Our Observation of the Day is this Nose-horned Viper (Vipera ammodytes), seen in Kosovo by @liridonshala!

“I grew up among wonderful nature near Peja,” says Liridon Shala, “which is the most beautiful part of my country.” So he’s been interested in nature and its protection for nearly all of his life. Now, as pharmacist living the city of Prizren, he’s focused on nature photography. “With my photos, I want to show people about the beauties we have, like birds, animals, and everything that belongs to the wild world…My main goal is to document my country's species, and educate the younger generations to protect them and nature.”

A few weeks ago, Liridon and a friend traveled to Albania on a photography trip. They weren’t particularly happy with their finds, but on their way back they came across a nose-horned viper on the road. They pulled over but it took them a moment to re-find it after it slithered to some nearby stones. “Due to its camouflage, we couldn’t find it on the stones. When we did spot it, I started to take some pictures, but I was worried there might be others nearby.”

Occurring in mostly rocky habitats from Italy through the Balkans and into Turkey and Syria, nose-horned vipers are relatively large (growing up to about one meter) and their fangs can be about 13 mm in length. Adults eat mostly small mammals and birds, and younger snakes are known to eat invertebrates like centipedes. Their venom is considered medically significant to humans, but like just about any snake they prefer to warn or escape rather than bite. The “horn” on the nose is composed of scales and is reputed to be soft to the touch (but don’t try to touch it, please).

Liridon (above) joined iNat a few years ago. Not only has he added over 500 observations, he’s also part of a team that’s worked on translating it into Albanian. He mostly uses it as a personal portfolio for his photographs, and as a place to learn.

(Some quotes have been lightly edited for clarity.)

- You can check out Liridon’s photos on Instagram!

- Take a look at the most-faved observations in Kosovo!

Our Observation of the Week is this Cladonia lichen, seen in Brazil by @paularomano! 

From 2004 through 2016, Paula Romano lived in Brazil’s Itatiaia National Park, a period which she considers “the golden period of my life because I had the opportunity of observing one of the most biodiverse places in the world every day. There, I got in touch with many researchers who helped me start to understand the dynamics of a forest.”

And in 2008 she came across the remarkable lichen you see above. “Lichens always called my attention,” says Paula. 

This Cladonia was a great surprise because I had no idea it was a lichen and I had never met someone who studies them. Its shape is totally different from any plant and lichen I had ever seen. I remember that the first time I saw it I was very astonished…I wonder how it evolved to reach that form.

A few weeks ago Paula posted her photos of this lichen to iNat and they were identified by @carlosvidigal, a Brazilian lichenologist, as potentially either Cladonia calycanthoides or Cladonia imperialis (more details would be needed to say for sure). I asked Carlos, who studied Cladonia for his masters degree, for some information about these lichen.

Both species occur on highlands and rock outcrops and can reach up to 15- 30 cm tall, making them the tallest in the genus. Members of this genus occur mostly on the ground, rocks or near the ground on dead wood. 

The majority of the species are characterized by this vertical thallus, which are called podetia. There are a great range of shapes and sizes but this one specifically we call “verticillate” as the scyphi (the cup) flares from the center from another scyphi, like growing in tiers. Recent studies show that Brazil is the center of diversity of Cladonia and they are everywhere.

Paula (above, in 2009) says she’s not an academic person but is interested in many areas of nature. “My main interest (or curiosity) has always been the connection among the species and how we are dependent on them, mainly insects in general,” she says, and she’s volunteering at a community garden, documenting the various plants and animals found there. She’s also been teaching Photography and Citizen Science workshops, drawing from her experience photographing nature since 2004. 

She joined iNaturalist last year, “mainly to make my observations useful.” 

It's nonsense to have so many useless observations. I was very bothered by it. It's also a very good way to study the biodiversity I’ve been registering since 2004 when I bought my first digital camera. Each photo I take I have in mind that it must have an educational function.

I can tell you that iNaturalist is a good therapy as well. There is always a celebration in my brain when an observation is used for research.

