Exploring New Ways to Learn from iNaturalist’s Community Expertise

News and Updates
1

December 3, 2025 UPDATE: You can now browse the first release of the ID Summaries demo to see species identification tips for about 150 taxa. These tips are drawn from the expertise of about 30 prolific identifiers on iNaturalist. This demo is separate from the rest of iNaturalist. None of the summaries or feedback in the demo appear anywhere else on the site or in our apps.

Here’s our blog post about the demo. This is just the first exploration of multiple approaches to highlight and summarize identification expertise in easily accessible ways. We’re excited to hear your ideas and feedback as we iterate on this idea.

If you’re interested in more of the technical details, we’ve answered some questions below.

We used Gemini 2.5-Pro to create these summaries, and our estimates of the energy, carbon, and water usage can be found here.

So far, we’ve heard incredibly helpful questions, feedback, and insights from the group of identifiers whose remarks and comments are being used in the demo. Some of those questions include:

How is data being selected and processed for the demo?

We’re working with identification remarks and observation comments from 32 users in total for this demo (28 prolific identifiers, 4 iNaturalist staff members). In total, this comprised 1,269,580 remarks and comments.

To ensure higher quality remarks and comments, we ran them through a series of processing and filters. We first extracted all their remarks and comments from the platform, then filtered out any with fewer than 5 words. Then, we selected remarks and comments only from observations that were identified to species or subspecies level, as well as filtered out observations of some species (including humans, cats, and dogs).

From there, all the remarks and comments went through another round of filtering (removing all remarks and comments with fewer than 10 words). These steps left us with 182,287 remarks and comments to sort and filter further.

What’s the threshold for how many comments are needed before a summary is generated?

After putting remarks and comments through a series of data processing steps and sorting them into their respective species, we removed any species from the list that had either fewer than 50 comments/remarks related to it, or comments from fewer than 3 users. This left us with 173 distinct species with 44,049 remarks and comments. For the demo, we selected the top 150 species from that list.

How does the LLM handle species-specific features vs. genus or family-level features? What about identification info that only applies to certain regions or in comparative context?

These are both areas that we’d like to improve in the future. Right now, the demo only uses remarks and comments from observations identified at species or subspecies level, and you can click through to the observations from which those remarks came to see location. However, the community has shared many ideas for how we could streamline the experience of getting additional geographic or taxonomic context along with each summary in the future.

How will upvotes/downvotes actually affect the summaries? How are we treating inaccurate summaries that are marked by the community?

We’re collecting all of the feedback on the ID summaries and on the individual remarks/comments contributing to each of them in a separate feedback dashboard. The ID Summaries Demo does not dynamically regenerate — instead, we will incorporate the feedback into the next round of updates, much like we do for our current Computer Vision system.

How far back does the demo’s dataset go? What about more recent ID remarks and comments?

The demo uses all remarks and comments made by 4 iNaturalist staff members and the 28 community members we worked with up until November 19, 2025, which was the most recent time the ID summaries were updated.

How are photos selected for each taxon? Will there be feature-specific photos in the future?

Since the focus of this demo is the summaries themselves, we’re only using a small selection of photos shared by the same 32 people whose remarks and comments we’re working with. From their photos, we ran a script to automatically select the research-grade photos with the most favorites. In the future, we’d love to find ways to incorporate tools like feature-specific photos that highlight certain aspects of an organism alongside an identification tip.

Will there be a way for people to directly edit or add ID tips to the demo?

This demo doesn’t have that capability, but we’re exploring possible future directions for letting people contribute more directly. In the meantime, please feel free to leave feedback via the voting mechanisms in the demo and/or here in the forum.

Overall, your feedback on the summaries in this demo are hugely helpful for us to understand what’s working and not working. Thank you for taking time to share with us. If you’d prefer to offer feedback privately, please feel free to reach out to carrie.seltzer@inaturalist.org.

Original post from October 15, 2025

Hi everyone,

We just shared an update on our blog about our ongoing work to make it easier for people to learn identification skills.

Please find the full blog post with more information linked here.

A very brief summary of the update:

  • We are exploring how to summarize existing expert knowledge to make it easier for people to learn identification skills without adding more burden for identifiers.
    • We’re developing a standalone demo that uses an existing LLM (not training a new one) to turn a volunteered set of identification remarks and comments into brief summaries.
    • This experiment began with only our staff’s identification remarks and comments. This yielded promising results, so we reached out to a small set of experienced identifiers to ask if we could conduct the same process with their content, as well. We’ll be working with them throughout the process to assess the results.
  • All of this is exploratory work and will continue to evolve with community feedback.
  • Once the demo is closer to launching, we’ll host a live preview and Q&A. You can indicate your interest in that live session here if you haven’t already.
  • In case there is any confusion, AI-generated images are not acceptable on iNaturalist as an evidence-based platform. We recently implemented more robust guidelines and tools to make it easier to flag and remove AI-generated images from the platform.

