6687 icon thumb

10000 lichen observations

Since Mike started this project 3 years ago we have added 10,000 lichen observations. Of those 3286 are already research grade, and 7811 have at least one ID to genus level.

Ingresado el 16 de junio de 2019 por tony_wills tony_wills | 0 comentarios | Deja un comentario

Aracnídeos perigosos e de importância médica no Brasil

Uma matéria minha no fórum Toca das Tarantulas falando sobre os grupos de aracnídeos que possam ter relevância para a saúde humana.


Ingresado el 16 de junio de 2019 por michelotto michelotto | 2 observaciones | 0 comentarios | Deja un comentario



Ingresado el 16 de junio de 2019 por naturalistkuo naturalistkuo | 112 observaciones | 0 comentarios | Deja un comentario

Nalle Bunny Run 2019-06-15

Despite nine registrations, only four people showed up for this morning's monthly group walk on Hill Country Conservancy's Nalle Bunny Run wildlife preserve. It's too bad since we had a fun morning seeing some great birds! We had barely started walking down the hill when we got a distant but pretty good look at this male Painted Bunting that had been singing for at least 30 minutes:

Painted Bunting

This group was very fortunate to see this bird. On many previous group walks we've heard this species singing all morning but could never get a look at one! This wasn't the only Painted Bunting on the preserve. Later down by the lake we heard another singing that turned out to be an all-green first-year male. There could be two pairs of Painted Buntings breeding here.

When we inspected the spring box we found this small toad clinging to the inside wall. Despite it literally having red spots, I think this is the much more expected Gulf Coast Toad rather than Red-spotted Toad. There were many tiny young Gulf Coast Toads around. (It would be very exciting to find a Red-spotted Toad since they historically occurred in the Austin area, but they haven't been seen around here for years.)

Gulf Coast Toad

Other good bird observations made on the walk included pretty close looks at Blue-gray Gnatcatchers, a male Summer Tanager, a White-eyed Vireo, and female Ladder-backed Woodpecker. By the large cottonwood trees on the eastern fence line we saw a Red-shouldered Hawk missing some tail feathers. (This is a seldom observed species on the preserve, even though I'd expect them to be common here.) We got to hear Canyon Wren, Red-eyed Vireo, and Northern Parula. This female Eastern Bluebird was down by the lake, near a juvenile bluebird it might have been feeding:

Eastern Bluebird

Near the end of the walk almost back up by the gate this bright orange beetle caught by eye as it flew in and landed on a Mexican Hat wildflower:

Orange Beetle on Mexican Hat

I made a very preliminary identification of its species, and I'm hoping more knowledgeable iNaturalist users will help me confirm or correct it.

I ended up recording 25 species of birds. Here's our complete eBird list.

Here are a few more photos on Flickr.

And the same photos are attached as iNaturalist observations to this journal post.

Ingresado el 15 de junio de 2019 por mikaelb mikaelb | 6 observaciones | 0 comentarios | Deja un comentario

June 15, 2019

Today was a very blustery day, yet still my dad and I headed out to go hiking. Normally I am filled with anticipation and excitement, this was a little different. With my backpacking trip to Yosemite drawing closer, the necessity to exercise with my pack increased. To say I was nervous was an understatement. I dreaded the possibility of pain and really just wanted to enjoy the wildlife. However, as soon as my feet felt the ground of that forest, my worries melted. I no longer was filled with anxiety, and I walked peacefully among the trees. We didn't see much wildlife, except for my first Dekay's snake which was very exciting. Although they are common, I find them extremely beautiful.

Ingresado el 15 de junio de 2019 por sbrabec sbrabec | 1 observaciones | 0 comentarios | Deja un comentario
32267 icon thumb

В проекте "Флора России | Flora of Russia" 90 000 наблюдений!!!

Дорогие друзья!

У нас есть приятная новость. В нашем проекте уже 90 тысяч наблюдений. В GBIF зачёте Россия вышла на восьмое место по общему числу наблюдений среди стран мира. Немного усилий и будет первое место среди стран Евразии!