I don´t think [iNaturalist] has changed the way I interact with or see the natural world, but it certainly has emphasized it, made it deeper and wider. Much deeper and wider. Thanks to the identifications and maps, it's possible to show people how fragile some species are. 

(Photo of Paula by Patricia Sierra)

- Nearly 200 species of Cladonia have been posted to iNat, check out the observations here.

- Until recently, lichens were thought to be the symbiotic relationship between fungi and algae. But we now know there’s a third member of this partnership.

This is the thirteenth in an ongoing monthly (or almost monthly!) series profiling the amazing identifiers of iNaturalist. With the recent addition of iNaturalist Taiwan to the iNat Network, we thought we'd profile the top identifier there.

Although he grew up in Taipei, an enormous city, Chia-Lun Hsieh (@galanhsnu)was able to explore nature quite often, thanks to his parents taking him hiking on weekends. He loved looking for bugs at a young age, but in junior high he found the first edition of “蕨類入門 (Guide to Ferns)”, written by Dr. Chen-Meng Kuo and illustrated by Mr. Kun-Mou Huang (see the revised version here). “I was totally surprised and immersed by the intricate leaf patterns of various ferns (and also lycophytes) illustrated in that book. Starting with this book, my interest gradually expanded to all kinds of plants, not only ferns but also flowering plants...I believe people can always find a new world if they look carefully into a specific group of plants.”

That interest in plants lead him to his current position as a research assistant in Dr. Kuo-Fang Chung’s lab at the Biodiversity Research Center of Academia Sinica (Taiwan). Current projects include researching the systematics of Berberidaceae, tracing the migration of Austronesian people through paper mulberry (Broussonetia papyrifera), the plastome evolution of Primulina (Gesneriaceae), Begonia, and Gentiana, and more. 

In 2018, Chia-Lun came across iNaturalist after returning from a trip to South Africa. “The diverse flora of South Africa is so fascinating but also bewildering for a newcomer like me,” he explains, and he found iNat when searching for information about Cape flora. 

After looking around the website, I soon realized that iNat is not only for South Africa or other western countries, but a worldwide platform for everyone to share observations of all kinds of organisms from any corner of the world. Meanwhile, I was very excited to find that there have also been some records and users from Taiwan on it, and my friend, Dr. Cheng-Tao Lin (@mutolisp), is the main promoter and curator for iNaturalist in Taiwan.

Now I frequently use iNaturalist for learning about the plants I don’t know through the taxon pages, which are very informative as I can get taxonomy, distribution, phenology, and image info there. With the continuous contributions from people all over the world and more carefully curated observation data, I believe iNat can be one of the most powerful and informative biodiversity databases that is universal to all countries and all categories of organisms. It is also an invaluable public science data source for all kinds of biodiversity research. I’m happy I found such a thrilling place!

In the nearly four and a half years since he joined iNaturalist, Chia-Lun has added IDs to over 222k verifiable plant observations in Taiwan alone, making him the top identifier of observations made there. He‘s constantly looking at newly uploaded observations from Taiwan (of plants and those without any IDs), and also goes through older Needs ID observations by family. He’ll also sometimes check out Research Grade observations to see if any need to be corrected, but doesn’t add agreeing IDs to existing Research Grade observations. “Additionally,” he says, “I force myself to always enter scientific names when I am making IDs for others. By doing this, I could gradually memorize more scientific names which are not frequently used in my daily life. It's very good botanical training.” 

