We are pleased to announce iNaturalist has joined 1% for the Planet as an environmental partner! This partnership offers a new way for iNaturalist to expand its impact by reaching more businesses involved in the environmental movement.

1% for the Planet is an accountability partner for businesses that are ready to reject business as usual and give back to environmental partners making a difference around the globe. Started in 2002 by Yvon Chouinard, founder of Patagonia, and Craig Mathews, founder of Blue Ribbon Flies, their members have given hundreds of millions of dollars to environmental partners to date.

To date, 5400+ business partners have given more than $540 million USD to environmental partners around the world.

“The intent of 1% for the Planet is to help fund these diverse environmental organizations so that collectively they can be a more powerful source in solving the world’s problems,” writes Yvon Chouinard, co-founder of 1% for the Planet.

Would your business like to be featured as a supporter of iNaturalist through 1% for the Planet? Please reach out to corporategiving@inaturalist.org.

Any organization, business, or other corporation can donate online, or check out other ways to give.

Our Observation of the Week is this Utricularia kumaonensis bladderwort plant, seen in Nepal by @elizabeth_byers!

“I grew up in the Adirondack Mountains of northern New York state where nature is dramatic and accessible,” says Elizabeth Byers, who’s currently a wetland ecologist in the Appalachian Mountains of West Virginia. “I love the verticality of biodiversity in the mountains, walking upward through different life zones and discovering hidden treasures on cliffs, in deep forests, and in little jeweled wetlands.”

And it’s not just the Appalachians where Elizabeth works, she has a special interest in subalpine and alpine ecosystems of eastern Nepal. Last year, she and her husband Alton spent five months in Kanchenjunga Conservation Area, a roadless part of eastern Nepal, where they studied alpine ecosystems on a Fulbright grant. Even getting to their research area involved walking a week from the nearest road, in canyons along the Tamur River. 

The Tamur River has some impressive riverside cliffs, and the trail snakes up and down the side slopes to circumvent them. There is one spot where a dangerous boardwalk has been built right along the cliff face directly over the rapids of the river, and the river spray washes the seepy moss-covered cliff face (and anyone walking by). For a botanically-minded person, this habitat is the mother lode for Utricularia species, tiny carnivorous plants that grow on wet cliffs where soil is essentially absent. Utricularia, also called bladderworts, derive nitrogen from miniscule insects that are lured into tiny spheres or bladders on the plant’s roots.  The bait is a sweet nectar, and once through the trapdoor there is no escape. Digestive fluids flood the bladder and digest the insect.

So, while carefully navigating the precarious boardwalk over the river, I stopped and braced my feet to search for Utricularia. My gasp of surprise and awe was completely inaudible above the roar of the rapids - there were literally tens of thousands of them in perfect bloom along the cliff face, more than I’ve ever seen in all of my wanderings. Shielding my camera (a Panasonic Lumix DC-ZS70) from the wet spray, I took a bunch of photos and collected a specimen to bring back to the National Herbarium in Kathmandu.

As Elizabeth said, bladderworts grow in wet areas where there isn't much soil - pretty much only the flowers are what stick out. Some, especially in Central and South America, are epiphytic and have large, showy, orchid-like flowers. 

“I've recently completed a field guide (mobile app) to the “Wildflowers of Mount Everest” in Nepal, and I’m working on a book on the “Flowers of Mount Kanchenjunga” with three Nepali colleagues, plus contributing to the upcoming “Primroses of Nepal” book,” says Elizabeth (above, taking the first-ever photograph of the rare Primula ramzanae).

iNaturalist has changed how I collaborate with international colleagues, how I develop restoration tools, and how I teach plant identification classes. It has also allowed me to enrich my life by learning some biota that are not in Plantae. It’s a transformational database and a remarkable community of experts and enthusiasts that is making nature more accessible while so many other forces in the world are distancing us from our roots. Especially in remote areas, it is a key tool for documenting biodiversity.

(Photo of Elizabeth by Alton Byers. Some quotes have been lightly edited.)

- here’s an explanatory video of how a bladderwort’s bladder trap actually works, and some nice footage of one in action.

- check out the most-faved bladderworts on iNat!

Our Observation of the Week is this Sanniostracus carnavalescus snail, seen in Brazil by @nagylafachetti!

Nágyla Fachetti Coser works at Sooretama Biological Reserve, which is “the largest conservation unit in the state of Espírito Santo, with more than 27 thousand hectares of forest,” she tells me. “I have always been interested in nature, but this interest strengthened when I started working here and having closer contact with the forest, which is home to enormous biodiversity, which I love.”

