Our Observation of the Week is this Ixorida philippinensis beetle, seen in The Philippines by @mrkbu!

“I am a digital artist by profession and currently trying to be a gardener and beekeeper,” Mark Bulahao tells me. 

My earliest focus was ants but my first real obsession was termites. iNaturalist, however, expanded my interests into groups that I was only mildly interested in before and others that I never thought I'd get into, like planthoppers, leafhoppers, earwigs, pygmy grasshoppers, fungus weevils, soldier and signal flies, curved-horn moths and who knows what's next. Sometimes I dread what new distraction I might fall into.

While at a swimming pool with some family and friends, Mark noticed a black spot on a plant. 

I quickly took out my phone and was thrilled by a beetle I've never seen before. Its patterns were striking and probably the most memorable thing about it, but beyond those were the interesting forms of the elytra and my favorite is the shapes on the face. I think it's a spillover from my enthusiasm for termites since the shape of the soldier's head and mandibles are the most diverse and diagnostic traits. For me the forms on the head alone can mean the difference between a nice species and the best species ever.

It's far from the biggest beetle but it wasn't tiny either and its markings are conspicuous, so I was surprised when I realised it was one of only a few observations on iNaturalist. For a creature that seems to want to be seen and isn't restricted to remote primeval forests, I expected there would be more.

Ixorida philippinensis is a member of the subfamily Cetoniinae, known as fruit and flower chafers in English. Adult beetles in this family often eat pollen and nectar from flowers, or sometimes nosh on flower petals and other parts of a plant. 

“Despite being into insects,” says Mark (below( 

I've never heard of the common name "flower chafer" before, so it reminded me that even in familiar settings there are more than a lifetime's worth of fascinating things to discover. But it's also a reminder that if even stylish creatures get under-observed and understudied (if it's an invertebrate, not economically important and lives in the tropics, I always assume it's understudied), then how about the more obscure organisms? Thoughts like this often lead me to more thoughts on shadow diversity, dark extinction, and the imperiled field of taxonomy.

The merits of iNaturalist are well known so I'd like to add a possible benefit that's only been alluded to and that is its potential to help with the Taxonomic Impediment, a crisis that gets discussed and or even mentioned far less than it should be. It's hard to notice this crisis when you're focused on charismatic wildlife, but you'll feel it when you're into the less popular lifeforms, and on top of that, if you observe in more biodiverse but less studied regions, you'll really feel it. I often lurk on iNat forums and the community is keenly aware of the shortage of identifiers and I believe this is just an extension of the Taxonomic Impediment. With all the amazing identifiers already active on iNat, it can blind one from the fact that scientists themselves have called taxonomists an endangered species, but iNat might be an additional breeding ground for future taxonomists and parataxonomists who may fill in the numerous gaps in a branch of science that often feels like a continent of ghost towns and underpopulated villages where the sheriffs are an underappreciated and aging workforce.

This might be too optimistic as it seems the majority of personalities that iNaturalist tends to attract are in it largely due to how fun it is and becoming a taxonomist involves work that most would consider less fun. Even I, who is seriously considering becoming an amateur taxonomist or parataxonomist when time and resource are no longer a hindrance, the urge to let it be just a fun hobby is strong. 

For now though, the iNaturalist community is already doing its fair share in tackling this problem because all the things it does well do add up, and in a crisis far from being solved despite decades worth of projects, publications and initiatives to help solve it, every drop counts and it seems those drops are turning into a spring. iNaturalist has great potential to become a major supporting candle for shadow diversity and bonfire against dark extinction, which is just two of the many reasons why I intend to be an iNatter for life.

- don’t get tricked: there’s a similarly named plant, Ixora philippinensis!

- check out the amazing diversity of fruit and flower chafer beetles here!

If you're an active observer and/or identifier on iNat, you'll often get a lot of notifications, some of which you may not want to or need to see or respond to. However, you can turn off notifications for some kinds of identifications by going to the Notifications page in your Account Settings:

By default they should all be set to “On” but you can choose to turn any or all to “Off” (make sure to click Save Settings after you make a change).