Ingresado el 15 de junio de 2019 por apseregin apseregin | 0 comentarios | Deja un comentario
31894 icon thumb

Сбой в работе навигации в Москве

В Москве произошел сбой в работе сервисов геолокации
14 июня 2019

Пользователи «Яндекс.Карт» и Apple Maps сообщили о массовом сбое в определении их местоположения. Локация пользователей, находящихся в центре Москвы, определялась геолокационными сервисами как аэропорт Шереметьево.

В «Яндексе» рассказал «РИА Новости», что неполадки, скорее всего, связаны со сбоями в GPS. «Такие сбои GPS происходят вообще во всех сервисах и устройствах, использующих геолокацию: от навигационных приложений до фитнес-браслетов»,— отметили в компании. Кроме того, «Яндекс» отметил, что «неверное геопозиционирование существует вне инфраструктуры интернет-сервисов», а геолокационные сервисы получают информацию о местонахождении с устройства и не декодируют сигнал от спутника напрямую.

Подобный инцидент происходит не впервые. В январе 2018 года пользователи уже жаловались на сбои в работе GPS. Тогда их местоположение определялось в Гвинейском заливе Атлантического океана.

Ingresado el 15 de junio de 2019 por apseregin apseregin | 1 comentarios | Deja un comentario

Pajareada Reto Naturalista Urbano

Reto Naturalista Urbano
Avistamiento de Aves
Santa Ana Oriental, Bogotá, Cundinamarca, Colombia

Sábado, abril 27 de 2019
6:00 - 8:45

20 Especies reportadas
56 Individuos vistos

Clima: Mayoritariamente nublado

Márinson Chaparro
Matías Lasso
Pilar Garzón
Simón Santos
Stella Hernández


Ingresado el 15 de junio de 2019 por simons6 simons6 | 13 observaciones | 0 comentarios | Deja un comentario
42109 icon thumb

BioDATA bioblitz winners

We congratulate course students komiljonsaidov with most observations and naturalist14481 with most species!

Ingresado el 15 de junio de 2019 por dagendresen dagendresen | 0 comentarios | Deja un comentario
23720 icon thumb

Preserve Now Open for Business

The parking area is in, the signs are up, and the first trail has been completed. The parking area is off Flagler Road, across from Griffiths Point Road. The trail still needs a bit of grooming at the start, just past the main introductory sign, but it now connects East Marrowstone Road with the parking area off Flagler.

Be aware of a warning sign for ground wasps about half way along the trail's course. Last I walked the trail, there were also some survey tape markers at the location. It is easy to walk by without incident if one stays to the trail.

My last walk turned up four new species for the iNat project. There are two sedges, an evening primrose called evening nightshade, and nice bunch of youth-on-age I'd not noticed before. Only the youth-on-age has research grade at this writing.

Also found during the trail work party on 6/11, was a raccoon skull. Our list of mammals is small, and only supported by traces, tracks, scat and bones at this point. This is also true for birds. I think we have some amphibians, at least red legged frogs from our earlier spring surveys.

Enjoy visiting the preserve. I look forward to seeing your observations.

Ingresado el 15 de junio de 2019 por kurtsteinbach kurtsteinbach | 0 comentarios | Deja un comentario
31902 icon thumb

Identifying “Black Snakes”

This is a piece out of my field guide I am working for for the Herps of Virginia.

The term “Black Snake” is a colloquial term to describe any snake that is black. This covers several species, but it mostly describes either the Eastern Ratsnake or the Northern Black Racer. The two are very different, but hard for most people to identify. This said, almost everything, except color, is different in these two species.

The Eastern Ratsnake (Pantherophis alleghaniensis)
The Eastern Ratsnake has a wider, flat head. The eyes are typical for a colubrid, and are separated from the nostril by three long scales. The lower half of the upper labials are white. The tip of the nose is blunt, and black. The first third of the underside is white, yet checkered, with a slate under side for the rest of belly. The skin on the ratsnake is white, and is visible between the scales when bent, or the snake has inflated. Scales are glossy, except when shedding. Dorsal scales are slightly keeled.