When I asked him why he’s so keen on identifying observations on iNat, Chia-Lun, explained

I have a strong curiosity about any (Taiwanese) plant that I don’t know or I have never seen before. If I couldn’t call the name of the plant at first glance, I will try very hard to figure it out. When I reach the answer, I can get a huge sense of accomplishment. So I enjoy spending time on identification or searching and reading information about how to ID various plants… 

I [also] really appreciate iNaturalist as a platform for biodiversity data accumulation and for nature lovers all over the world to communicate and share knowledge with each other. Therefore, I am willing to contribute to iNat by improving the quality of its records. I could also benefit from this as I sometimes need to retrieve data from iNat, and I need to make sure those records are correct and ready for subsequent analyses.

iNat is a wonderful place for me to continuously practice and absorb new knowledge about various taxa. Since the beginning of my usage of iNat in 2018, I have learned so much and my plant ID skill has improved a lot as well during the process of IDing for others and communicating with other users or experts. For instance, I have acquired many updated taxonomic knowledge and identification tips of Peperomia from @guido_mathieu, Chamaesyce-type Euphorbia from @nathantaylor, Senna from @jeanphilippeb, Musa from @chris971, various Taiwanese plants from many Taiwanese users and experts, and more to be listed…

It is a delightful task when reviewing and identifying plants - as if I am meeting many old and new friends.

- You can check out Chia-Lun’s research on ORCiD.

- Some of Chia-Luns favorite references for identifying are 植物觀察資料庫 (Plant Observations Database), Plants of Taiwan, Flora of China, and various field guides to ferns and lycophytes of Taiwan.

- The photo at the top shows Chia-Lun next to a giant Chamaecyparis formosensis tree in Cinsbu, Taiwan.

iNaturalist Taiwan is the newest member of the iNaturalist Network! iNaturalistTW is a collaboration with the National Chiayi University and Taiwan Forestry Research Institute.

《愛自然·臺灣》(iNaturalist Taiwan) 是 iNaturalist 國際網路的最新成員！《愛自然·臺灣》是由國立嘉義大學與行政院農業委員會林業試驗所共同協作維運的。

Taiwan is located in the transition zone between tropical and subtropical regions of Asia. A total of 70% of the land area is covered by mountains in Taiwan, while 60% of the terrestrial area is covered by forests. Therefore, complex mountainous topography and humid climate affected by Asian monsoon cause rich habitats and high biodiversity. The logo for iNaturalist Taiwan is the Taiwan lily (Lilium formosanum A.Wallace), which is widely distributed from the seacoast to the mountain summit over 3,000 m. The Taiwan lily was chosen as the logo because the scientific name “formosanum” is from the Formosa (The first time Portuguese sailors saw Taiwan and said “Ilha formosa”, which means “a beautiful island”). It can be representative of Taiwan people’s resilience and solidarity. Some indigenous tribes, such as western Rukai people, believe that the Taiwan lily is a symbol of purity in their culture.

臺灣位於亞洲熱帶和副熱帶交界，其中大約有 70% 的土地是山地地形，而 60% 的陸域面積是由森林所覆蓋。複雜的山地地形和亞洲季風系統所帶來的潮溼氣候讓臺灣有豐富的棲地環境和極高的生物多樣性。《愛自然·臺灣》的標誌是臺灣百合(Lilium formosanum)，其廣泛分布從海邊到3000公尺高山上。我們選擇作為臺灣的代表標誌是因其學名 formosanum 是由臺灣的古名福爾摩沙(Formosa，葡萄牙水手第一次看到臺灣後，稱呼臺灣為「美麗之島(Ihla formosa!)」)而來，而臺灣百合也可以代表台灣人的堅韌與團結。有些原住民如魯凱族貴族的花飾文化視臺灣百合為純潔的象徵。

The iNaturalist community in Taiwan has been growing steadily since 2018 when Dr. Cheng-Tao Lin (@mutolisp) translated the iNaturalist website and mobile apps into Traditional Chinese. Dr. Lin is a professor at Biodiversity Research Center, Department of Biological Resources, National Chiayi University. Dr. Lin introduced iNaturalist in the courses of environmental education curriculum and engaged in promoting biodiversity citizen science projects. Recently, there are over 1.47 million observations, 30,000 observers, and 11,000 identifiers in Taiwan. Many researchers, citizen scientists, NGOs, and even government agencies use iNaturalist to explore and study Taiwan’s biodiversity and contribute biodiversity data for conservation policies. You can read more about earlier activity in Taiwan from the iNaturalist World Tour post in 2019. iNaturalistTW appreciates the contributions of many naturalists, citizen scientists, community members and especially the identifiers, such as the top identifiers @galanhsnu, @leaf0605, @jodyhsieh and @fernslu. iNaturalist Taiwan also thanks the financial support by the Taiwan Forestry Research Institute, National Science and Technology Council (MOST 110-2121-M-415-001, 111-2121-M-415-001), and Yushan National Park Headquarters.

