.
If you stumble upon any interesting Snapshot photos – opossums or otherwise – please reach out to us. You can share them by using the “Talk” function on Zooniverse or by emailing them to DNRSnapshotWisconsin@wisconsin.gov.
Have you ever wondered what is responsible for the crimson shade of a fox’s coat, or the distinctive stripes that distinguish a raccoon tail? The answer, in short, is pigments! Pigments are chemical compounds that determine the color an object appears to the human eye based on how much light they absorb or reflect. Melanin is a major group of pigments naturally produced by most animals. Two types of melanin, eumelanin and pheomelanin, control the color that hair appears. This is true from the hair on your head to the coats of the critters you see in the wild!
While most species maintain the same coat coloration year-round, some swap out their coats seasonally for white, “ecologically fashionable” winter coats. This process is known as molting. You may recall some species around the world that do this, including Arctic fox (Vulpes lagopus), White-tailed ptarmigan (Lagopus leacura) and various weasel species. Changing coats is not only a terrific way to help avoid predation, but may also serve as an extra tool to keep warm during the frigid winter months. Because the white fur lacks pigment, it is believed that there is extra space in the hair shafts for air that can be warmed by the animal’s body heat (think of a bird ruffling its feathers during a cool morning to trap in warm air).
Although the exact mechanisms behind this wardrobe change are not fully understood, there is evidence that suggests that the length of daylight, also known as photoperiod, plays a key role in when animals switch their coat color. Receptors in the retina transfer messages to the brain that it’s time to get a new outfit for the next season. Once this process begins, the hair begins to change color starting with the extremities.
A local expert at swapping out coats is Wisconsin’s own Snowshoe hare (Lepus americanus). You can most commonly find these long jump champions in the northern forests of Wisconsin. Contrary to the common Cottontail rabbit, Snowshoe hare swap brown summer coats for bright white during the snowy winter months to camouflage with their surroundings.
Snapshot Wisconsin cameras capture images of Snowshoe hares year-round across the state. This provides a unique opportunity to not only pinpoint the time of year that snowshoes go through their wardrobe change, but also identify the surrounding area’s brown down or green up state. Because Snowshoe hares rely heavily on their coat color to stay camouflaged and avoid predation, any mismatch between coat and season can make a hare an easy target for lunch. Snapshot Wisconsin cameras can capture images of these mismatches to help understand interactions between Snowshoe hares and predation, as well as Snowshoe hare molting biology across time.
As many volunteers may be aware, Snapshot Wisconsin operates continuously and year-round. This is distinct from many other studies and monitoring efforts focused upon wildlife that typically evaluate population status during a particular time of year and look at changes between years. One belief that underpins Snapshot Wisconsin is that because the environment consistently changes across the year, how animals move, behave, live, die also changes. Consistent and continuous data collection provides the project much richer insights into animal habitat associations, and it also gives the project the ability to evaluate which time of year deserves most focus–when should we be monitoring things?
As discussed in previous posts, we heavily rely on spatial data produced by processing satellite imagery in order to quantify species’ habitats and estimate or predict where animals are. Recall that two important sensors or satellites are Landsat, which has fine spatial resolution but captures imagery of Wisconsin less frequently, and Modis (on the Aqua and Terra Satellites) that has coarser spatial resolution, but captures an image of Wisconsin daily. Data produced from Modis imagery is incredibly useful for capturing, say, the timing of larger scale phenomena like big snow events, or the onset of either long-term snow coverage in the winter or green up in the spring. The behaviors and activity of animal species are often connected to the timing of these environmental cues (or others, like temperature, or the length of daylight).
One animal species that is particularly sensitive to seasonality is the black bear: bears spend the winter in dens in a state of torpor. In brown bears, previous research has suggested that the timing of bear den entry is sensitive to environmental factors, while the timing of ending torpor is more related to individual physiology. One thing we are interested in is whether bear behavior (out and about, or in torpor) exhibits any correlation with the variation in the timing of plant green-up and senescence across space, and whether “mismatch” between when bears exit dens and when plants green up (plants like sedges are an important food source for bears early in the year) seems to have any population consequences.