Here are plenty of examples:

Adult: https://www.inaturalist.org/observations/22328888

Adult: https://www.inaturalist.org/observations/21876192

Adult: https://www.inaturalist.org/observations/26563543

Adult: https://www.inaturalist.org/observations/26563509

Adult: https://www.inaturalist.org/observations/26554782

Adult (Note locomotion): https://www.inaturalist.org/observations/26343884

Adult: https://www.inaturalist.org/observations/25771955

Transitioning juvenile: https://www.inaturalist.org/observations/17612993

Juvenile: https://www.inaturalist.org/observations/25962238

Juvenile: https://www.inaturalist.org/observations/25028649

Juvenile: https://www.inaturalist.org/observations/24786660

Juvenile: https://www.inaturalist.org/observations/23467841

The Northern Black Racer has a narrow head. The eyes are very large, and are separated from the nostril by three short scales. The only white on the upper labials is on L1. The tip of the nose is sharp, and brownish. The chin is typically white, and the belly is a blue-gray. The skin is gray, but scales overlap where skin is not visible. Scales are dusky. All scales are smooth.

Here are plenty of examples:

Adult: https://www.inaturalist.org/observations/24940095

Adult: https://www.inaturalist.org/observations/13592626

Adult: https://www.inaturalist.org/observations/13189733

Adults: https://www.inaturalist.org/observations/19227821

Adults: https://www.inaturalist.org/observations/23035814

Adult: https://www.inaturalist.org/observations/19227788

Adult (in shed): https://www.inaturalist.org/observations/17203474

Subadult (note "coachwhip" shape): https://www.inaturalist.org/observations/20410397

Transitioning juvenile: https://www.inaturalist.org/observations/26559348

Juvenile: https://www.inaturalist.org/observations/26997543

Juvenile: https://www.inaturalist.org/observations/15043658

Finally, posture and locomotion are good ways to identify at a distance. Racers tend hold their heads high and their long body tapers. This gives them a “coachwhip” like appearance. Ratsnakes only hold their body strait or kinked when moving, or on a narrow perch. When they are strait, the hold their head close to the ground, as long as they are not attempting to climb. When sitting, a Ratsnake holds a posture like a dropped piece of yarn.

Ratsnakes can move when they need to, but they are nothing compared to the Racers. To put it in simple terms, imagine a typical two-lane highway. The road is about twelve feet wide. A Ratsnake can enter the road, and exit the other side, in about six seconds. A Racer, going full speed, can enter and clear the road in less than two seconds.

Racer live a high speed lifestyle. They are so built for speed, Racers cannot constrict their prey. Instead, they pin down small animals and swallow them whole. This is very different from the Ratsnake. Ratsnakes are constrictors.

Thank you all who have submitted to the project, and are members following this project. Please, invite anyone who you believe would enjoy to join. I am excepting recommendations for the next times ID Tip. I hope everyone has a wonderful week!

Thank You,
-Ty Smith

Ingresado el 15 de junio de 2019 por tysmith tysmith | 0 comentarios | Deja un comentario
12613 icon thumb


Winter 2019 is amazing. Over the last week we have made some great observations! Harry, Lucy, Diana and Pam A have been hard at work uploading for months! Harry has been getting some terrific footage of fish up close- see goatfish feeding here(https://www.youtube.com/watch?v=Ib1IzbLu7Ec)
Just in the last few days we have seen a beautiful Green turtle close to Shark Island!. It seems quite fearless if we approach it carefully. See video here:( https://www.youtube.com/watch?v=GPfBUeWA5JA)

Today 15 June 2019 we were lucky enough to again see the highly camouflaged Angel sharks! We saw three swimming gracefully across the white sandy flats.