We welcome thoughtful feedback from the community, and please abide by the Forum Guidelines.

43 Likes
2

I put this thread on slow mode to encourage a broad base of discussion.

10 Likes
3

I think this is a fantastic application of AI and will add value to all of the comments that we make relevant to IDs because those comments can actually be found and put into this broader context. I feel that this will make it even more likely that I will add future insightful comments on observations. Given that the amount of information that the AI model is based on, I can’t imagine that it will require an unacceptable amount of energy usage. And it links directly to the comments upon which the summary was based.

[Note added later: Even if the AI summaries prove to be of no value, having AI identify comments that appear most useful in providing diagnostic criteria seems of great potential value.]

24 Likes
4

Thank you for closing comments on the blog post, and keeping the conversation here in one place. (Better than the ongoing grumbles about closing comments halfway last time)

https://www.inaturalist.org/projects/observations-with-id-tips You may be able to incorporate some of this at a later stage.

10 Likes
5

It shows promise, but hard to say much beyond that without trying it out. Somewhat like trying to guess how nice a car will drive from just looking at it.

I will say it very much could turn into a disaster without proper illustrations or definitions of anatomy. If the CV starts talking about, RM, R2+3 wing veins. That information will mean nothing to people if they do not know the names of the structures for that organism. If I am using words like Gonostylus, superior volsella, most people are going to say “Gono what? I have no idea what that is”
Also what is the alternative? Some things yes you can word better, but how can I explain IDs without using the proper names for anatomy when there are no name alternatives?

Aesthetically, the UI looks nice and I do look forward to the development of this. I think it has the potential to work and be a good help.

29 Likes
6

We tried to manually collate this using a project on iNat: https://www.inaturalist.org/projects/keys-s-afr - basically trying to accelerate access to diagnostics, notes, distributions and other information posted on observations. In theory one filters by a taxon, and the project should turn up relevant information.
[e.g. Velvetworms in the Cape : https://www.inaturalist.org/observations?project_id=18643&subview=table&taxon_id=90935&verifiable=any - which interestingly illustrates how information from a decade ago is inaccurate today - the number of new species has changed the distributions)
In practice, it is impossible to curate. The beauty of AI is that it should be able to do this rapidly, comprehensively and extensively, as well as summarize and integrate.

Look forward to seeing how this evolves.

9 Likes
7

Can I add my own expertise for some species(and cite dichotomous keys as evidence)?

7 Likes
8

I think the example Monarch ID summary is kind of weak? The summary repeats the same thing in two different ways, probably not recognizing that they were saying the same thing.

A human-made summary or guide would probably show a Monarch and a Viceroy side-by-side with an arrow to the band on the hind-wing of the Viceroy, instead of relying on jargon that most beginners don’t know (e.g. “subterminal” and “hindwing” - even if the latter seems obvious, it isn’t to someone who has never paid attention to butterflies before: many haven’t yet noticed that butterflies have more than two wings).

A good summary would also note the locations where Monarchs can be found, where both Monarchs and Viceroys can be found, and compare and contrast with other species which are easily mixed up with Monarch (e.g. Queen, Danaus gilippus).

About the only good thing I can say is that the summary didn’t distort the comments overmuch - only inserting “adult” and “notably”.

44 Likes
9

Yeah, given things like what you pointed out, I’d definitely say any computer-aided summary should be a starting point, and may need to be heavily revised by a person who actually knows how to ID that taxon for the guidance to be succinct and accurate enough to be of use as a casual reference. I’d say a human review is straight-up necessary before releasing any computer-aided summary for public consumption.

A test case like a monarch also shows the need for life-stage-specific categorization of ID guidance. Location-specific delineations will often be useful, as well.

Just putting AI-aided summaries on pages with the inevitably ignored “oh btw this is AI so it might be wrong“ disclaimer is not responsible.

25 Likes
10

One of the many challenges with making this honestly useful is going to be the fact that the best identification tips for the same species often vary geographically. Tips from one county are often misleading the next county over. The same can apply across season, life stage, etc. AIs are still quite bad at circumstances like this where information is only true in an unstated piece of variable space.

I strongly agree with:

And given the fact that it needs human revision anyway, I don’t see any advantage of the AI summary over directly giving the human reviser the comments the AI is summarizing.