Snapshot Wisconsin cameras capture bears growing and moving across seasons.
While Wisconsin vegetation greens up from late winter to mid-summer, bears also become increasingly present across the landscape.
BUT…..while satellite imagery provides an excellent overhead synopsis of plant activity, it is not always clear which plants are making the image green. Bears–and many other animal species–primarily eat green matter at ground level rather than leaves at the tops of trees. Snapshot Wisconsin’s cameras provide a ground view that we can relate to satellite images to get a sense of what airborne imagery is responding to. In the long term, this will allow improved estimates of where animals are and at what time.
My brother Ian was a picky eater. Breakfast was always a bowl of Crispex. For lunch, he ate a PB&J and refused to eat the crusts. I was the opposite. Even as a young child, I loved proverbially “gross” foods like mushrooms and started drinking coffee when I was twelve.
Turns out that some animals are like Ian and some are like me. For example, monarch caterpillars only eat milkweed. We call animals like the monarch specialists. Conversely, some animals will eat, well, just about anything. Raccoons, for example, are equally happy eating crayfish from the creek or scraps from your garbage can. We call such species generalists.
Diet isn’t the only thing to be picky about! Some species exhibit preferences for precise habitat types. For example, the Kirtland’s Warbler breeds only in young jack pine barrens, primarily in Michigan, but also occasionally in Wisconsin. On the other hand, some species are ubiquitous. The coyote is an exemplar habitat generalist—you might spot one in the wilds of the Chequamegon-Nicolet National Forest or in a suburb of Milwaukee.
Taken together, diet and habitat comprise what we call the ecological niche of a species. You can think of a niche as the “cubbyhole” that a species occupies within the broader tapestry of its environment. The breadth of a niche is a continuum from extreme specialists (like Kirtland’s Warblers) to extreme generalists (like raccoons). Some species fall between those extremes; deer are a great example. Deer are strict herbivores, but they can be found in many different habits, from forests to farmlands. So, not every species can be neatly classified as a generalist or a specialist.
Scientists are interested in generalists and specialists because they exhibit different responses to change. Like a trained craftsman whose job is replaced by a machine, the specialist has nowhere to go when the environment changes. Generalists, on the other hand, can capitalize on the vacant niche space and colonize altered landscapes. Given the widespread changes humans are exerting on the earth, we are seeing global proliferation of generalists while many specialists are disappearing, a process known as biotic homogenization.
This may seem dire, but the more we learn about generalists and specialists, the more we’ll be able to do to maintain biodiversity and lose fewer specialists. In the meantime, I encourage you to think about the animals you see on a regular basis. Is that squirrel outside your window an ecological jack-of-all-trades? Are there any habitat specialists that live on your property? And maybe even think about your own niche—are you a generalist, a specialist, or somewhere in between?
Stop for a second and try to visualize 23 million of something. The number of species on the planet? That’s roughly 8.7 million. The number of residents in Wisconsin? Nah, that’s not even 8 million! How about photos collected by the Snapshot Wisconsin project since 2016? Ding ding ding! (well – 23,706,425 photos to be exact, not like we are counting or anything…)
Up until recently, Snapshot Wisconsin volunteers were uploading roughly one million photos total per month – but this number is bound to increase after nearly doubling our volunteer base! When we share this statistic during trainings and presentations, we always know to expect the question, “How do you keep up with all of those photos!?”
“Well, it’s a little complicated”, is how we generally start the answer. In this blog post we will dive into how the project has been maintaining this vast amount of data so far, and exciting prospects for the future of Snapshot Wisconsin.
