Our Observation of the Week is this Anoplocnemis curvipes bug, seen in Kenya by @ndanganga!

“I became interested in nature at a young age (around 8 years) mostly due to spending time out in the fields taking care of my family's herd of cattle,” says Kariuki Ndang'ang'a, who grew up in Kenya. 

With other boys I adventured a lot into the then almost intact countryside which had a lot of wild berries to eat, trees to climb, as well as mammals, birds and other animals to describe and hear stories about. Eventually I chose a “Wildlife Management” university degree and since then I've not stopped. I am particularly interested in ornithology/ study and conservation of birds, and have written a lot about my bird research. However for the last almost 20 years I have been working in a bird conservation NGO on conservation projects, programmes and leadership. Despite my bird specialisation, I still find myself looking at other forms of fauna and flora.

Lately, Kariuki tells me, he’s become interested in photographing odd plants and insects. “Not that I can identify them,” he explains, “but there is fun in placing a picture in inaturalist and getting suggestions of the taxa's identity from other people.”

One morning, Kariuki was walking around his fruit and vegetable garden,

appreciating how green it has suddenly become following recent rains, and suddenly among the weeds I noticed this strange bug!! As expected I took a picture on my phone and loaded it on iNaturalist, only to realise hours later that it had been chosen as the Observation of the Day. I couldn't help but share a screen shot of the X post on my WhatsApp update.

Anoplocnemis curvipes is a species in the leaf-footed bug family (Coreidae), most of which suck sap from plants. Quite a few species, like this one, have enlarged femurs, and many have “leaf-like” growths on the tibia of their hind legs. Anoplocnemis curvipes is known as a pest of cowpea (Vigna unguiculata), a common crop in Africa. 

Kariuki (above) has been on iNat for a few years and tells me he uses it

for quickly identifying and learning about interesting plants and animals (especially invertebrates, amphibians and reptiles) I bump into during my day to day activities. iNaturalist has changed the way I interact/see the natural world by increasing my curiosity for anything I see around me.

(Photo of Karikuki by George Ndung'u)

- take a look at the amazing diversity and beauty of the coreids!

- this Southern African frogleg leaf beetle also has some enlarged femurs!

Each time you post an observation of a plant, additional data can be collected for the study of phenology—the timing of events like flowers, fruits, and leaf color change.

Now, you can annotate all observations of vascular plants to indicate evidence of leaf buds, leaves, seasonal color change, or no leaves.

This is what the options look like on an observation of a vascular plant:

Also, we’ve simplified the annotations related to flowers, fruits, and seeds. The appropriate option(s) should be selected based on the evidence provided in the photos.

If you hover over the options with your cursor, you will see the definition. You can also review the definitions in our documentation.

On taxon pages, by default you see a chart of overall seasonality. Take a look at the Japanese Maple. If you add a place filter in the upper right to restrict it to Japan, you can see that it is most observed in April and November.

If you click on “Flowers and Fruits” and hover over the points on the chart, you can see that April has observations in all four categories: flower buds, flowers, fruits or seeds, and no flowers, fruits or seeds. Note: the chart settings offer the option to “Hide ‘No Annotation’” which was selected here.

If you click on “Leaves” and hover over the points on the chart, you can see that November has many observations with colored leaves.

It is hard to strike the balance of broad applicability and useful specificity for almost 400,000 species of plants. Although many species do not fit nicely into these categories, the goal is to provide a useful starting place for most species of plants. We worked closely with other phenology programs (USA National Phenology Network and Budburst) and phenology researchers to develop and revise these terms.

iNaturalist observations have already been used for many studies of plant phenology, such as the impact of climate change on the wood anemone, spatial and temporal gradients in flowering phenology across Europe, and anomalous Yucca blooms across southwestern North America. Increasingly, researchers want to access more data by using machine learning to label fruits, flowers, and leaves based on a set of training data. With 8 million annotated and verifiable angiosperm observations (out of 71.8 million angiosperm observations), iNaturalist is a massive and growing source of data to understand plant phenology. Now with the ability to add leaf annotations, we can make 76 million vascular plant observations more useful, too.