The first preference has been around for years but the next two were added in April of 2025, so you may not be aware of them yet. 

Turning off notifications for Confirming IDs will prevent notifications being generated for you when someone adds an ID that exactly matches your ID on that observation. For example, if you ID an observation as Columba livia and someone adds an ID of Columba livia to the observation, you will not be notified of their ID.

Turning off notifications for Infraspecies IDs will prevent notifications being generated for you when someone adds an infraspecies ID (a subspecies, variety, etc), that agrees with your species level ID. For example, if you ID an observation as Columba livia and someone adds an ID of Columba livia var. domestica to the observation, you will not be notified of their ID.

Turning off notifications for Non-disagreeing Ancestor IDs will prevent notifications being generated for you when someone adds an ID that is an ancestor of your ID but does not explicitly disagree with it. For example, if you ID an observation as Columba livia and someone adds a non-disagreeing ID of order Columbiformes, you will not be notified of their ID.

However, if someone includes a remark with their ID, eg “You can tell this is X subspecies due to Y features,” you will be notified of their ID even if it meets one of the above criteria.

As someone who gets a lot of notifications, I’ve found that using these preferences greatly reduced the number of notifications I get and helps me more easily find the notifications I need to attend to most. We hope they help you as well!

We released a computer vision update today! Model v.2.22 has 103,765 taxa compared to 101,374 taxa in the last model and is trained off data exported on April 20, 2025.

This model is the result of millions of observations and identifications shared on iNaturalist. As new taxa are observed and identified, taxa (mostly species, but also genera, families, etc.) are added to the model once there are at least 100 photos and 60 observations of that taxa. As taxonomy changes and misidentifications get corrected by the community, sometimes taxa are also removed from the model. To keep up with these changes, we update the model every month or two so that the community can benefit from the improvements. Check out our help page for the most updated information on how we update the model.

Below are links to the taxa added since the last model. You can click through and search for your username to see if you have observed or identified any of these species. If so, thank you!

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

The graph below shows how the number of taxa included in the model has grown over the last few years — nearly doubling from ~55,000 in 2022 to ~103,000 today.

Each time we release a new model, we evaluate it against the previous one.

The graph below shows model accuracy estimates using 1,000 random Research Grade observations in each group not seen during training time. The paired bars below compare average accuracy of model 2.21 with the new model 2.22.

When we update the computer vision model, we also update the geomodel. With this release, we’ve updated our geomodel using a new training approach called SINR (spatially implicit neural representation). Our previous geomodels predicted species distributions based on spatial grid cells. All iNat observations were aggregated into multi label presence sets per cell, then a model was trained on these aggregations using multi label binary cross entropy over species presence in the cell. It produced sharp geo priors which make it useful in downstream computer vision tasks, and is straightforward to develop and debug.

In contrast, a SINR model learns directly from individual observations and carefully constructed pseudo absences, and uses negative sampling loss to distinguish where species are likely or unlikely to occur. It provides better generalization and avoids discretization artifacts, aligns with the work of our research collaborators, and is easier to adapt to interesting new directions for producing pseudo absences. It’s empirically stronger on mapping tasks, and we believe that as we keep working on it, it will catch up on the geo prior / CV task.

Here’s a head to head comparison on some key metrics:

This new model training approach improves the way we model species ranges across space. It offers better alignment with expert range maps and more robust predictions for sparsely observed species. We’ll continue to refine how the geo model supports the computer vision system and hope to see quick improvements with the geo prior improvement in the next few releases, without losing the mapping/range evaluation wins. We appreciate all the observations that make this possible, and are especially grateful to our research collaborators at Vispedia who created the SINR approach that we’re using.

Thank you to everyone in the community who contributed observations and identifications for all the species in this model! This is truly a collective effort.

EDIT MADE 7/1 at 11:30 am PT: Clarified language around which taxa are added to model.

New research and discoveries from the iNaturalist community

Every month, new papers and articles are published using iNaturalist data for real-world science. Here are some highlights from June 2025!

Check out research highlights from May here. And if you like reading about science supported by iNaturalist data, be sure to sign up for our monthly newsletter to get stories like these delivered directly to your inbox! You can also find more on our social media channels.