A few weeks ago, Nágyla was helping to monitor one of the reserves trails when she spotted the snail you see above. “I saw it in a tree and at first I hesitated to record it as I already had many records of snails,” she says, “but I later photographed and posted it to iNaturalist.”

Nágyla’s observation is one of only eight observations of the species on iNat, and I reached out to Daniel Cavallari (@danielcavallari), a Brazilian taxonomist who recently coauthored a paper that moved the snail from Leiostracus to the genus Sanniostracus, which he says is “a portmanteau of two lexicons, ‘sannio’ (Latin for ‘harlequin’). and ‘ostrakon’ (Greek for ‘shell’).” 

As far as we know, it is endemic to the Atlantic Forest of southeastern Brazil. While it was described in 2016, the stretch of forest where the species was initially found was deforested to make way for tomato cultivation. This left us concerned about the possible extinction of the species, but other individuals were observed (including here on iNaturalist) later. We were scared, but considering the vulnerability of land snails to climate change and such, it was a well-founded scare! 

“I still don't have training in the environmental area,” says Nágyla (above). “I'm currently taking a technical course on the environment and I'm interested in all groups of living beings. I always try to photograph as many individuals, animals, plants, fungi, and later post them on iNaturalist.”

I use iNaturalist, because this is a platform that brings together nature lovers from all over the planet. through it I can acquire a lot of knowledge, discover the names of species that I photograph and contribute to science and research. I can photograph a rare species, or even one that has not yet been described, and thus attract more researchers to explore the enormous biodiversity of the reserve.

Using iNaturalist has certainly changed my relationship with the natural world. Now I am more attentive to issues of conservation and preservation of nature, I am increasingly willing to see its beauty, even in small details, like tiny animals and fungi, for example.

(Photo of Nágyla by Sheyla Rossi. Nágyla wrote to me in Portuguese. I used Google Translate, and performed some alterations to the quotes for clarity and flow.)

- Daniel also coauthored this paper, which looks at the utility of iNat as a tool when studying tropical mollusks!

- check out two past terrrestrial gastropod observations of the week, one from @souhjiro, and another from @pizzamurderer!

- Sanniostracus carnavalescus belongs to the family Bulimulidae. Take a look at some of the most-faved observations of that taxon!

Our Observation of the Week is this Black Widow (genus Latrodectus) and its American Broad-front Fiddler Crab (tribe Minucini) prey! Seen in the United States by @evan_tree.

“As part of Texas Master Naturalists, I was fortunate enough to visit the East Foundation's El Sauz Ranch in deep south Texas,” says Evan Trees. 

While most of the group was looking up at birds, I was looking down in a very old (and dry) concrete cattle trough and in an enclosed corner I spotted the black widow's web, which I was very surprised to see had trapped a crab. I saw that the spider was still feeding on this particular crab (a type of American Broad-front Fiddler Crab) and there was another wrapped and discarded below in the leaf litter. I later told Texas Parks and Wildlife Dept urban wildlife biologist Sam Kieschnick (@sambiology), who was nearby, and he immediately gave it a precise identification as a Northern Black Widow (Latrodectus variolus).

I believe the crabs must scuttle up from a nearby brackish water pond and get trapped in the enclosure, eventually stumbling into the web to be consumed.

The genus Latrodectus - known as widow spiders, redbacks, and button spiders, among other English names, is one of the world’s most notorious spider groups, as their venom is medically significant to humans. A widow bite causes latrodectism, the symptoms for which include fever chills, and intense muscle pain. It sounds like a truly miserable illness but is rarely fatal, and widow spiders do not seek out humans to bite, they must be provoked and generally given no other option. 

It’s decapodian prey is an unknown species of fiddler crab (family Ocypodidae), and fiddler crabs show up in tropical and temperate areas of the world. They’re fairly terrestrial and can be seen on beaches and sandy areas where the males court females by waving their one large “fiddling” claw. Latrotoxin, as Evan pointed out to me, contains at least one chemical that specifically affects crustaceans, so if the spider is able to get a bite in then the crab can be subdued.

Originally from the US state of Pennsylvania, Evan (above) credits his interest in nature to his family, his rural upbringing and the scouts. He moved to Texas about a decade ago and tells me

I've completely fallen for the incredibly unique and fragile ecosystems here -- karst springs, chalk prairies, vernal pools. I spend a lot of time in the greenbelts, urban creeks and overgrown lots around Austin observing the effects of development on wildlife, what manages to endure in hidden places and how life rebounds in the aftermath of disturbance.