Then a small White spotted Eagle ray swam close by!! What a great few days! congratulations to Shelly Ocean swimmers for all your constant and meticulous uploading of observations!
Every observation is so important and this is great record of our area to show the seasonal changes!

317 species
220 species
208 species
186 species
180 species
The OBSERVATIONS leader board is as follows
1887 observations
825 observations
738 observations
689 observations
563 observations

Ingresado el 15 de junio de 2019 por pam_darook pam_darook | 0 comentarios | Deja un comentario

Taxonomy of Dewberries, Blackberries, and Brambles in Texas (Rubus spp)

I have basically identified my Rubus observations as R. trivialis or R. oklahomus, but I was aware there were other possibilities that I should look into. I've been looking closer at Rubus species in Texas this past 2 weeks. This journal post will walk through the musical score that is Rubus taxonomy yesterday, today, and tomorrow in Texas.

The Flora of North Central Texas, aka FNCT, (the primary flora key for DFW) listed 6 possible species in DFW: aborignium, apogaeus, bifrons, oklahomus, trivialis, and riograndis. iNat observations were in 14 species, so I knew we had some errors. I looked at all 14 species on BONAP to see which of those 14 were not documented in Texas at all. I manually added genus level IDs and comments to those (DFW) observations with the link to the map. Afterward, I went back and reviewed all of Texas observations and did the same for those.

I'll note here that if you upload an observation of a Rubus species, the ID suggestions frequently come up with species not in Texas as a first choice. (Ex. R. armeniacus.) Typically only 1 of the top 5 species recommendations is in Texas. It may even say "Seen nearby" since so many were mis-ID'ed.

If you browse the species maps for Rubus on BONAP you will count 227 species in North America. I kid you not. Or maybe it was 229. Or 224. I lost count. Fortunately, not all of those are in Texas, though. (USDA Plants Database is in line with BONAP.)

So I wandered over to Flora of North America, aka FNA, to see what they had to say about it. I'll give you the short version here: "Rubus, especially the blackberries, presents some of the most difficult species-level problems, because of polyploidy, apomixis, and hybridization. As a result, differences of opinion on the number of species to be recognized from a given region can vary tremendously... R. K. Godfrey (1988) wrote, 'oversimplification appears to be the only way to achieve a practicable solution to the dilemma.'" (I'll agree with that!)

The FNA key lists about 25 species for all of North America. I looked at every single one and the distribution ranges to find all of the species in Texas. They only list FIVE: bifrons, flagellaris, pascuus, pensilvanicus, and trivialis.

Another hop over to Plants of the World Online, aka POWO, (which iNat uses to determine synonyms and currently accepted names) was aligned with FNA. (R. riograndis is treated as R. trivialis in FNA, but not in POWO, so that will be our 6th.)
Which brings me to...

Here are a list of the synonyms and their currently accepted names for just the DFW species listed in FNCT:
R. aboriginum --> R. flagellaris
R. apogaeus --> R. flagellaris
R. bifrons --> No change
R. oklahomus --> R. pensilvanicus
R. trivialis --> No change
R. riograndis --> No change

These changes will bring iNat taxa in line with FNA and POWO and their state range maps, but it will require you to know the previous name to look at county maps on BONAP (which was last updated online in 2013/14.)

You will begin to see some curation changes on iNat affecting Texas Rubus species, to bring us into agreement with FNA and POWO, as listed above.

To summarize, all of TEXAS only has 6 possible Rubus species:
trivialis, and

This means R. allegheniensis and R. fruticosis are not valid TX species under any source.

Any observations ID'ed otherwise would be 1) a species not in Texas according to the simplified species list of FNA and PONO, 2) a cultivar, or 3) an old synonym that needs to be curated to the simplified list.

As a next step, I hope to put together a VERY simplified illustrated guide to the 3 most common Texas species: R. trivialis, R. flagellaris, and R. pensilvanicus. The purpose will be to give a quick and dirty way to differentiate those, as well as suggestions on what photos would help for a species-level ID.