BONUS: Read Dana Milbank’s article from last week that mentions iNaturalist, "I hiked the Appalachian trail. It fixed my brain."

Have an iNaturalist observation, project, or story you want highlighted on our channels? We'd love to hear from you!

Right now, if you spent just one second looking at each observation on iNaturalist, it would take nearly 8 years of non-stop viewing to see them all.

And if each observation were a mile, we could circle the Earth about 10,000 times (or about 6,200 times if each observation is a kilometer).

These aren’t just numbers. They represent real moments of attention to nature from nearly 4 million observers across the world, and over 400,000 people dedicating time and effort to identify other people's observations.

It took 14 years to reach our first 100 million verifiable observations, but just another two for the next 100 million. Now, the community has added another 50 million in a little under a year. There’s a growing, global community paying closer attention to nature every day, and we’re so grateful that you’re part of it.

Each observation is a single data point — but together, they create a living, dynamic map of life on Earth. Let’s take a closer look at the 250 million observations as 250 dots, where each dot represents 1 million observations.

Imagine 250 million observations are represented by 250 dots

How many dots from each species category?

166 of the 250 dots are of plants and insects. Fish are represented by just 3 dots, while protists are represented by 1.

How many dots are from each continent?

Dots are spread across continents, with the most currently coming from North America.

More than 100 million of these records are shared with the Global Biodiversity Information Facility (GBIF), contributing to over 6,500 scientific publications — and every new observation continues adding to our understanding of the immense biodiversity around us.

The graphs below show the number of observations posted each month since iNaturalist was launched in 2008, and where iNaturalist observations have come from around the world. Click on each image for interactive versions!

Observations Over Time

Observations by Country

This milestone wouldn’t be possible without every person who has taken the time to observe, identify, or share iNaturalist with others. The data you all have contributed and curated powers real-world science and conservation, and we’re grateful to everyone who’s been using iNaturalist to make change in the world for biodiversity. Thank you! You’re all part of a global movement to make biodiversity more visible — revealing patterns of change, highlighting places in need of protection, and strengthening our collective ability to understand the natural world.

If you want to look back at how we celebrated past observation milestones, you can read about 200 million, 150 million, 100 million, 50 million, 25 million, and 15 million.

iNaturalist is excited to announce an award from Google.org Accelerator: Generative AI to help build tools to improve the identification experience for the iNaturalist community. The project we proposed builds off of our demo from last year to search iNaturalist photos with text. The award from Google.org provides $1.5M over 2.5 years plus access to Google staff to advise the iNaturalist team.

Our nonprofit mission is to connect people to nature through technology and advance science and conservation. We see this new opportunity with Google.org as a clear extension of the work that we’ve been doing for years to build better tools to connect people to nature. By using generative AI (GenAI), we hope to synthesize information about how to distinguish different species and accurately convey that to iNaturalist users. Instead of just offering AI species suggestions of what you saw, we want to offer a why as well. By providing explanations in addition to a list of suggestions, iNaturalist hopes to more effectively grow a skilled community of naturalists who have the information and tools to improve and vet the data on iNaturalist.

We explored this idea in this blog post last year using these frogs as an example. Currently, iNaturalist’s computer vision model can distinguish these frogs, but we don’t do a good job of explaining how. We’d like to use GenAI to tell people not just which frog it is but why it’s that frog.

Our goal is to build a working demo by the end of the year, and we’ll share more updates as the project evolves.

More generally, we're excited to use this grant to learn more about how AI is changing the technology landscape and how we can leverage these tools to enhance our mission and impact. As we learn about what AI tools are available to our nonprofit and how we might use them, we will continue to weigh ethical and environmental concerns.

We’ve tried to address some of the questions that have been raised on social media and in the forum in these FAQs.

FAQs

What is the history of iNaturalist and AI?

iNaturalist has been synthesizing photos and identifications using machine learning since 2017 to provide computer vision suggestions (a kind of AI) on the iNaturalist website and mobile apps. In 2023 we started incorporating observation location into our model training process, which resulted in the geomodel and range maps. All of the training of these models happens on two machines we own and control. Each time we update the model, we write a blog post about the new species that have been added thanks to the observations and identifications from the iNaturalist community. You can read the most recent blog post from April.