臺灣的《愛自然》社群在林政道博士(@mutolisp)將網站和行動裝置介面翻譯成正體中文之後，從 2018 年就開始穩定成長。林政道是國立嘉義大學生物資源學系&生物多樣性中心的教授。林政道將《愛自然》引進環境教育學程中的課程，並致力於推動生物多樣性相關的公民科學專案。目前《愛自然》在臺灣有 147 萬多筆觀察紀錄、30,000 多名觀察者和 11,000 多名鑑定者。許多研究者、公民科學家和 NGO 團體，甚至是政府單位使用《愛自然》來探索與學習生物多樣性，並貢獻這些生物多樣性的資料於保育政策上。您可以閱讀 2019 年的這篇《愛自然世界之旅》 介紹來了解更多早期發展的相關細節。《愛自然·臺灣》非常感謝眾多公民科學家、社群成員與熱心的鑑定者，特別是 @galanhsnu, @leaf0605, @jodyhsieh, @fernslu 等協助鑑定，也感謝林業試驗所、國家科學及技術委員會(補助計畫編號：MOST 110-2121-M-415-001, 111-2121-M-415-001)和玉山國家公園管理處提供經費上的補助。

About the iNaturalist Network

The iNaturalist Network now has twenty localized sites that are fully connected and interoperable with the global iNaturalist site. Any iNaturalist user can log in on any of the sites using their same username and password and will see the same notifications. All data from all network sites are still shared globally and fully accessible from each site using search filters.

關於 《愛自然》國際網路
《愛自然》國際網路(iNaturalist Network)目前有 20 個在地化的網站，它們與全球的《愛自然》網站相連結與共同維運。任何一個《愛自然》的使用者都可以使用相同的帳號和密碼登入至任一網站，也會看到相同的通知。所有的網站資料仍會在全域中共享，並可以從每個網站使用搜尋篩選來存取所有資料。

The iNaturalist Network model allows for localizing the iNaturalist experience to better support regional communities and local leadership, without splitting the community into isolated sites. The iNaturalist team is grateful to the outreach, training, translations, and user support carried out through the efforts of the iNaturalist Network member institutions.

《愛自然》國際網路的模式讓 《愛自然》的經驗可在地化，以便在各國範圍內提供更好的社群支援和在地化管理，而不用把社群切分成各個孤立的地點。《愛自然》團隊非常感謝透過《愛自然》國際網路成員機構的努力來推廣、培訓、翻譯和提供使用者支援。

We would like to invite anyone from Taiwan to affiliate their account with iNaturalistTW!

我們想邀請臺灣的每個人來將您的帳號加入至 《愛自然·臺灣》中！

Our Observation of the Day is this Asterella drummondii liverwort, seen in Australia by @knicolson!

Ah, liverworts. They are small non-vascular terrestrial plants, but I think in general people are less familiar with them than they are with mosses, another large group of non-vascular plants. However, Australian botanist Kym Nicolson is a fan. “Small is beautiful,” he says. “I have had a fascination with small ephemeral plants for many years. The small often non-colourful, non-spectacular plants that you can’t see unless you get down on your hands and knees, with your face close to the ground. The things you don’t see when walking. You have to stop and look.”

Earlier this month, Kym visited Belair National Park, outside of Adelaide, to test a new camera.  

