Our Observation of the Week is the first Protoglomeris vasconia pill millipede posted to iNat! Seen in France by @ldvn. 

Ludivine Lamare, a twenty-one year-old French biology student who identifies as a transgender woman, grew up tidepooling and insect hunting and has always had an interest in nature. First marine life, and now terrestrial arthropods.

I've only started photographing the world around me in the middle of the Covid lockdown in summer 2020. Back then, I wouldn't even think about picking up photography as a hobby and yet... I started using iNaturalist pretty much at the same time, focusing on “easier” targets such as odonates. Today, my two biggest interests are harvestmen (Opiliones) and spiders.

Last month, Ludivine journeyed from her current base in Limoges, France, to the French Pyrenees mountains and went looking for harvestmen. After scouting a tunnel when she arrived, she returned to it at night, looking for Ischyropsalis luteipes and Sabacon.

Unfortunately I didn't find any, but while prospecting, amidst the countless Meta menardi and Nesticus cellulanus watching me from every angle, I saw an unusual pill millipede which first struck me by how big it was (by European pill millipedes standards I must add).

But no matter how strong my arachnid fever may be, I never turn down a nice millipede. I was frankly quite surprised later on when I found that it was the first observation of this (rather conspicuous) species on the site, though some others already existed elsewhere on forums and databases. Especially as it wasn't very hard to ID.

As you might suspect from their common name, pill millipedes are millipedes that can roll up into a defensive ball shape, much like pill woodlice (which are isopods). “It feels like pill millipedes and Myriapoda as a whole suffer from a lack of representation. Because even though Protoglomeris vasconica may have a relatively narrow distribution, it doesn't seem to be particularly rare nor well hidden when it is present.” Like many other millipedes, they’re detritivores and can exude a gnarly fluid when threatened. 

“When I started using iNaturalist two years ago, it was merely a way for me to have my personal gallery of ‘things I observed,’” says Ludivine, “but now I find it a very engaging way to generate data.”

I like how I am able to share valuable illustration photos of overlooked species, and how accessible those documents can be to any other naturalist worldwide, experts and hobbyists alike. Going forward, I'd love to continue documenting “the forgotten ones” now that I'll soon have access to my own stereomicroscope. And I plan on starting speleology at some point. Some very interesting harvestmen are entirely troglobitic and I'd love to help shed light on those even a tiny bit. This specimen of Ischyropsalis pyrenaea, for example, was the culminating point of my vacation, and the first record on iNaturalist as well!

For now I've been talking mostly as someone who posts observations on here but since I also started helping with IDs, I must say conversing with experts and enthusiasts is very convenient on iNaturalist. And while I did most of the learning on other sites and forums, it has been a really good starting point. Encouraging more people to help with IDs and care about the quality of the data is important especially in the context of citizen-science projects like this where ID mistakes are to be expected.

- As Ludivine hinted at, European pill millipedes (as well as others in the northern hemisphere) are relatively small compared to pill millipedes in the southern hemisphere. About four years ago, one of those giant pill millipedes was an Observation of the Week!

- Here’s a short video with some pill millipede facts.

Our Observation of the Week is this Spiny Moleroman (Genus Chelypus), seen in South Africa by @rachel_grace!

“I remember when visiting Kruger [National Park] we stopped for a long line of Processionary Moth caterpillars crossing the road, which other cars passing by didn't seem to understand,” recalls Rachel Scharf, describing a family trip. “I'd love for people to notice the smaller animals as much as the bigger ones too.”

Well, on a visit to Kgalagadi Transfrontier Park in April, that’s exactly what Rachel and her companions did!

When we saw this Spiny Moleroman in the Kalahari we were just leaving the Kalahari Tented Camp where we had stayed the night. It was midday and quite hot. As animal sightings are sometimes scarce in the Kgalagadi park, we've come to appreciate the smaller sightings a lot more. So when we noticed a strange something running across the dirt road, we wanted a closer look. We had never seen anything like it! That's why we enjoy coming back to visit the Kgalagadi because every time it's a different experience! After we spotted this strange creature on the move we then noticed every bird in the grass and trees nearby had noticed it too and they really wanted the tasty fast food this creature was for lunch.

Since we wanted to know what it was we didn't want it to get eaten! So we chased off the birds so we could look at it and take the shot, and then safely escorted this creature to the cover of the long grass it was trying to get to.

Like other members of the arachnid order Solifugae, spiny moleromans are not venomous nor do they make silk. They use their relatively large chelicerae (or mouthparts) for grabbing and cutting prey, such as small arthropods or vertebrates. Species in genus Chelypus have specially adapted feet for digging, and like other solifugids can run quite quickly. And while they can deliver a painful bite, they’re not considered medically significant to humans.