How is generative AI relevant to iNaturalist?

One of iNaturalist’s biggest strengths is its community of knowledgeable naturalists who spend time and energy helping identify observations. We know that this is a massive undertaking — especially as iNaturalist continues to grow, bring on new users, and support large-scale bioblitzes — and that without additional support, data quality becomes an issue.

Since its beginnings, iNaturalist has worked to leverage emerging technology (like computer vision, and even mobile apps in the early days) for biodiversity and conservation — and we think generative AI could be used to support the hard work done by folks making IDs on iNaturalist. For years we have grappled with how to surface the most useful identification tips shared by these members of the community, and we think that generative AI could provide a scalable way to synthesize and share useful information about how to identify the 100,000 different species included in our current modeling process. We are still exploring different approaches to this, but overall, the goal is to make observing and identifying on iNaturalist better and more enjoyable while also delivering more high-quality data needed for science and conservation.

How will you ensure that the identification tips are reliable?

We will incorporate a feedback process for the AI-generated identification tips so that we can maintain high standards of accuracy. Since this project is in its early stages, we don’t know exactly what this will look like, but we will share updates to be more transparent moving forward.

Ultimately, we want to continue synthesizing information across iNaturalist so that it’s more useful and accessible. We’ve been doing this with photos via our computer vision suggestions (and have a system to credit iNaturalist users whose photos and identifications were used in the model), and now, we’re excited to expand this tool to include text descriptions, too. We deeply appreciate your time and feedback, and we will continue doing our best to connect people with nature through technology.

Update on June 11, 2025 at 9:15pm EDT

We recognize that this announcement has caused a lot of upset and confusion among people who care deeply about iNaturalist. In the hundreds of comments, we hear that many people feel betrayed, disrespected, and without agency. We sincerely apologize.

With respect for the ethical and environmental concerns raised, we’d like to offer more clarity about our plans with this grant and program. We know that trust is not easily rebuilt, but we’d like to try.

First, to clarify some things we did not clearly communicate:

1. We are not replacing or changing the current human-curated system of identifications. Many of you have rightly pointed out that this is at the heart of iNat, and we wouldn’t dream of doing away with it. Anything we explore with AI would only be meant to enhance the experience of some users: by, for example, providing an interesting tip about identifying the species, suggesting that the photographer try to capture a particular aspect of the plant or animal that might aid a human identifier, or explaining the computer vision’s logic for the identification it’s suggested.

2. We are not giving Google special access to your iNat data, and we have no obligation to use Google’s infrastructure as part of this grant. Google is providing funding and advice on how to potentially leverage AI.

3. iNaturalist has successfully incorporated machine learning and computer vision (kinds of AI) since 2017, with a very small footprint (primarily three machines running in spaces we control). We understand that new technologies can have much larger environmental impacts, and we aim to quantify the environmental footprint of iNaturalist’s infrastructure for 2025 and beyond.

4. This grant funds our team exploring new ways to surface and organize helpful identification comments — and if the demo we create is not helpful, compromises data quality, has outsized environmental impacts, or is overall too flawed, we will not keep it.

This project is just getting off the ground, and we don’t know what it will actually look like to the user yet. We, along with many of you, are concerned that features like these could have a negative impact on iNaturalist, so our plan is to take an experimental approach to see if we can solve some of the core problems iNaturalist users have surfaced previously. If after testing and refining this experimental feature, we find that it reduces data quality and enjoyment of the platform — or its environmental impact is too large — then it’s not something we would continue with.

The iNaturalist community has always been a core partner in informing the direction of the platform, and we appreciate and hear your feedback (including but not limited to):

• We understand that you are concerned about inaccurate, out-of-context and/or hallucinated information being provided by a tool like this. We agree that any AI-provided information be clearly labeled as such and that there be a way to upvote/downvote or otherwise flag potentially misleading information, and we are excited to explore more ways for how this may happen.