As it had been a wet spring, there were patches of moss and small ephemerals.  I was photographing some very small Centrolepis plants and then realised alongside was a miniature forest of fruiting bodies of the liverwort Asterella drummondii, which I then also proceeded to photograph. I have only seen these fruiting bodies a couple of times before and only once in this National Park. Liverworts are often overlooked due to their size.

It's a challenge photographing such small objects and I like to place the camera on the ground on a small beanbag to get a lateral view rather than photograph from above. The photos often show detail you can't see by just looking.

One of the advantages of getting close to the ground is you see a whole world of biodiversity you did not know existed. Tiny spiders, mites, ants and an array of other insects. I recently saw a peacock spider and am now trying to resist the temptation to get interested in the Salticidae.

As Kym noted above, his photograph shows the fruiting body Asterella drummondii. When looked at from above, you’ll see they generally have a single long thallus from which the fruiting body emerges.

Kym (above) says he’s had a lifelong interest in plants, which motivated him to earn a PhD in Botany at the University of Adelaide. 

For years I photographed and identified plants for my own personal interest, just as a hobby. The advent of iNaturalist has provided a purpose and a repository for my observations. I see myself as a contributor to iNaturalist rather than an end user of the observational data. A citizen scientist contributing observational data on our valuable biodiversity.

I have a particular interest in grasses and the Australian Chenopodiaceae (now placed in the Amarathaceae) and take every opportunity to try and photograph species I haven't previously seen and add them to iNaturalist.

- The iNat community has posted over 100,000 liverwort observations, check them out!

- Gardening Australia’s got this nice video about non-vascular plants.

Our Observation of the Week is this trio of Predatory Fungus Gnats (in the genus Heteropterna), seen in Singapore by @airgel!

In early August, Sam (@airgel) and some nature guides went for a night walk on a dirt road named Track 15. “It's quite a popular spot for night walks here in Singapore,” says Sam.

I spotted these flies (presumably) sleeping, hanging from this strand of silk - like tiny line dancers! I called my friends over to take a look - but after just three shots they had disappeared. I feel kinda bad for waking them up, but if the picture can be used to educate and contribute to research, I suppose it's worth it. I was also fortunate enough to have the shots in focus - being able to make out wing venation is really important for identifying a whole host of insects.

When I uploaded the photo as an observation, I had no idea what type of fly I had seen. Next thing I knew, it was Observation of the Day and the identifications started coming in! I'm humbled and grateful for everyone's help with identifying these gnats.

As you’d suspect from their common name, predatory fungus gnats (Family Keroplatidae) can feed on both fungi and other animals during their larval stage. According to BugGuide

they spin hygroscopic webs to collect spores or small invertebrate prey. Predaceous species kill their prey with an acid fluid (mostly oxalic acid) secreted by labial glands and deposited in the droplets of their web; mycophagous larvae also have acid webs and occasionally feed on pupae of their own species or on dead insects. 

iNat user @treegrow suspects that the trio Sam photographed, which appear to be males, are hanging on spider silk and are likely looking for receptive females.

In addition to the gnats, Sam also saw his first Cyrtarachne bird dropping mimic spider and Bipalium hammerhead flatworms that night.

While Sam (above) has always been into nature (“there are pictures of me as a toddler staring at ants on the ground”), he credits his first macro lens as the impetus for his “deep dive” into the natural world. 

As I started looking for subjects to photograph, I learnt more and more and fell ever deeper in love with nature. My interests broadened when I got involved with a group of nature guides in my university - I started learning more and getting more into the conservation and outreach side of things. But my focus will always be my first love - inverts! I study aerospace engineering, but hope to contribute to research efforts some day - I still have a lot to learn!

He says that for about two years his photos mostly lived on his hard drive but a persistent friend finally persuaded him to start posting his photos to iNat this year.

It's been awesome! With iNaturalist, I've been able to learn so much more about the life I photograph. I especially love it when the experts come in and have discussions in the comments, on top of providing identifications. I think that's where the greatest potential for learning lies for me!