Rachel (above, at Professor Anne Rasa's Meerkat Sanctuary) credits her mother for cultivating her childhood interest in nature, and explains that this was rekindled during the pandemic. “All that free time I had gave me the opportunity to reconnect with my love of nature even if just in my garden,” she explains and with the Caterpillar Rearing Group in Africa she starting rearing the lepidopterans in her backyard.

Because I love rearing caterpillars so much, it has opened my eyes to so much more. It led me to discovering iNaturalist and interacting with nature and the people in its community. As I would look for caterpillars and I'd find other weird and wonderful creatures I had no idea about!

I love using iNaturalist to ID all the strange creatures I come across from caterpillars to mammals to this Spiny Moleroman! It really helps me to get out of my comfort zone of Lepidoptera which I enjoy observing and helping to identify the most. The iNaturalist community of other people around the world who love nature and who are always willing to help is really wonderful! Being able to use my phone's camera for all of my observations makes it really accessible for anyone who wants to take part. I really enjoy sharing, exploring and learning with others about God's beautiful creation! :)

- Solifugids are known by many common names in English, such as wind scorpions, sun spiders, and camel spiders. Though they are arachnids, they are neither spiders nor scorpions.

- Check out some of the other cool solifugids on iNat!

- Arachnologist Dr. Paula Cushing goes over some solifugid facts during an interview with Emily Graslie in this episode of The Brain Scoop.

We’ve released a new computer vision model for iNaturalist. This is our first model update since April 2022. The iNaturalist website, mobile apps, and API are all now using this new model. Here’s what’s new and different with this change:

• It includes 60,000 taxa (up from 55,000)
• It was trained using a different approach than our previous models, which made it much faster to train

To see if a particular species is included in this model, you can look at the “About” section of its taxon page.

It’s bigger

Our previous model included 55,000 taxa and 27 million training photos. The new model was trained on over 60,000 taxa and almost 30 million training photos.

It was trained using a transfer learning strategy

During previous training runs, our strategy was to train the entire model on the dataset. This means that all of the model weights were candidates for being updated, in order to learn the most efficient and useful visual features for making suggestions for the taxa in that dataset. When training this model, we froze most of the model weights (thereby freezing the visual feature extraction) and only trained the very last layer of the model, the layer that makes the taxa suggestions. This is a machine learning strategy known as transfer learning.

One way to think about this is to imagine that someone was asked to learn all about different kinds of cars. Later, that person was asked to differentiate between two different kinds of pickup trucks, but only using distinguishing characteristics they learned from their study of cars (for example, color, size, visual shape, branding, engine size, etc), without learning anything new about pickup trucks (for example bed capacity, towing limits, etc). Chances are, that person could distinguish between most kinds of trucks without needing to learn anything new specifically about pickup trucks. They may not perform as well as someone who learned about trucks from the beginning, but they have strong foundational knowledge to draw upon for the task.

Our new model was trained using a transfer learning strategy. We used the internal weights and visual features from our previous model which was trained on 55,000 taxa. The advantage of this approach is that we didn’t need to learn all of those internal model weights and visual features again, so training was quite a bit faster. It’s only been four months since our last model was released, which is the shortest time between model releases so far.

As with the pickup truck analogy, it could be that this model trained with the transfer learning approach is slightly less accurate overall than if we had trained the entire model again. However, in our testing this new model appears to achieve nearly the same accuracy as the previous model while containing more taxa. Our plan going forward will be to spend the time fully training a model about once a year to maximize accuracy with new photos and taxa, and to use the faster transfer learning approach in between full training runs so we can release models more frequently than we have in the past.

Future work

First, we are still working on new approaches to improve suggestions by combining visual similarity and geographic nearness. We still can’t share anything concrete, but we are getting closer.

Second, we’re still working to compress these newer models for on-device use. The in-camera suggestions in Seek continue to use the older model from March 2020.

We couldn't do it without you

Thank you to everyone in the iNaturalist community who makes this work possible! Sometimes the computer vision suggestions feel like magic, but it’s truly not possible without people. None of this would work without the millions of people who have shared their observations and the knowledgeable experts who have added identifications.