For me, iNaturalist is a lens through which to see all the hidden, incredible things around me. I like to go into “Explore” and find plants or trees nearby that I'm learning about to go out and see in person. And when I see something I don't recognize, after identifying it I like to look through observations by other users to see what the plant looks like in different seasons, under different conditions and at different phases of development. And I'm just now learning more about connecting with and communicating with other users since some more training given by Texas Master Naturalists.

(Photo by Pearl Chen. Some quotes have been lightly edited for clarity.)

- check out this interview with @sambiology from 2017! 

- a birder’s fiddler crab observation in California extended the species’ range by hundreds of kilometers.

- Deep Look has some phenomenal footage of Latrodectus spiders here, as well as some surprising facts about their reproductive behaviors.

We are embracing the Halloween spirit with a spider theme woven through these iNaturalist impact highlights from October 2023! If you missed last month's highlights you can find them here.

Invasive Species Science

@ashleytwahlberg’s new study in the Journal of Arachnology used iNaturalist data to assess the invasion of the Brown Widow Spider across the Americas. Similarly, @dcoyle and colleagues at Clemson Extension are using iNaturalist to track the invasive Joro spider in the southeastern United States.

Not to be outdone, October is also Spotted Lanternfly season. You can read here about @tanya_campbell’s observation documenting lanternflies creeping into Canada and iNaturalist help tracking this invasion from Maryland to New York. This story highlights @drcrayfish’s help identifying invasive crayfish in Canada, while this story highlights iNaturalists use in understanding the Chinese Mitten Crab invasion in the United Kingdom.

Climate Change Science

Leaving our spider theme for a moment, our favorite climate change story was about @sgorta and colleagues using iNaturalist data to understand biodiversity responses to recent Australian megafires.

Check out this study using iNaturalist to understand the climate change impact of methane emissions from termites, and this story about @clairegoodwin_hmsc’s work using iNaturalist to document out-of-place species in marine ecosystems driven by climate change.

Science Discoveries

Our favorite science discovery from October was this story about @louwclaassens use of iNaturalist to discover a new species of pipehorse. The effort leveraged the iSeahorse project on iNaturalist which turned 10 years old this month.

There were many examples about range extensions like this story about @nedster and @nicolem42’s discovery of Lemon Cuckoo Bumble Bee in Illinois, @silviatav’s study on the discovery of stalked jellyfish in Portugal, a worm lizard range extension in Brazil, new millipedes reported from the Canary Islands, and hybrid buntings reported in Russia.

Conservation and Monitoring

Back to our spider theme, this great article makes a compelling argument for how observing spiders can help us understand why they are declining with iNaturalist anecdotes from @mira_l_b and @bnm50.

In other news, Newsweek and CapetownEtc told the story of @eugene_hahndiek’s thought to be extinct flower posted from South Africa that Custodians of Rare and Endangered Wildflowers (CREW) identified. Read more about CREW’s use of iNaturalist in this recent Biodiversity and Conservation article. We loved @elia_van_tongeren and colleague’s paper on how iNaturalist helped understand butterfly extinction patterns in Italy and stories about monitoring declining Christmas beetles and bandicoots in Australia.

Don’t miss ScienceFriday’s excellent piece on @akilee and colleagues monitoring the spread of Beech Leaf Disease. This article described @scott654’s study assessing potentially at risk Illinois hoverflies, while other studies used iNaturalist to assess West Atlantic marine taxa, butterflies in Ecuador, and cactus biogeography.

Lastly, we couldn’t resist this photo from @rony_alberto_garcia_anleu of @seyner and Wildlife Conservation Society colleagues using iNaturalist to monitor species in Guatemala’s Maya Biosphere Reserve.

Roadkill and Landscape Connectivity

No spiders here, but equally ghoulish, this article highlighted the value of roadkill observations @damonyeh and colleagues’ Tahoe Basin Connectivity Study. In Australia, this story described @katyw’s use of roadkills on iNaturalist to find wombat road crossing hotspots as part of her rescue work. Roadkill observations helped @raul_pommer and colleagues study the distribution of Crab eating fox in Brazil while this story links reporting roadkills to iNaturalist with snake conservation in Vancouver.

iNaturalist Impact on AI Research

Yesterday, New Scientist described mind-blowing research by @carlosemunoz using iNaturalist images to train a Neural Network to show how insects like @tshahan’s moth pictured here mimic spiders to avoid predation.

iNaturalist images contain a tremendous amount of information that help scientists study everything from how monarch caterpillars and woodsorrell are changing color to adapt to climate change, to helping morphologically delineate Chilean geckos, to public health science around exposure to poison ivy, to @marinejanine’s sea dragon behavior research.

iNaturalist images and AI tools are supercharging this Phenotypic Revolution by allowing scientists to more easily detect and measure phenotypic patterns. Two articles on image analysis with iNaturalist appeared in this month’s special issue of Applications in Plant Sciences. One offered new tools for extracting color patterns from iNaturalist images while the other outlined new techniques for improving the usefulness of iNaturalist photos for image analysis.

