Archive | May 2019

May Science Update: Maintaining Quality in “Big Data”

Snapshot Wisconsin relies on different sources to help classify our growing dataset of more than 27 million photos, including our trail camera hosts, Zooniverse volunteers and experts at Wisconsin DNR. With all these different sources, we need ways to assess the quality and accuracy of the data before it’s put into the hands of decision makers.

A recent publication in Ecological Applications by Clare et. al (2019) looked at the issue of maintaining quality in “big data” by examining Snapshot Wisconsin images. The information from the study was used to develop a model that will help us predict which photos are most likely to contain classification errors. Because Snapshot-specific data were used in this study, we can now use these findings to decide which data to accept as final and which images would be best to go through expert review.

Perhaps most importantly, this framework allows us to be transparent with data users by providing specific metrics on the accuracy of our dataset. These confidence measures can be considered when using the data as input for models, when choosing research questions, and when interpreting the data for use in management decision making.

False-positive, false-negative

The study examined nearly 20,000 images classified on the crowdsourcing platform, Zooniverse. Classifications for each specie were analyzed to identify the false-negative error probability (the likelihood that a species is indicated as not present when it is) and the false-positive error probability (the likelihood that a species is indicated as present when it is not).

false_negative_graph

Figure 2 from Clare et al. 2019 – false-negative and false-positive probabilities by species, estimated from expert classification of the dataset. Whiskers represent 95% confidence intervals and the gray shading in the right panel represents the approximate probability required to produce a dataset with less than 5% error.

The authors found that classifications were 93% correct overall, but the rate of accuracy varied widely by species. This has major implications for wildlife management, where data are analyzed and decisions are made on a species-by-species basis. The graphs below show how variable the false-positive and false-negative probabilities were for each species, with the whiskers representing 95% confidence intervals.

Errors by species

We can conclude from these graphs that each species has a different set of considerations regarding these two errors. For example, deer and turkeys both have low false-negative and false-positive error rates, meaning that classifiers are good at correctly identifying these species and few are missed. Elk photos do not exhibit the same trends.

When a classifier identifies an elk in a photo, it is almost always an elk, but there are a fair number of photos of elk that are classified as some other species. For blank photos, the errors go in the opposite direction: if a photo is classified as blank, there is a ~25% probability that there is an animal in the photo, but there are very few blank photos that are incorrectly classified as having an animal in them.

Assessing species classifications with these two types of errors in mind helps us understand what we need to consider when determining final classifications of the data and its use for wildlife decision support.

Model success

When tested, the model was successful in identifying 97% of misclassified images. Factors considered in the development of the model included: differences in camera placement between sites; the way in which Zooniverse users interacted with the images; and more.

In general, the higher the proportion of users that agreed on the identity of the animal in the image, the greater the likelihood it was correct. Even seasonality was useful in evaluating accuracy for some species – snowshoe hares were found to be easily confused with cottontail rabbits in the summertime, when they both sport brown pelage.

bear_photo

Not only does the information derived from this study have major implications for Snapshot Wisconsin, the framework for determining and remediating data quality presented in this article can benefit a broad range of big-data projects.

Advertisements

Snapshot Saturday: May 25th, 2019

In addition to making excellent back-scratchers, trees also offer a tool for black bear to communicate with one another. These so called “rub trees” assist bears in shedding their winter coats while leaving behind their scent, making their presence known to passersby.

Check out this black back and their rub tree captured on a Marinette County Snapshot Wisconsin camera!

This slideshow requires JavaScript.

Did you know you can view and classify photos collected from Snapshot Wisconsin cameras across the state at www.SnapshotWisconsin.org? It’s a fun activity for the whole family!

Rare Species Sighting: American Marten

In late February this year, a Snapshot Wisconsin trail camera deployed in Vilas County captured an American marten (Martes americana). This is the first time an American marten has been captured on a Snapshot Wisconsin camera! The below American marten was identified by the trail camera host, Ashley, and the identification was then confirmed by several species experts in the Wisconsin DNR. While American marten can vary in color, they are best identified by their pale buff to orange throats, dark legs and tails, vertical black lines running above the inner corners of their eyes, and bushy tails that account for one-third of their total length.

marten_SSWI000000011754918A (002)

American marten captured on a Vilas County Snapshot Wisconsin trail camera.