Ingresado el 15 de junio de 2019 por kimberlietx kimberlietx | 10 comentarios | Deja un comentario

Casually exploring

I’m exploring here and there...when I can. Still taking pictures and posting again.

Ingresado el 15 de junio de 2019 por dna_55555 dna_55555 | 0 comentarios | Deja un comentario
16395 icon thumb

National Pollinator Week

Next week--June 17 to 23--is National Pollinator Week, and what better way to contribute to pollinator conservation than to document native pollinator species for the ESNPS? You can help determine how New York's native insects, which have co-evolved with native plants for thousands of years, are handling the threats of pesticides, habitat loss, and the climate crisis by contributing your observations here.

There have been some interesting observations rolling in, despite the wet and generally uncooperative spring weather. Many people estimate that Mother Nature is about two weeks behind schedule. Summer seems genuinely around the corner, though, and as temperatures warm and the sun makes multi-day appearances, insect activity should pick up. Grab your camera and be ready for it!

Find registered Pollinator Week events here: https://www.pollinator.org/pollinator-week.

Ingresado el 15 de junio de 2019 por mattschles mattschles | 0 comentarios | Deja un comentario
5894 icon thumb

Increase in reports of sick sea lions linked to domoic acid toxicosis, experts say.

Marine wildlife rescue groups have been responding to an increase in sick sea lions over the past few weeks.

The Channel Islands Marine & Wildlife Institute (CIMWI), which covers Santa Barbara and Ventura counties, says the animals are showing signs of domoic acid toxicosis.


Ingresado el 15 de junio de 2019 por biohexx1 biohexx1 | 0 comentarios | Deja un comentario
5531 icon thumb

How People Saved the Seabirds of the California Current.

The San Francisco Bay Area is bordered on the west by the California Current, one of five upwelling-driven “boundary currents” on Earth where the vast majority of the world’s fishery harvests occur. These boundaries are the edges of major oceanic gyres, like the North Pacific Gyre in the case of the California Current. The incomparable productivity of these stretches of ocean are generated by strong, persistent winds that bring the upwelling of nutrient-rich water from the depths into the sunlight where phytoplankton, the base of the food web, can thrive.


Ingresado el 15 de junio de 2019 por biohexx1 biohexx1 | 0 comentarios | Deja un comentario
7475 icon thumb

Lady Bugs.

Like so many every-day creatures, the lady bug is a pretty amazing creature with remarkable attributes. Michael Ellis explains.


Ingresado el 15 de junio de 2019 por biohexx1 biohexx1 | 0 comentarios | Deja un comentario
44568 icon thumb

Why Everybody Is So Excited About 23 Salmon.

After millennia of migrating to and from the sea, Chinook salmon disappeared from California’s San Joaquin River 65 years ago. Now they’re trickling back.


Ingresado el 14 de junio de 2019 por biohexx1 biohexx1 | 0 comentarios | Deja un comentario
21000 icon thumb

Los Angeles is building an urban wildlife crossing.

Caltrans authorities working in Los Angeles County are pushing toward creating a $60 million wildlife crossing that will allow urban animals to roam throughout the region's mountainous geographies. The 165-foot by 200-foot crossing would span over US Highway-101 and Liberty Canyon in the city of Agoura Hills.


Ingresado el 14 de junio de 2019 por biohexx1 biohexx1 | 0 comentarios | Deja un comentario

Clarifying Ancestor Disagreements

What is the Community Taxon?

Every observation with at least one identification has what we call an Observation Taxon. This is the label shown at the top of the observation page and is the taxon that the observations is "filed under" on the tree of life.

The Community Taxon (also sometimes called the Community Identification) is a way to derive a single identification from multiple identifications provided by the community. If an observation has more than one identification, it will also have a Community Taxon. The Observation Taxon will match the Community Taxon unless: (a) the observer has opted out of the Community Taxon, (b) there is an identification of a finer taxon that hasn’t been disagreed with (more on disagreements shortly).