Filtering Photos for Zooniverse:
Zooniverse is a crowdsourcing platform hosting sites for a large variety of projects, including Snapshot Wisconsin. Here anyone with internet access can go online and classify images collected by trail cameras in the project. Before photos are sent to Zooniverse, Snapshot Wisconsin trail camera hosts have the opportunity to view and classify their own photos.
While the volunteers are required to identify and remove human photos, classifying blanks and animals is extremely helpful! Why is this? We conducted an analysis to determine the accuracy of single classifications made by volunteers in their MySnapshot accounts, versus consensus classifications made by volunteers on Zooniverse. We were able to identify species that volunteers are really great at classifying (e.g. deer, squirrels, raccoons, turkeys, etc.)! When these photos are classified by volunteers in their MySnapshot accounts, we do not send them to Zooniverse. Instead we take the volunteer’s classification as the “final classification” for the image, which helps cut back on the number of photos for which we rely on Zooniverse classifications.
Crowd Sourced Classifications on Zooniverse:
The remainder of photos are uploaded to Zooniverse in “seasons”, with each season containing anywhere from 30,000 to 50,000 images. Once a season wraps up, staff members can be caught scrambling around the office getting a new season ready to go. To prepare for each season we need to upload photos and their information, as well as manually review photos to ensure no humans or excessive number of blanks get uploaded. On average, it has taken roughly 3 months for a season to be fully classified and a new season to be uploaded, which generally includes a break that lasts a few weeks.
On Zooniverse, multiple volunteers will view and classify each photo to produce a consensus classification. Photos are viewed by upwards of 11 volunteers if a consensus isn’t reached early on; if a consensus is never reached the photos will go on to expert review by staff members. Since launching in 2016, Zooniverse volunteers have helped the project move through 9 full seasons of photos. Season 10 just launched last week! Across these seasons, the project has had over 6,000 registered volunteers participate and classify 2,253,244 images, or an average of 2,596 photos per day.
Moving Forward – Machine Learning to Classify Animals:
Recently a team of researchers created a computer model using machine learning that classifies images captured by trail cameras. Machine learning is the science of getting computers to learn and act like humans do, and improve their learning over time in autonomous fashion buy feeding them data and information in the form of observations and real-world interactions¹. In this case, the computer model was provided over 3 million images of animals, each that had already been classified by a human, to aid the computer in “learning” to determine which species is which in trail camera images.
The trained model was able to classify approximately 2,000 images per minute at 98% accuracy on images of species collected in the United States. The Snapshot Wisconsin team recently prepared a large set of classified images to further improve the model, and to potentially be incorporated into the project to help keep up with the booming number of images collected. This isn’t to say that volunteer classifications (MySnapshot or Zooniverse) would be replaced, but using automated classifications could help ramp up the speed at which the project produces viable data.
To view the scientific paper, Machine learning to classify animal species in camera trap images: application in ecology, visit this link: https://www.biorxiv.org/content/biorxiv/early/2018/06/13/346809.full.pdf
- Faggella, Daniel (2018, October 29). What is Machine Learning? Retried from https://www.techemergence.com
As graduate student on the Snapshot Wisconsin project, part of my role is to help the team better understand their volunteers and conduct research that will assist with program improvement. One way I do this is by surveying trail camera hosts when they enter the program and after they have been participating in Snapshot Wisconsin for one year.
Developing a survey takes more work than you might expect! Some things, like age or occupation, are relatively easy to measure. However, abstract concepts like satisfaction or attitudes are much more difficult to capture in a survey. These abstract concepts must be measured in more indirect ways, and typically social scientists develop a number of survey questions or items to measure a concept.
For example, let’s say I wanted to measure someone’s job satisfaction through a survey. You could ask, “How happy are you overall with your job?” (Rate 1-5).
In order to capture more aspects of job satisfaction, it would be better to ask: “How happy are you with each of the following parts of your job? Autonomy, work load, salary, coworker relations, etc.” (Rate each 1-5).