40 Likes
11

It’s definitely something we found when using my comments for Thamnophis sirtalis, which occurs across much of North America and varies in coloration wildly from place to place. I pretty mostly ID it in California along the coast, where it pretty much always has a red head. Ones on the east coast of North America have quite different coloration. So some of my comments were not pertinent to those populations, but others (such as scalation) were. Definitely something to consider.

But it did a good job summarizing ID tips for distinguishing Taricha torosa and Taricha granulosa, which are two often-confused species in California.

It could also summarize comments about what’s needed for IDs, like “Photos of the genitalia are necessary for identification” or “Photos of the mushroom gills are needed to distinguish this species,” which I think would be a useful.

As the blog post says, this is kind of kicking the tires on this approach and learning from it.

It’s certainly made me think of how I write my comments and how I could improve them.

21 Likes
12

I really appreciate that the model directly includes the comments that it is referencing to make it easier to look into the context and discussion that the information came from. Its usefulness and so on are hard to gauge without getting my hands on the model directly and seeing how it talks about similar species (what would the corresponding viceroy page look like? how useful would it be for comparing those two species?)

I understand that the point of the grant is to include the LLM and so it was necessary to include as part of the demo. But I also wonder if this would be better (and cheaper, and more slim-downed) as a model that helps look for ID information and discussion on iNat and collates it together like on this page, without the need for an LLM to write a summary at all. Surfacing this kind of info itself seems the most useful thing it’s doing to me, not writing the summaries.

36 Likes
13

I was thinking that a “limitations to ID” section at the very top might be a good use. “Only identifiable when blooming”, “adults are indistinguishable unless X is visible”, etc.

It also seems like being able to link to not just the comment but the associated observation might be necessary to make sense of comments that include context like “in your area” or “in our region”.

17 Likes
14

Even this varies geographically. Here in Sonoma County the caddisfly Nerophilus californicus is clearly identifiable by coloration. In other parts of its range, one needs to look at the finer anatomy.

11 Likes
15

I don’t understand how AI works so I can only tell you how this makes me feel. Every time I read that AI is better, faster etc. it lowers my motivation to identify. It makes me feel that what I do when identifying (mostly unknowns) is not going to be useful any longer. I don’t know how AI works, but I have read a great deal about how it doesn’t work so I am wondering if I will be endlessly correcting a program, instead of interacting with the people on iNat. I will say again, this is how I feel not what I know. I have learned so much on iNat from so many people. I hope I have passed on that learning to others. How I feel is that AI will take that away.

32 Likes
16

That’s especially true of the Computer Vision, correct? Perhaps some day you won’t have to mindlessly pour over millions of unknowns and you can spend your time doing more valuable activities. And that would have been made possible by your identifications.

9 Likes
17

I think there’s a lot of potential here, especially if allowances can be made for geography, life stage, stress, etc. I really look forward to trying it out. I’m actually kind of curious if it works better for species where I copy and paste some standard text across a lot of observations or those where I offer information pertaining to a specific observations. If the AI proves to be responsive to new comments, I think it will motivate me to add more contextual information to my comments.

15 Likes
18

Humans identifying observations (including unknowns, I do a lot of the same!) will always be useful and important! :slight_smile: The comments and IDs from the community are essential to iNaturalist, and it’ll stay that way.

With this demo, we’re also hopeful/curious to see if displaying people’s comments and linking directly to them will help encourage more direct discussions and interactions.

12 Likes
19

I’m not sure if a large language model is the right way to do this as opposed to a different language model? If we’re starting with a corpus of iNat staff ID comments, then wouldn’t it be easier to tag those with the relevant features and just search those, instead of doing the LLM-style “generate the most likely next word”?

A rudimentary example:

[category: taxon] Bees can be differentiated from [category: taxon] hover flies by the number of [category: body-part] wings.

And then if the CV model suggest bees, it can be accompanied with volunteer-written text tagged with [category: taxon: bees]. Not sure if the ID summary demo used any tagging? If it does I’ll remove the over-explaining lol

In my opinion if the computer generated IDs behaved more like a search engine (of pre-written ID tips written by volunteers) it would be more helpful than a large language model. Both complicate iNat’s user interface though.

Unfortunately, LLMs are all the rage and iNat probably doesn’t have the manpower to do its language processing in-house. Oh well.

14 Likes
20

just give us a community wiki at that point, it will be easier to implement and edit. please just stop with the ai… most of us are tired of having ai and llms shoved down our throats at every opportunity. please listen.

49 Likes