• We hear that people would like to be able to understand and control how their data is used on and beyond iNaturalist. On iNaturalist, you own the copyright to your data, and iNaturalist Terms of Use prohibit the use of data for commercial AI training. Whether commercial AI companies are beholden to copyright law or terms of use or can argue “fair use” of publicly accessible data is being worked out in the courts and is something we are paying attention to.

• Most importantly, the community will be involved in the creation of this and any major new features.

We will not be implementing any new changes to what you see on iNaturalist right now without involving the community. Our plan is to have an initial demo available for select user testing by the end of 2025. If you have more feedback, ideas, concerns, or questions you’d be willing to share, please use this form so we can more easily keep track of them.

Additionally, if you would like to attend a virtual Q&A session to have some of this discussion in real time, please let us know in this form (more details to be determined).

Again, the project funded by this grant is just getting started. We will proceed carefully and respectfully, and we’re immensely grateful for this incredible and engaged community.

Hello, identifiers (and aspiring identifiers) of iNat! Thank you for all of the essential and difficult work you do on iNaturalist.

As a way to make your valuable identification time more efficient, we’ve added a small but helpful Disagreements filter to the Identify page, which you can access by clicking on the Filters box:

When you check that Disagreements box, the Identify page will show you only observations where at least one active identification is an explicit disagreement, such as:

Why add this filter?

This will help you find observations where more informed community input is most beneficial, at any taxonomic level. 

In the example above, the observation now has a Community Taxon of Class Arachnida due to the two disagreeing identifications, and would benefit by more people seeing the observation and weighing in with an informed opinion. If two more people agreed to the Harvestmen (Opiliones) identification there, for example, the observation’s Community Taxon and Observation Taxon would change to Harvestmen (Opiliones) and be more easily findable by someone who specializes in that taxon. It’s like a relay race, we’re doing everything we can to pass the baton to the next person.

In testing it out over the past week, I’ve found that for me it’s most useful when combined with other filters that restrict results by location and taxonomy. For example, restricting results to California shows me observations where I have enough knowledge to weigh in with an informed identification or comment. I’ve also found it useful when going through my own observations to see where I need to update or withdraw my identification.

Technical Details

If you’re familiar with editing search URLs, this filter adds the param disagreements=true to the URL. Other possible values are false and any (which is the default).

Added clarification on July 2nd, 2025: the disagreeing ID must be active and must be disagreeing with another active ID.

We hope this new filter will help you when you’re looking for observations to identify! Let us know how you’re using it or if you have any feedback. Thanks again for making iNat what it is!

As community scientists, we can all play a crucial role in tracking and monitoring invasive species. This month, we're highlighting five species that need your attention in different parts of the world. Your iNat observations could make a difference in understanding and managing these invasive species.

In the United States

1. Spotted Lanternfly (Lycorma delicatula)

This eye-catching but destructive pest continues to be a significant concern across the United States. A recent observation from Oregon by @josiegraydon put local officials on alert as they work to prevent this invasive insect from establishing new populations in the Pacific Northwest.

2. Rusty Crayfish (Faxonius rusticus)

These aggressive crustaceans are native to the U.S., but their range is rapidly expanding. An iNaturalist observation in the Little Thompson River in Colorado by @scupin raised concerns about their potential impact on local aquatic ecosystems. Wildlife officials are actively monitoring their spread and implementing control measures.

In India

3. Gonipterus platensis

The recently established eucalyptus weevil is gaining attention in Tamil Nadu, India — and community scientists have played a crucial role in documenting its presence through iNaturalist observations like this one. by @ashwinv.

In Brazil

4. Zaprionus tuberculatus

This invasive fly species has been documented in Pará, Brazil (observation above by @jeanmartins). As a potential agricultural pest, monitoring its spread is crucial for developing effective management strategies.

In the United Arab Emirates

5. Vegetable Leafminer (Liriomyza sativae)

Recently found in Dubai, this tiny but impactful pest poses a threat to vegetable crops in the region (observation above by @firouzierfan). Early detection and monitoring are essential for managing its spread.