Meanwhile, the iNaturalist dataset has become a standard benchmark dataset for the Computer Vision community as evidence by its use in papers this month by Jinglun Li et al., Panos et al., Lianbao Jin et al., Zikai Xiao et al., and Anonymous authors. Caltech incorporated an iNaturalist scavenger-hunt into an AI event on campus this month which highlights this virtuous cycle between iNaturalist and the AI research community.

iNaturalist for Land Stewardship

This role of iNaturalist in bridging native species, bioregionalism, and stewardship was highlighted by author Jenny Odell in a talk from earlier this month. We were inspired by @thenectarbar’s quote: “if every single person would make a 10-foot by four-foot space and dedicate it with native plants then we are doing our part to put the diversity back” from this story about Texas gardeners using iNaturalist to identify native plants. @robdv’s excellent article describes using iNaturalist to attract native insects while this article highlights using Seek to help rear and restore butterflies. Beyond planting and attracting native species, @andreakautz explains in this article how iNaturalist can be used to identify and remove invasives from gardens.

This article details the excellent work of @vmacphail and other Pollination Guelph volunteers who used iNaturalist to log hundreds of species at restored sites that were just bare sod a few years ago. Other events that incorporated iNaturalist into restoration themed events included this story on Rosemont Preserve Restoration Day, this story on the upcoming Armour Hill Clean-up, and this story on the Wall Street Journal’s Giveback Day 2023. Lastly, this story highlights @luisfssantos and colleague’s use of iNaturalist to document a rare plant as part of efforts to purchase and preserve a Portuguese wetland.

October iNaturalist Events

Coverage of spider themed October events included the North Carolina Spider Search and Aracnoctubre. Keeping with the Halloween theme, we loved the coverage of the Life in Our Cemeteries iNaturalist event in Australia.

Student led bioblitzes were highlighted in this article about the North Carolina Campus Nature Challenge, and this article about the CASS Minibioblitz in New Zealand. Lastly, this video features a Wisconsin Tyke Hike by the Delafield Public Library in Wisconsin.

iNaturalist’s Human Health Impact

This article profile’s @scarlett_smout’s research on healthy bodies and minds and her use of iNaturalist. Likewise, this Guardian article endorses iNaturalist and Seek as great apps for connecting to nature. But how do people connect to nature if they can’t get over their fear of creepy crawly things like spiders? Backpacker editor and spider enthusiast Adam Roy describes how and the role of iNaturalist in this excellent podcast.

Several stories mentioned using iNaturalist in seasonal nature activities to help people connect to nature such as enjoying fall foliage in Central park with @carey_russell. Many stories focused on mushroom hunting ranging from this story on @allthingsfungi’s efforts to get people overcome their fear of fungi, to @mycology_mike leading mushroom hunts around Oberlin College, to @nschwab’s Mycoblitz Europe project, to this story about @bdthomas mushroom foraging in Rhode Island. This article describes using iNaturalist to get started with foraging. Please remember to forage responsibly!

iNaturalist’s Education Impact

This study details @ulfi_faizah's experience incorporating iNaturalist into a University biology course in Indonesia, while two separate Brazilian studies assessed iNaturalist’s use as a remote learning tool for teachers here and here. This article on @biolily’s work at Autonomous University of Nuevo León high schools in Mexico exemplifies how great teachers are using iNaturalist in the classroom. Also check out this article on @craig_williams work using iNaturalist to build curricula around mosquito monitoring in Australia and this article on @ptimmldne use of iNaturalist with students in Nebraska.

iNatters in the News

This month, we featured spider researcher @ajott in an identifier profile. We loved this profile on ecology professor and bird photographer @phylogenomics. Check out this article on scientist and prolific iNaturalist identifier @cehmoth’s work to catalog moths in Montana. This profile highlights Native Bee Society of BC's Bee Tracker creator @beespeaker’s work helping pollinators. This article highlights @jlmason’s work conserving the Ontario Carp Barrens, and this article summarizes a talk by @danbachalis about surveying species in Hammonton, New Jersey.

Thank you to everyone who participated in iNaturalist this October! Your support makes it all possible.

Donate to iNaturalist

This is the twentieth entry in an ongoing monthly (or almost monthly!) series profiling the amazing identifiers of iNaturalist.