Bear with me while I get theoretical for a moment…
Imagine you have a whole universe of survey items you could ask someone about job satisfaction. If you choose just one question to ask them, that question is not likely to be a good representation of their job satisfaction as a whole. However, if you ask them multiple questions, you get a much better representation of their job satisfaction.
Let me use an analogy. If I want to know all the different species of mammals found in a particular county and I put out just one trail camera in that county, it isn’t likely to be sufficient. I put out a whole bunch of cameras across the county, I’d get a much more accurate count.
Often, I get this question from people who take surveys: Why do some of these survey questions seem so similar to one another? Can’t you ask this with just one question?
The answer is: if we are asking about an abstract concept in a survey, assessing it indirectly though multiple questions is the best way to go if we want valid scientific results.
Through email and the internet it is so easy to deliver surveys and if you are like me, you get a survey in your inbox from some business or organization just about every week. Hopefully this sheds a little light on what goes on behind the scenes before you get that “new mail” notification.
For those of you who have completed a Snapshot Wisconsin survey, your responses are truly valued. We are learning a lot; see here for some early results and keep your eyes on the blog for more. If you are interested in learning more about the science behind surveys, let me know in the comments!
The Snapshot Wisconsin team (mainly our awesome summer intern, Ally) spent a lot of time over the summer prepping equipment for our statewide launch. We had over 200 kits made and thought that was a good amount. None of us could have predicted the phenomenal response from new volunteers! Since August 9th we have had more than 1100 people signup to host Snapshot Wisconsin cameras across the state. Additionally, more than 300 people had signed up in non-open counties over the last 2 years. So, things at Snapshot Wisconsin have been super busy, to put it mildly. We started our fall training schedule last week with in person training in Platteville and Darlington. This week we are off to Merrill and Crandon (the remainder of our training schedule can be seen here). We also launched a new online training system, including brand new videos, last week. More than 200 people have completed the new online training system and we are working on getting them setup with MySnapshot accounts and getting equipment out the door. Thanks to all the volunteers for their patience and enthusiasm for getting started with our project. We have been working on some automation to better manage the multitudes of new volunteers, in time that should help us to be more efficient.
We are really excited to spend our fall traveling, meeting new volunteers and seeing new photos come in from all over Wisconsin. Stay tuned for more behind the scenes blog posts to come!
My name is Emily Buege – I’m the newest Snapshot Wisconsin team member, and I wanted to do a quick blog post to introduce myself. After obtaining my bachelor’s degree in ecology from Winona State University, I moved to Tuscaloosa, Alabama where I began working toward my master’s degree in environment & natural resources. In the mix, I also spent a summer working at the International Wolf Center in Ely, Minnesota.
My master’s thesis examined the distribution of nesting sites for several native fish species in the Bladen River in Southern Belize. Specifically, I looked at which habitat variables seemed to be most important for each of four species as they chose a site suitable to brood their young. All four species were cichlids, which are well-known for defending their eggs and fry against predators. Not only did that parental behavior make for an easy way to identify and record the nest locations, but it was also fascinating to watch!
Being that my project was through the University of Alabama’s Department of Geography, one can imagine that it was spatial in nature. Combined with my preexisting passion for wildlife conservation, the skills and interests that resulted from my time at UA led me to my new position with Snapshot: Spatial Analyst and Database Manager. I am very excited to dive into these roles, because the project is rich in spatially-explicit data! This is especially true with the launch of Phase 2 – all corners of the state will be reporting wildlife data that has previously been unavailable.
In addition to making more maps with our new data, one of the efforts I’m looking forward to working on is data visualization. Now that Snapshot Wisconsin has collected so much data, there are a lot of opportunities to do visualize that information. Right now, we have no way of allowing the public to interact with the data or to view a select set of photos. We hope that as the project grows, we can develop a tool to do just that. I think that making data interactive and visual allows more people to connect with it on a deeper level.
See you out in the field and on the message boards!