What you can do

If you encounter any of these species or other suspected invasive organisms in your area, here's how you can help:

1. Take multiple clear photographs from different angles
2. Upload your observations to iNaturalist
3. Find out if there are local agencies or organizations tracking the spread of this species and send them your iNaturalist record
4. Tell your friends & family to keep an eye out, too!

Your observations matter — with each one, we can build a better understanding of these species and support monitoring efforts worldwide. For more information about invasive species in your region and how to report them, visit your local conservation authority's website or contact them directly.

What species are we missing from this list? Let us know in the comments below!

Our Observation is this Phyllomorpha lacerata bug, seen in Georgia by @axelgosseries!

Originally from Belgium, Axel Gosseries tells me he currently splits his time between Belgium, Portugal, and the Caucasus.

In Portugal, I am in charge of a holm oak savannah where I mix observations, conservation and regenerative farming. In Caucasus and Belgium, I merely do observations at this stage. I love to explore and whenever possible to contribute a little bit to documenting the beauty that surrounds us. If time allows, I would like to focus more on certain groups of insects in the future.

He became interested in nature at around the age of seven, inspired by local bird ringer Roger Coryn. 

As a teenager, I became actively involved in a Belgian association called Jeunes & Nature. It had three striking features. First, it was managed by young people only. As soon as we reached our mid-twenties, we had to leave. It really felt like a bunch of friends, with no hierarchy at all. We still see each other regularly. Many of them became professional biologists and I am unsurprisingly the only one who became a philosopher :-). Second, we were doing both nature observation and nature conservation, a mix that I always liked. And third, just like iNat, it was a group of enthusiasts who were curious about all types of living beings, not just birds or plants. We were learning so much from each other! But we were in the late 20th century and e-mails and the internet were just at their early stage.

Axel started traveling to Romania in the early 1990s and loved the people and nature there so he kept returning, eventually also checking out the Caucasus and loving it there as well. 

Last month, while visiting the area, Axel says:

we were spending the day with three great friends, Yves, Nina and Tazo, in a Pistachio savannah in a remote part of Georgia. I was not looking for any species in particular. We had spent an hour or two looking for birds and it was now time for insects and plants. Typically, we distribute ourselves in the landscape, a few tens of meters away from each other and we continue chatting from a distance, while discovering amazing things one after the other. The Phyllomorpha was just passing by and I decided to take some pictures of it. Incredible body shape.

One of the observations identifiers, @kgrebennikov, was kind enough to write me some information about this species, of which little is known:

Phyllomorpha lacerata is a species in the Leaf-footed Bugs family (Coreidae) spread from Sardinia to Syria and Iran. It occurs in deserts and other dry habitats on the ground. The biology of this and closely related species remains poorly known. The main host plants are probably plants of the genus Paronychia, possibly also other species of the family Caryophyllaceae. Like all species of the tribe Phyllomorphini, Phyllomorpha lacerata has an unusual “leaf-shaped” body with broad flat lobes and spines. This is most likely due to mimicry - this appearance makes them look more like dried flowers or fruits of desert plants rather than insects. Including the host plant of the species (e.g., https://www.inaturalist.org/observations/283604860). 

Axel (above in Portugal), joined iNat about two and a half years ago, and says:

I find iNaturalist amazing because you can just go for living beings that you would otherwise never would go for, due to lack of books or ID keys. And here, you just take pictures as good as you can and you start learning a lot, thanks to all the great work of iNat identifiers. There is no barrier. You can be a beginner or an expert. We just share the same space. 

With iNat, I regained this spirit of a sharing community of knowledgeable enthusiasts that I had experienced in my youth. And I found a perfect way of mixing the scientific part with a permanent sense of amazement. You go into a forest or wander around in fields of flowers, and every few minutes or so, you get this feeling of “wow, I didn’t even imagine that such a beauty existed!”  And you can share this passion through the platform.

(Photo of Axel by Yannick Vanderborght. Some quotes have been lightly edited for clarity.)

- Check out the most-faved observations of bugs in the tribe Phyllomorphini!

- a year ago we featured @crocusadamii’s hedgenettle from Georgia as Observation of the Week!