“I was always fascinated by how things work and wanted to get to the bottom of things,” Dr. Anja Junghanns recalls when describing her childhood in Germany. 

When I was maybe 5 or 6 I was sure I was the first person to realize where mosquitoes come from. I had found some small wiggly critters in the rain barrel in our backyard and decided I needed to take a closer look, so I put them in jars and other translucent containers to observe them. I soon realized that they would change at some point into what my childish imagination termed “waterponies” (pupae) and was rather surprised to find mosquitoes later on in those closed containers. When I at some point was able to observe how one of those “waterponies” released a mosquito to the world I was in total awe (and maybe a bit disappointed to later find out that this was already common knowledge).

She’d also smash rocks with hammers to get at what was inside them (with protective goggles on, of course), consume nature documentaries, and was especially fascinated with arthropods and herps. “I was always especially interested in the parts of nature I had the least information about,” she explains.

Since joining iNaturalist a few years ago, Anja has identified over 76k spider observations, but says that “As an arachnophobic, diving into the spider world was actually a last resort for me.” She resided in a cool garden shed, but the downside is that it attracted “masses of large and hairy spiders each autumn and spring.” Feeling like she might have to move out due to the arachnids, she photographed these two spiders in 2010 and tried to identify them.

I still recall how disgusted I was by it and at the same time fascinated. It was also the moment I realized that it was easier for me to deal with spiders looking through the viewfinder of a camera.

I learned that the hunting spider in this observation (Scotophaeus) was actually my friend and would hunt down those huge hairy ones that I so despised. So I tried to learn to tolerate them. And it was all a slippery slope from there. I found more and more species in my tiny house and learned about their amazing hunting skills (Ero spiders, which while tiny are also spider hunters), their somehow lovely maternal behaviors (a lot of spider moms will protect their breed until death) and their impressive senses and other curiosities (like many spider males being basically mating machines only, often losing interest in basic surviving mechanisms like feeding).

So in 2012 she decided to study spiders for her thesis and ended up researching matriphagy in Stegodyphus spiders, along with some Danish and Israeli specialists. 

Matriphagy means that a spider mom will be eaten by her young before they disperse from their nest - a rather extreme and deadly behavior for the spider mom to secure their babies survival .. and which is connected to the extremely rare and therefore especially interesting case of social evolution in spiders (only about 25 spider species of about 55,000 known species today can be termed “social”). During my PhD I dug deeper and deeper into this topic which culminated into my thesis on “Evolution of Sociality: mechanisms and dynamics of social behavior in spiders”. To this day I am still in love with Stegodyphus spiders.

Anja and her partner have, for several years now, been living in different parts of the world and that included Ecuador in 2020, which is when she joined iNat because she wanted to learn about the unfamiliar wildlife she was encountering there. She initially started identifying observations here as a way of giving back to the community.

Websites like this do not function well if everybody just wants to get something out of it but not give back. It is basically how I learned to use and participate on the internet very early on…So the first months and years on iNat I tried to at least do 3 identifications for every observation I put on here. My interest in identifying spiked significantly since last year, as living in Bogotá does not allow me to take my camera out every day and observe a lot (for safety reasons and also as the capital itself is surprisingly low on insects unfortunately.). So identifying increasingly became an outlet to stay connected to nature. And I quickly started to fall in love with the dedicated, helpful and interactive spider identifier community here. Now identifying is a means for me to relax, connect and learn.

Having such a mobile lifestyle means that Anja doesn’t have a lot of physical references, so she generally uses online ones. 

For European spiders and their distribution there are some great websites I use to get species lists first (e.g. https://wiki.arages.de/ and https://araneae.nmbe.ch). The best source of spider information for worldwide endeavors is the World Spider Catalog. However, one needs to already have at least a bit of a clue about what genus one is interested in and can check distribution of individual species and scientific source material from there. When diving into a new taxa I will always try to go back to the scientific papers published on the taxa from there and will often through references in said papers dive deeper and deeper until I get a good understanding about how to distinguish a certain taxa or what other similar species to be aware of.

When I identify I will check my “usual suspects” (Stegodyphus, Argiope worldwide, Pisaurids in Europe and North America) first to keep up with them. If I still have more drive to ID after that, I decide what I am most interested in that day. Sometimes I pick a certain species in a certain place and will work through the “Needs ID” observations. Other times I feel like I want to push some of my own “needs ID” observations further and will dig into the topic of a certain taxon.. usually also ending up IDing for others, when I find out more about them. Sometimes I will quick and dirty go through Araneae worldwide and will often just be able to put it to family, sometimes genus. I enjoy how those “mental trips around the world” show me the amazing variety of our eight-legged friends.