I think iNaturalist has also shaped the direction of my photography. On top of thinking about things like colour, composition and ethics, I've started thinking - how can I get the most scientifically useful and accurate shot? For instance, I've come to prefer shooting the dorsal view of jumping spiders instead of the classic anterior face-on view, because I find dorsal views more useful in identification. And the more identifiable something is, the more useful the observation.

I also think iNaturalist has broadened my focus. I've recently started to take more notice of plants, and although I have next to no relevant knowledge, the wonderful local identifiers have made it really easy to learn more.

(Photo of Sam by @phoebezhouhuixin.)

- You can follow Sam on Instagram here.

- Perhaps the most famous member of Family Keroplatidae is the New Zealand Glowworm. Check out PBS Deep Look’s video about them.

It’s September, 2022, and we’ve released a new computer vision model for iNaturalist. This follows updates in August and April 2022. The iNaturalist website, iNaturalist mobile apps, and API are all now using this new model. Here’s what’s new and different with this change:

• It includes 65,000 taxa (up from 60,000)
• It is the second model to be trained in our new, faster approach

Taxa differences to previous model

There are 5,811 taxa in the new model (v1.2) that weren’t in the old model (v1.1).

4,717 of those represent newly added choices. For example, of the 3 species of Carpillus, the old model only included Spotted Reef Crab and Convex Crab whereas the new model also includes Batwing Coral Crab.

907 of those taxa represent more refined replacements. For example, the old model included the Crestless Curassow genus Mitu which contains 4 species of birds. None of these species had enough photographs to be included in the model. The new model includes the species Razor-billed Curassow as a more refined replacement for Mitu. Because genus Mitu was replaced by Razor-billed Curassow, the number of choices was not increased by this refinement.

Lastly, 187 of thetaxa in the new model but not in the old model result from taxon changes. For example, in the old model Wedge-rumped Storm-Petrel was represented by the taxon Oceanodroma tethys, but due to a taxon change the new model has replaced that taxon with Hydrobates tethys. This is the same species but in a different genus so again the number of choices was not increased by this refinement.

There were also 1,165 species in the old model which are not in the new model. 31 of these were lost because of a decrease in the amount of data. For example, the old model included 2 species of genus Aplysilla, Encrusting Rose Sponge (Aplysilla rosea) and Aplysilla glacialis. However, due to new identifications added by the community, many of the observations that were identified as Encrusting Rose Sponge now represent other taxa. As a result, the new model no longer includes this taxon as a node.

As described above, there are also taxa in the older model not in the newer model because they were refined (e.g. genus Mitu) or because they were the inputs of taxon changes (e.g. Oceanodroma tethys)

The charts below summarize these taxa. We can use these categories to filter out just this set of 4,717 new taxa added to the new model that aren’t the result of refinements or taxon changes.

By category, most of these 4,717 new taxa were insects and plants.

Here are species level examples of new species added for each category:

• Other Animalia
• Mollusca
• Plantae (sample of 200)
• Amphibia
• Protozoa
• Mammalia
• Actinopterygii
• Insecta (sample of 200)
• Chromista
• Arachnida
• Aves
• Fungi
• Reptilia

Click on the links to see these taxa in the Explore page to see these samples rendered as species lists.

You can find an entire list of all the species added to the new model here.

Remember, to see if a particular species is included in the currently live computer vision model, you can look at the “About” section of its taxon page.

This is our new vision model release tempo

Our previous goal for releasing models was twice a year, and we struggled to even meet that. However, with the new transfer learning approach that vastly speeds up training, we now plan to release a model every month, with the caveat that our schedule could grow longer as the number of photos continues to grow. This means that there will be much less taxonomic drift between the taxonomy that the model knows about and the taxonomy at the time the model is showing suggestions to a user.

We will still be training a full model once or twice a year, which we’ll then do transfer learning from in order to make release models. Extra hardware provided by NVIDIA and donations from the iNat community have made it possible to have a training strategy that combines both full model training and transfer learning.

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!

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!

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.

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!