Identifications hang on nodes on the tree of life. An identification adds an agreement with that node and also all of that nodes ancestors back to the root of the taxonomy.

If two identifications are on different branches of the tree of life, they each count as an agreement for the branch they are on and a disagreement for every node on the other branch back to the common ancestor of the two branches.

Each node is scored with the cumulative number of Agreements (i.e. the identifications on it or its descendants), the total number of Disagreements (from identifications on other branches), and something called "Ancestor Disagreements" which we’ll describe shortly.

The Community Taxon is the finest ranked taxon with at least two agreements where the ratio of the number of agreements to the sum of agreements, disagreements, and ancestor disagreements is greater than ⅔.

In contrast, the Observation Taxon is the finest ranked taxon with at least one agreement that has no disagreements. The Observation Taxon will match the Community Taxon if: (a) there are no taxa with agreements and no disagreements finer than the Community Taxon, or (b) the taxa with agreements an no disagreements finer than the Community Taxon is of rank subspecies. If the observer opts out of the Community Taxon, the Observation Taxon will always be the Observer's identification.

What are Ancestor Disagreements?

So what are Ancestor Disagreements? If one person adds an identification of one node and another person thinks it’s not that but can’t provide an alternative on another branch, they might add an identification of an ancestor of that node. For example, I might add an identification of Seven-spotted Lady Beetle, but you might add an identification of the family lady beetles, which contains that and many other species.

When the Community Taxon was first implemented, any identification made after previous finer identifications in time was implied to be a disagreement with these finer taxa. These ‘implicit ancestor disagreements’ are now labeled as such.

They only disagree with taxa associated with previous finer identifications. Also some bugs were fixed in how the Community ID charts on the observation page handle "implicit ancestor disagreements".

What are Explicit Disagreements?

Because of confusion about whether people were disagreeing or not, we later made ancestor disagreements "explicit". When an identification is made that is an ancestor of the Community Taxon (or the Observation Taxon if there’s only one identification), the identifier is now presented with a choice to indicate whether they are disagreeing with the Community Taxon or not.

If they are not disagreeing, their identification does not count as an ancestor disagreement for the taxon that was the Community Taxon.

And the identification is not labeled as a disagreement:

However, If they are disagreeing, their identification counts as an "explicit ancestor disagreement" with the Community Taxon.

And the identification is labeled accordingly:

Two ways to disagree...

When we implemented this, we thought that ancestor disagreeing should disagree with the entire branch below the disagreeing identification i.e. “I disagree that this is Seven-spotted Lady Beetle *and* all taxa on the branch between Seven-spotted Lady Beetle and the taxon I have proposed”. Let’s call this the “Branch Disagreement” way to disagree.

We’ve since come to realize that our communication about this was inconsistent and confusing, based on numerous discussions with community members in person and in the Forum. Furthermore, these discussions suggest the community interprets disagreeing as just with the Community Taxon i.e. “I disagree that this is Seven-spotted Lady Beetle but not the whole branch below the taxon I have proposed”. Let’s call this the “Leading Disagreement” way to disagree. We’ve also since realized from the Forum that Leading Disagreement is a more common and less controversial way to disagree than Branch Disagreement.

At the end of this post, we’ll discuss planned changes to improve things moving forward. But for now, let’s try to clarify our communication describing how things are currently behaving to all get on the same page.

Imagine the following sequence of identifications:

Branch Disagreement tallies disagreements as follows:

Which differs from how one would tally disagreements for the Leading Disagreement case:

Notice that this can impact how the Community Taxon is calculated. In this example, Branch Disagreement computes the Community Taxon as Lady Beetles Family:

While Leading Disagreement would compute it as Asian Lady Beetle:

The site is currently assuming Branch Disagreement as it calculates the Community Taxon. We tried to capture the language for the Potential Disagreement question to distinguish "not disagreeing" with "branch disagreeing" as:

To more precisely capture how the Community Taxon was being calculated this could have been worded something like:

Likewise, Ancestor disagreement identifications could have been more precisely labeled something like the following to reflect how the Community Taxon is being calculated.