These updates were supported by a collaborative grant from the US National Science Foundation to advance plant phenology research through the creation of Phenobase. Phenobase will aggregate plant phenology data from many sources using the Plant Phenology Ontology to maximize data interoperability, in addition to using machine learning to infer phenological stages from photos. The Phenobase collaboration involves the USA National Phenology Network, University of Arizona, Louisiana State University, University of Florida, and the Chicago Botanic Garden.

To learn more about adding annotations, you can review the definitions in and a tutorial about using the Identify tool to add annotations quickly using keyboard shortcuts. Now you can see on your profile how many observations you have annotated. Thank you to everyone who annotates observations!

Our Observation of the Week is this Tatra Chamois (Rupicapra rupicapra tatrica, Kamzík vrchovský tatranský in Slovak), seen in Slovakia by @terana!

“This photo was taken one summer morning in 2013 near the mountain hut where I worked as a student,” says Linda Majdanová, who graduated with a degree in Ecology and Biodiversity Protection. 

When I had free time, I wandered around the surrounding peaks and watched chamois for hours. They are unusually hardy animals. I have many wonderful experiences with them, it is amazing to watch chamois cubs playing together on the remaining snow. Today, meeting a chamois during a hike in the Tatras is not so exceptional, as their numbers, decimated by hunting in the past, have increased thanks to protection. But it is always a pleasant experience to meet this iconic animal, which is undoubtedly a symbol of the Tatras.

A subspecies of the northern chamois, Tatras chamois are herbivorous goat-like mammals which inhabit the Tatras mountains in Slovakia and Poland. As Linda says, they were commonly hunted, with only a few hundred remaining by the end of the 20th century. With conservation work, over a thousand are counted pretty consistently in the mountains now, see the census numbers on its Wikipedia page.

Linda (above) remembers always loving nature, and says 

We lived near the forest and I went on secret trips to nature almost every day and brought home all kinds of bugs, frogs or mushrooms. I was always extremely curious and wanted not only to see, but also to know what I found around me, so instead of fairy tales and children's books, I read educational encyclopedias.

She’s now in the middle of her doctoral studies at the Department of Forest Ecology of the Czech University of Life Sciences in Prague where she specializes in wood-inhabiting fungi in primary and old-growth forests - the topic of her dissertation.

I started contributing to iNaturalist only recently, so I gradually upload older recordings in addition to current observations. I was quite surprised that there are many experts who are able to identify different groups of organisms, which is amazing. Since I spend a lot of my working and free time in the field, whenever I see something interesting or something I don't know, I tend to take a picture of it. And now I know that my observations will not fall into the dust somewhere in a file but will contribute to the knowledge of the world's biota. I also like to look at species distribution maps and find out what lives/grows in different parts of the world.

(Photo of Linda by Vladimír Ruček.)

- this video has some excellent chamois footage.

We are excited to announce the launch of our Vision Language Demo, developed in collaboration with our long-time partners at the University of Massachusetts Amherst, the University of Edinburgh, the University College London and MIT, with generous support from Microsoft AI for Earth. This demo enables you to search a snapshot of 10 million iNaturalist photos using text queries. For instance, typing in "a bird eating fruit" will return matching photos ranked by their relevance to your query.

By clicking the “View these observations in Identify” button at the bottom, you can open these photos in the iNaturalist Identify tool where you can add the observations to projects or add observation fields or annotations. We are excited to learn if you find this tool useful for finding and organizing observations representing different life stages (“a caterpillar”), flowering phenology (“a cluster of red berries on a leafy green branch”), captive/cultivated (“a houseplant in a pot”) etc. into projects and with annotations.