Anja’s advice for taking spider photos:

Observing spiders can often be a bit disappointing, as it is often hard or impossible to ID them to species with typical observation photos. Many species (especially in many non-web building spiders) have sister species with near identical characteristics and can only be distinguished by observing the genital features as well - which is often impractical or impossible in the field. However, for cobweb builders I would always try to get a good shot from the ventral and dorsal side if possible. If you are lucky, the ventral shot is good enough to examine important features of the epigyne (the female genital region). Sometimes being able to clearly see certain hairs and bristles on the legs and palps of the spiders can make the difference between being able to go to species or having to stick with genus or complex. Habitat can also be an important information in some species. So taking some time to either take a photo that includes the habitat or give a description of it might make a difference (e.g. moist or try, forest or meadow, wilderness or around the house...)

Generally, I would advocate for a more relaxed approach to spider IDs.. it is fine to stick with genus sometimes and a lot of my own spider observation will never go to species ID as well.

Aaand some of Anja’s favorite spider taxa and observations:

• Stegodyphus spiders are just amazing. The South African Stegdyphus dumicola is one of only 20-something social spider species (out of more than 50,000 known spiders species so far) that live and hunt cooperatively.. those observations shows a nice aspect of it, where those relatively small spiders are able to overwhelm large or dangerous prey together: https://www.inaturalist.org/observations/9319352,  https://www.inaturalist.org/observations/71788845,  https://www.inaturalist.org/observations/106786957 
• Spiders are also amazing at camouflage, which I always find very impressive, like camouflaging as bark, as parts of flowers, or bird poo. 
• I also admire their hunting methods from mimicking their own prey to hunting by swinging a glue drop to catch insects.- Some are just objectively beautiful: https://www.inaturalist.org/observations/37680242, https://www.inaturalist.org/observations/50496754,  https://www.inaturalist.org/observations/172517230,  https://www.inaturalist.org/observations?place_id=any&taxon_id=333585

- the first identifier profile was of @naufalurfi, another spider identifier!

- iNat was recently mentioned a few times in this article about the importance of documenting spiders, and how doing so can help people appreciate and like them more.

Our Observation of the Week is this Holacanthella paucispinosa springtail, seen in New Zealand (Aotearoa) by @frankashwood!

“I became interested in nature as a young child – some of my earliest memories are turning over rocks in the garden and my mum explaining to me what all the different invertebrates were,” recalls Frank Ashwood. 

So, it’s a childhood dream come true that I now work as a professional soil ecologist and hobbyist macrophotographer, spending my days researching and photographing all those same animals that once fascinated me as a child. Fortunately for me, I recently moved to New Zealand, where there’s some of the most spectacular soil invertebrates in the world – particularly the giant springtails!

A few weeks ago, Frank participated in an event organized by the University of Canterbury, held at the Cass Mountain Research Area.

I knew H. paucispinosa was in the general area thanks to a colleague previously finding one nearby (shoutout to @fuligogirl on iNaturalist), so I was on high alert for it while turning over deadwood for invertebrates. However, a whole morning passed without finding one, and just as I was about to give up hope, I turned over the right log and found a pair of them huddled together! This is one of the five species of Holacanthella endemic to New Zealand, and they’re not only incredible creatures to look at, but are also important decomposers of decaying wood in native beech forests.

While they do have six legs, springtails are not considered insects. They instead belong to a separate subclass of hexapods, and lack the external mouthparts which insects have. Most springtails have a furcula, an abdominal appendage which can be released with great force, propelling the animal into the air when it needs to escape a predator. Most springtails are shorter than 6mm in length, but members of Holacanthella can be 17mm long - truly enormous (relatively).

"I only started using iNaturalist a couple of months ago, when I moved to New Zealand from the UK," says Frank (above). 

It’s very popular with the naturalist community here, so I decided to give it a try. I’ve found the app’s community-based approach to identification has helped me learn native species ID much faster than if I’d had to start from scratch. It’s also given me greater confidence in recording organisms outside of my usual areas of expertise, as I don’t have to know the exact species to still make a useful biological observation.

(Photo of Frank by Ian Dickie)

- David Attenborough and the BBC crew have some sweet footage of springtails hopping, among other activities.

- springtails come in all shapes and sizes, take a look at the most-faved observations of them on iNat!

We released a new computer vision model today. It has 80,962 taxa, up from 79,797. This new model (v2.8) was trained on data exported on September 17th and added 1,785 new taxa. We’re celebrating crossing this 80,000 taxa milestone with a conversation with iNaturalist machine learning lead Alex Shepard.

Alex, you’ve been with iNaturalist since 2014. How did you first get interested in computers?