In addition to adding observations and identifications, here are other ways you can help:

• Share your Machine Learning knowledge: iNaturalist’s computer vision features wouldn’t be possible without learning from many colleagues in the machine learning community. If you have machine learning expertise, these are two great ways to help:
• Participate in the annual iNaturalist challenges: Our collaborators Grant Van Horn and Oisin Mac Aodha continue to run machine learning challenges with iNaturalist data as part of the annual Computer Vision and Pattern Recognition conference. By participating you can help us all learn new techniques for improving these models.
• Start building your own model with the iNaturalist data now: If you can’t wait for the next CVPR conference, thanks to the Amazon Open Data Program you can start downloading iNaturalist data to train your own models now. Please share with us what you’ve learned by contributing to iNaturalist on Github.
• Donate to iNaturalist: For the rest of us, you can help by donating! Your donations help offset the substantial staff and infrastructure costs associated with training, evaluating, and deploying model updates. Thank you for your support!

Our Observation of the Week is this Loasa tricolor plant, seen in Chile by @rocio-rmrz!

Currently an undergraduate biology student at the National Autonomous University of Mexico, Rocío Ramírez recently spent a few months in Chile for a research trip, learning forestry engineering field skills. As part of the program, they visited Canelo-Canelillo Park in Valparaiso, along the coast. 

I remember we were walking along the shoreline of the beach when someone yelled “look at the Loasa!” There were some stinging weeds that didn't seem very showy, but when I turned over the flower (which usually faces down) I saw strikingly beautiful petals with a characteristic morphology. At that moment it only occurred to me to take a photo with my cell phone because I didn't have something to position the flower for a good photo, however I knew we were going to return and I had to take a good photo there. 

We came back a few days later and a few meters from the Puyas (Puya chilensis) there was another small population of Loasa tricolor and now I was ready to take a good photo. I took out my camera and macro flash and, using a napkin, I put the flower in a better position and took several photos, trying to get a good shot of the details. Despite the napkin, I got irritated by the stinging hairs a couple of times but I think it was worth it. 

As Rocío mentioned, species in this genus have stinging hairs, similar to nettles. And in addition to being showy, the flowers are anatomically quite special.

Dr. Paulette Naulin, was the person who invited me to the field practice, mentioned that Loasa tricolor flowers are examples of hercogamy, which is the separation of male and female structures to prevent self-pollination. This is why they have such characteristic morphology.

“Since I was little, the activity I enjoyed doing the most was playing among the wild plants outside my house,” says Rocío (above, outside of Santiago), which led her to her current focus of botany.

I really didn't know what to do until a teacher mentioned in class “study what you liked to do the most when you were little because that's what you'll do for the rest of your lives,” and that's how I decided to study biology. When I was in my third semester, I studied botany and I was amazed at the vast diversity of plants, so I decided that this was what I wanted to do for life. I am currently developing my undergraduate thesis on parasitic plants of the Orobanchaceae family in Mexico, but what I like the most is finding new species of plants that I did not know in the field. Also, thanks to my boyfriend I was introduced to the world of photography, especially macro photography, which I personally like a lot because I think it highlights all the complex and curious structures of certain species.

She joined iNaturalist (“Naturalista” in Mexico) and mostly uses it to get ID help for critters and plants she comes across, and she’s learned ranges of native plants as well.

In Mexico, Naturalista has been used so that the task force members of the Natural Protected Areas can share the species they find on their usual routes, which seems to me to be a very useful tool to broaden the knowledge of biodiversity. Something similar is being applied in Chile, where they put on a small iNaturalist workshop in which the students of the group had to upload the species they encountered during field practice.

(Rocío’s text was written in Spanish. I’ve used Google Translate and lightly edited the text for clarity.)

- @diegoalmendras took a nice close-up of Loasa hairs in this observation.

- Check out other iNat observations of this stunning genus.

On the night of August 26th (approximately 8 pm Pacific Daylight Time), a power outage impacted almost all of iNaturalist’s servers for several hours. iNaturalist rents servers from Microsoft Azure and the outage happened at Azure’s US West 2 data center.

As far as we can tell, no critical data was lost - that means photos, sound recordings, observations, identifications, projects, comments, and any other content uploaded to iNaturalist should all be there. You can read updates and discussion from the event on the iNaturalist Forum.

However, for anyone to be able to find all of the data, about a week’s worth of search indices needed to be rebuilt before we could bring iNaturalist back online, and that process - done almost entirely by @pleary - took about a day. Everything should be back as it was with the exception of notifications - some notifications generated in the past week may be lost, while others that you already viewed may appear again (we’re trying to err on the side of people getting them if they didn’t use iNat last week). In the next week we’ll be looking into how to prevent this situation from happening in the future. 

We want to thank the iNaturalist community for the support it's shown us; on the iNaturalist Forum, on Twitter, and elsewhere during the past two days (and every day, really). We’re humbled that iNaturalist is an important part of so many lives, and we’re deeply sorry it was down for this long, especially if it was during a crucial event you had planned. We’re looking forward to seeing what you observed during the downtime!