Extirpated from Wisconsin in the 1940’s, these small members of the weasel family were later reintroduced to the state and placed on the Wisconsin Endangered Species List in 1972 due to loss of suitable habitat. Marten are restricted to the northern portion of the state where they reside in dense, mature forests with preference for areas that are a mix of coniferous and deciduous trees.

Untitled-3

Counties shaded in blue have documented occurrences for American marten in the Wisconsin Natural Heritage Inventory database. The map is provided as a general reference of where occurrences of American marten meet NHI data standards and is not meant as a comprehensive map of all observations. Source: WNDR.

Did you know that marten are excellent climbers? They use this skill not only to hunt down prey, but also to avoid potential danger. These solitary animals are very territorial, with territories spanning an average of two square miles for males and one square mile for females. Although the breeding season lasts from July to August, fertilized eggs do not fasten to the uterine wall until January or February. Females birth two to four kits in March or April, and raise their young in tree dens without any male assistance.

There is still much to be learned about American marten, as their nocturnal lifestyle and often shy demeanor make them a difficult species to study. Follow this link for more information about American marten in Wisconsin, and stay tuned to discover what rare species will be captured next on Snapshot Wisconsin trail cameras!

Snapshot Saturday: May 18th, 2019

Test your Wisconsin wildlife identification skills with this below trail camera image. These small, rare members of the weasel family were once extirpated from the state and later reintroduced in Wisconsin northwoods. Staff members were pleasantly surprised when the first individual of this species made their debut on a Snapshot Wisconsin camera in Vilas County this year!

marten_SSWI000000011754918A (002)

Interested in hosting your own Snapshot Wisconsin camera? Visit our webpage to find out how to get involved: https://dnr.wi.gov/topic/research/projects/snapshot/.

An Iowan Learns About Porcupines

M2E72L208-207R399B417

Before joining Snapshot Wisconsin in 2016, I knew very little about porcupines. I grew up in Iowa where porcupines were extirpated in the 1800’s. What I knew consisted of what I learned from my grandparents as a youngster on summer fishing trips to northern Minnesota. Essentially, porcupines have sharp quills and you don’t want your dog to tangle with them. I never saw a porcupine on any of these trips but was always on alert to make sure my dog, a Miniature Schnauzer named George, never wandered too far.

My first task upon joining Snapshot Wisconsin was classifying photos from Black River Falls, where trail cameras are in place to monitor the reintroduced elk population. As I was flipping through photos, I kept seeing these critters that I couldn’t identify. They were small, rounded and dark colored, always facing away from the camera, and only appearing at night. I wasn’t sure what these could be, and we had yet to create resources to help with this task, such as the Snapshot Wisconsin Field Guide*. Sometimes I classified them as raccoons and sometimes as beaver (in my defense, our early cameras didn’t take very clear photos!)  Eventually, my porcupine identification skills improved and thankfully so did the photo quality of our cameras. Porkies have since become one of my favorite species captured on our cameras. Read below to learn more about these quill-y, charismatic critters!

There is only one species of porcupine in Wisconsin, the North American porcupine (Erethizon dorsatum). Worldwide there are 23 different species of porcupines. Our porcupine is the second largest rodent in North America, only beavers are larger. Their size ranges from 7-30 pounds and 20-26 inches. They typically give birth to one young per year. Young are called porcupettes.

M2E49L137-137R399B381

Porcupines are herbivores, consuming tree bark, branches, buds, evergreen needles, garden produce, and even tool handles.. A common misconception is that porcupines can shoot their quills when threatened. The quills are actually loosely attached  and embed themselves in the unfortunate victim when they come in direct contact with the porcupine.