Unlike the iNaturalist Computer Vision Model and Geomodel which we train ourselves off of iNaturalist observations, we did not train this model nor is it trained on iNaturalist data. This demo is built off a freely available Vision Language Model that was trained on millions of captioned images not necessarily relating to the natural world. This means that it knows about other things in addition to living organisms (e.g. "a bird perched on a car") but it also means that it currently has biases and may return inappropriate or offensive results that we don’t fully understand. Please keep that in mind when using it.

You can help us and our research collaborators understand how this model (or other Vision Language Models models we may explore or build) perform by clicking on the “Help us Improve” button. By marking the photos on the page that are relevant or not relevant to your search (e.g. "Mating dragonflies") and clicking submit we will be able to compare the performance of different Vision Language Models at this image retrieval task.

We built this demo to better understand the potential of Vision Language Models to help the community organize, explore, and explain the information contained within iNaturalist images. Building this demo has helped us understand the opportunities and challenges associated with this new technology. For example, while these models sometimes demonstrate a surprising ability to describe what is happening in images at a coarse level, they also fail to grasp more complex, finer concepts such as species names.

Two exciting possible future avenues are:

1. Helping to explore and organize iNaturalist images

iNaturalist data have been used in more than 4,900 scientific publications. While many scientific applications stem from qualities of the data that are already easy to filter (species, location, date etc.), an increasing number of studies are leveraging “secondary data” contained within the images themselves ranging from species interactions, to animal behavior, to phenotypic patterns revealed in the images such as color. Here are some examples of recent published studies that resulted from pulling patterns out of iNaturalist images:

Conservation: Recovery plans for the endangered Red-bellied Macaw were premised on the belief that the parrot relies on fruits from a single species of palm for food. Silva and colleagues examined iNaturalist images of this parrot eating fruit and found that it has a much more diverse diet than previously thought.

Climate Change: To reveal how plants are adapting to climate change, Funkano and colleagues examined iNaturalist images of wood sorrels from around the world and found that leaf color is evolving to become redder in urban heat islands.

Animal Behavior: Jagiello and colleagues examined thousands of iNaturalist images of hermit crabs and found that they are increasingly utilizing lighter weight plastic trash in lieu of shells. This study reveals how certain animals are able alter their behavior to take advantage of the Anthropocene and resulting impacts on the ecosystem.

Evolution: Most mammals are thought to have brown eyes. Tabin and Chiasson examined iNaturalist images to test this. They found an exception in the cat branch of the family tree where eye-color is extremely variable and explored the role that sexual selection plays. This paper was covered by Science magazine.

Mimicry: Muñoz-Amezcua and colleagues used computer vision models to examine iNaturalist images and found that many more insects mimic spiders than previously thought. This study reveals how in addition to more efficiently surfacing patterns that the human eye can detect (e.g. cats with blue eyes), vision models can also detect patterns that have gone undetected (e.g. moths that resemble jumping spiders).

We’re very excited to explore whether Vision Language Models can make it explore and organize the rich data contained within iNaturalist images.

2. Explaining Computer Vision species identifications

As anyone using tools such as ChatGPT knows, multimodal Vision Language Models can help explain images in a way that complements more traditional Computer Vision systems. The iNaturalist Computer Vision AI does a great job of telling us what species is in a photo, but it doesn’t do a great job of explaining why that species is suggested.

Offering explanations is something the identifier community does quite well by sharing expertise in text remarks (e.g. “This is Striped Rocket Frog and not Rainforest Rocket Frog because the white stripe extends from the eye to above the leg rather than to the groin.”). We’re interested in building Vision Language Models trained on iNaturalist images and remarks that will help iNautralist users understand why the Computer Vision AI is suggesting certain species and how to distinguish between them.

Deeply integrating Vision Language Models into iNaturalist is still far off and will require new funding opportunities and lots of product and engineering work. But we are very excited to share this small milestone on that journey. Please share your feedback on this exciting new demo!