I have an undergraduate degree in history and a masters degree in fine art, but I come from a family that worked for Apple. So as a kid, I always had access to computers. I taught myself how to program as a kid not because I wanted a career as an engineer but because I’ve always been around and love computers. I’ve always found this stuff to be fascinating.

How did you first get iNaturalist involved with machine learning and computer vision?

I was excited for a long time about some kind of statistic or tool to help the community make identifications. We had a tool called the Identotron that let you choose species based on things like color and location - a sort of primitive trait based matching. I was looking for ways to improve that and was coming up with pretty dumb approaches. For example, I was looking into clustering the kinds of species people were seeing to try to predict what they might find next. Around 2016, there were these breakthroughs in computer vision that caught my attention. Before that, there were models that could do things like recognizing hand-drawn digits - very simple recognition tasks like that - or could recognize the same face from the exact same pose, but they couldn’t recognize that face from other angles. Deep Convolutional Nets were the first kinds of models that could do that.

How did you go from those explorations to iNaturalist releasing its first computer vision model?

There were a lot of things that fell into place at the right time. People were just coming out with open source tools to help build on these Deep Convolutional Nets that I had access to experiment with. At the same time, NVIDIA very generously donated a GPU that we could use to train models beyond the experimental proof of concept phase. We also met Grant Van Horn and colleagues at Visipedia who brought a huge wealth of formal background in machine learning and statistics. Beyond the fact that we trained our early models on their code, their help and all the things they were able to teach us was invaluable - ranging from how to train out full models to training models with performance and at scale, to how to pick the right photos, to how to know when we’re done training, all those things.

How have these machine learning tools integrated into the iNaturalist community and platform?

We really started with the goal of easing the burden on the community identifying all these photographs. As a tool, computer vision gives the identifier a great starting place that’s a good ballpark. On the other hand, the model often makes predictions that aren’t correct. It’s just meant to be suggestions, but it does enter the whole conversation about things like data quality. This is an ongoing challenge for us. I think iNaturalist data quality continues to be really good on the whole, but we have to be vigilant about data quality and how the Computer Vision Model feeds into that.

What are we not currently doing that you’re excited about?

There’s a bunch of technical things that I’m excited about and want to get to but we haven’t yet. For example, I think bounding boxes could really help improve accuracy and there’s interesting roles for the community to help us do that well. I’m really interested in model explainability. For example, can a model not just suggest what’s in the photo but tell you why? And I’m always interested in finding ways to help improve accuracy of our models and improve the speed at which we train. Our dataset size is growing rapidly so we have to keep finding ways to increase our capacity to train, ranging from tweaking what we have and exploring entirely different kinds of training architectures. I’m interested in how the Computer Vision Model and the Geomodel can better work together to offer suggestions. Likewise, can we model other parts of iNaturalist in ways that help us better understand iNaturalist or help us understand species in ways that make the platform more engaging? Lastly, I’m interested in these models teaching us new things, so we’re not just using the model to represent or synthesize human knowledge already in the community but using these models to actually teach us something new about the natural world.

The model released today has over 80,000 taxa, how has the model grown over time?

Our first model was released in 2017 and had about 13,000 species in it. In 2019, we had a Microsoft AI for Earth grant to make improvements to how we made predictions up and down the taxonomy. This is the model that we used when we released the Seek in-camera suggestions. In 2021, we got an Amazon Machine Learning Research Award and used this opportunity to figure out how to speed up training time to reduce turnaround time to get new information from the community reflected in the model. The first model using this approach in 2022 (1.0) had 55 thousand taxa. Since then in monthly model releases we’ve been adding 1 to 2 thousand species each time leading up to today's model with over 80 thousand taxa. We’ve been training all of these models off of donated NVIDIA GPUs. Thank you NVIDIA!

Is this sustainable?

Good question. If you think about the model as a dice where there’s some probability associated with each side, we now have an 80 thousand sided dice. Every time we add a side it’s slightly harder to get the right answer just because there’s more choices. I’m really proud of the fact that we’ve been able to keep accuracy high despite adding so many new choices. I think this has a lot to do with the high quality of the iNaturalist data we’re training on. But we don’t know if there are limits we will hit down the road. We’re constantly working to squeeze a bit of accuracy out of the model or shave some time off of training runs. We’re definitely reaching the limits of our current set of hardware. There’s always work to do.

Final thoughts?

Sometimes we talk about adding taxa to the model as adding rarer and rarer species, but I like to think of this as adding common species from increasingly overlooked parts of the globe. This makes me happy because I know as the model grows we’re making iNaturalist more useful and available to more and more people from around the world.