M2E34L88-89R391B360

Porcupines occur in the Northern and Central Forest regions of Wisconsin. To date, we have had  4,175 reports of porcupine from trail camera hosts. These have not yet been verified and presumably include a few raccoons and beavers due to my early classification mistakes and similar errors by other staff and volunteers. A handful of porcupine classifications from southern Wisconsin (Grant, Iowa and Waukesha counties) revealed the true species to be woodchuck, raccoon, unknown bird and squirrel. Species distribution maps are quite useful for classifying our photos and Snapshot Wisconsin data will be instrumental in updating these in future.

Find out more about porcupines at the links below!

Sources:

*Snapshot Wisconsin Classification Field Guide (located on the right hand side of your screen while classifying photos on Zooniverse)

Snapshot Saturday: May 11th, 2019

Can you guess what tree-climbing species is featured in this Snapshot Saturday? We will give you a hint, their “crimson cousins” don’t share this skill!

5.11.19_SnapshotSaturday

Did you know you can view and classify photos collected from Snapshot Wisconsin cameras across the state at www.SnapshotWisconsin.org? It’s a fun activity for the whole family!

May Volunteer of the Month

May’s Volunteer of the Month is
Chris from Portage County!

Volunteer of the MonthMay’s Volunteer of the Month goes to Chris from Portage County! Chris is a Professor of Biology at UW-Stevens Point. Chris was first introduced to citizen science around 10 years ago through the Wisconsin Bat Program. In collaboration with the Urban Ecology Center and Milwaukee area high school teachers, Chris has since developed a bat curriculum that incorporates citizen science, or as it is known in Milwaukee, community science.

Chris first discovered the Zooniverse platform about two years ago, which led him to learn about Snapshot Wisconsin. After he began hosting his own trail camera, Chris stated that he was initially annoyed by a fawn that rested in front of his camera resulting in hundreds of photos (which we are sure many volunteer have experienced!) Chris’s “aha moment” was then realizing how interesting the data collected about that fawn was – time alert, sleeping, stretching, foraging.

When asked about his advice for potential volunteers, Chris shared, “There are lots of citizen science projects, but Snapshot Wisconsin does a great job of motivating its volunteers. Start with Zooniverse. Snapshot Wisconsin was a pioneer project on this global platform and will connect you immediately to Wisconsin wildlife. If you are hooked by Snapshot like I was, you can consider hosting your own camera and become a small part of a big thing.”

Thank you, Chris! Thank you to all our trail camera hosts and Zooniverse volunteers for helping us discover our wildlife together.

Snapshot Saturday: May 4th, 2019

Trail cameras offer a non-invasive approach to monitor not only animals, but their surrounding habitats as well. In addition to capturing exciting images of wildlife Snapshot Wisconsin cameras are programmed to take a daily time-lapse image at 10:40 a.m.  As part of the project’s phenology research staff members began measuring the greenness in these time-lapse photos to determine when the different “phenophases”, or significant stages in the yearly cycle of a location’s vegetation, are occurring across the state.

M2E67L194-194R377B333

If you have noticed the vegetation around you becoming a little more colorful, that is because much of the state is entering the “greenup” phenophase. This Snapshot Saturday features a Sawyer County elk enjoying spring greenup from May 2018.

Interested in hosting your own Snapshot Wisconsin camera? Visit our webpage to find out how to get involved: https://dnr.wi.gov/topic/research/projects/snapshot/.

April #SuperSnap

This month’s supersnap goes to an inquisitive red fox (Vulpes vulpes) chasing prey, nominated by @AUK. Red fox are known for their intelligence and cunning. These abilities help them to survive all over the world in a diverse set of habitats including mountains, deserts, grasslands, urban environments and here in Wisconsin!

The University of Wisconsin Madison has launched a project, the Urban Canid Project, to investigate red fox and coyote use of urban landscapes. Similar to Snapshot Wisconsin, the Urban Canid Project uses the power of citizen science to collect data on space use, behavior and population demographics of city dwelling canids. To learn more about the project, check out this link.

This slideshow requires JavaScript.

Continue classifying photos on Zooniverse and hashtagging your favorites for a chance to be featured in the next #SuperSnap blog post. Check out all of the nominations by searching “#SuperSnap” on the Snapshot Wisconsin Talk boards.