On that note, here is a sample of new species added to v2.8!

• Amphibia
• Insecta
• Plantae
• Aves
• Fungi
• Mammalia
• Arachnida
• Actinopterygii
• Chromista
• Other Animalia
• Mollusca
• Reptilia

Our Observation of the Week is this Fungus Root plant (Balanophora fungosa), seen in Australia by @donalddavesne!

“I stumbled on this strange Balanophora plant while on a hike in Far Northern Queensland, where I was traveling for a scientific conference,” says Donald Davesne, who’s currently working as an evolutionary biologist with the Museum für Naturkunde in Berlin and the Muséum national d'Histoire naturelle in Paris. 

My first thought was that it was a mushroom, but looking more closely I quickly realized the presence of flower parts and leaves. The thing lacks any green, which explains why it could be hard to recognize it as a flowering plant. I deduced this is because this plant functions the same way as the broomrapes (Orobanchaceae) that I knew from my home continent. It is a parasite that feeds on other plants and lost the ability to produce its own energy through photosynthesis.

As an evolutionary biologist, I was thrilled!

If you take a close look at fungus root plants (and yes, they do parasitize other plants), you’ll see that there are two types of flowers. The rounded top part is covered in tiny, tiny female flowers, and the larger male flowers grow near the base. The flowers emit a “mousy” smell which seems to attract all sorts of pollinators, from insects to rats. Several insects use parts of the plant as breeding chambers.

Donald (above), who’s studying the evolution of teleost fishes, says he’s always been interested in nature but his experience as a field naturalist is somewhat limited and mostly came via the Timarcha Association when he was a student in Paris. That’s changing, however. 

I started using iNaturalist right after the first COVID lockdowns in 2020, though, and haven't stopped since. Using my camera to document everything I see, and putting observations on the website made me learn so much, not only on the organisms I am most familiar with (vertebrates) but also on other stuff like plants.

(Photo of Donald by Julien Guibert-Peeters. Some quotes have been lightly edited for clarity)

- you can follow Donald on X/Twitter, and check out a bio and list of publications here.

iNaturalist works best as a tool for helping people collaborate around species identification when there is clarity about the taxonomy everyone is referring to. This also makes it easier for iNaturalist curators to maintain the iNaturalist taxonomy when it's clear what direction they should be curating in. Five years ago we introduced Taxon Frameworks as a tool to help provide this clarity by explicitly referencing taxa on iNaturalist to external taxonomic references.

Since then, the number of Taxon Frameworks with external references has increased. The World Registry of Marine Species is now being used for nearly all Animal Phyla outside of Arthropods and Chordates. All Chordate taxa are linked to references such as the Reptile Database and Catalog of Fishes. Plants of the World Online is the reference for Vascular Plants. We still have no taxonomic references for Kingdoms such as Fungi and Chromista.

For Arthropoda, the vast majority of groups lack references. But most of the few arthropod groups we did have references for such as Mantids and Phasmids were referencing the Species File Group. This month, the Species File Group migrated to a new system known as Taxon Works. As a result, we were able to rewire these taxon frameworks up to their new home and add a few more branches on Taxon Works such as Harvestmen, Grasshoppers, and True Hoppers.

The pie chart below shows these taxonomic groups by percent of observations. 68% of these observations (colored areas) now have taxonomic references. This is thanks in part to complete coverage of Vascular Plants (green - 39%) and Chordates (blue - 20%). Of the other large group, Arthropods (24%), only 23% have references. The 3 large insect orders Lepidoptera, Coleoptera, and Hymenoptera account for most of these Arthropod gaps. At 6%, Fungi is the other large gap in taxonomic coverage.

We’re very excited that Taxon Works is providing a platform that makes it easier for taxonomic providers like the Species File Group to maintain and share their taxonomies. We hope these tools will facilitate progress filling gaps like Lepidoptera and Fungi in the coming years. iNaturalist derives huge benefit from access to well maintained global taxonomies. Our sincere thanks go to those maintaining the taxonomies the Taxon Frameworks depend on such as:

Chordates

• Eschmeyer's Catalog of Fishes
• Reptile Database
• Amphibian Species of the World
• Clements Checklist
• ASM Mammal Diversity Database

Arthropods

• Species File Group "Small Insect Orders" *
• World Odonata List *
• World Catalogue of Opiliones *
• Universal Chalcidoidea Database *
• World Auchenorrhyncha Database *
• World Spider Catalog
• ChiloBase

Other Animals

• World Register of Marine Species (WoRMS)

Vascular Plants

• Plants of the World Online

*Managed in an instance of TaxonWorks