Planned changes to distinguishing the two ways to disagree

While we hope the above description will help clear up much of the confusion with how iNaturalist is handling explicit ancestor disagreements, we’ve also learned that these two ways of disagreeing (branch and leading) are distinct and both useful. While "leading disagreement" is clearly the most commonly-used way to disagree, we still think that "branch disagreement" is useful, particularly in enabling the community to stop observations from becoming too finely identified beyond where the community can be certain.

We’re working on changes that would enable identifiers to indicate which way (leading or branch) they are disagreeing. The Potential Disagreement prompt will have three questions:

Here the first orange button would mean a "leading disagreement" and the second would mean a "branch disagreement".

Likewise, "leading disagreement" identifications will be decorated as:

and "branch disagreement" identifications will be decorated as:

Apologies for the length of this post, but we hope it clarifies some of the confusion about how the "ancestor disagreement" functionality is currently working and planned improvements to address concerns expressed in the forum.

Ingresado el 14 de junio de 2019 por loarie loarie | 12 comentarios | Deja un comentario

Vision Model Updates

iNaturalist currently uses vision models in two main places: 1) a private web-based API used by the website and the iNaturalist iOS and Android apps, and 2) within the recently updated Seek app. When Seek 2.0 was released in April, it included a different vision model than we were using on the web. At that time the web-based model was a third-generation model we started using in early 2018. That web-based model was trained with the idea it would be run on servers, and servers can be configured to have far more computing power than a mobile device. As a result that model was far too large to be run on mobile devices.

Early this year, with an updated Seek in mind, we started another training run with two main goals: shrinking the file size of the model, and allowing it to recommend taxonomic ranks other than species (e.g. families, genera, etc.).


The mobile version of the model needs to be small in terms of file size to minimize the amount of data app users would need to download. Smaller models can also be used by more devices as they need fewer resources to run (e.g. memory, battery), and can generate results faster, which is important for Seek's real-time camera vision results. These models take a lot of time and money to train, so we also wanted a model that could be simultaneously trained to produce a large web-based version and a smaller version for use in mobile devices.

Unfortunately, shrinking the file size like this slightly decreased model accuracy compared to the larger web-based version (kind of similar to image compression), and we found that was an unavoidable tradeoff. We take this into account when processing the model results, and on average for a similar error rate, the mobile version might recommend a taxon at a higher taxonomic rank than the web-based version. The taxon results we show to users shouldn't be less accurate, but they may be less specific.

More Species Represented

We wanted the model to include more species data, even when some species don't have enough photos to be recognized as species level. There are some species with a small amount of photos that, if we trained on that small set of photos, likely wouldn't have enough information for the model to reliable recognize those species.

Our 2018 model only included taxa at rank species. We set a threshold for number of photos, and species below the threshold were not included. We could still recommend higher taxa by doing some post-processing of results, but the model itself would only assign scores to species. In our latest training run we allowed the photos from species under the threshold to be rolled up into their ancestor taxa until the threshold was reached, and we allowed the model to assign scores to these non-species nodes. This allows more species to be represented in this newer model, sometimes at the genus level mixed up with photos of other species in the genus under our threshold. Now instead of not knowing anything about these species, the model can at least identify the genus or family, etc.

Replaced Web-Based Model

On May 24 we replaced the existing web-based model from 2018 with the web-based version of the 2019 model used by Seek. You may have noticed taxa higher than species starting to appear in vision suggestions, and this is why. That means the iNaturalist iOS and Android apps, and web vision suggestions have all been using this new model for the last few weeks. As of right now we are using the same model everywhere. The model has a web-based version (used by the website and iNaturalist apps) and a mobile version (used by Seek). The two versions are from the same training run, but can produce slightly different results because of compression in the smaller mobile version, and because the web-based version can weight results based on nearby species occurrences.


By adding photos of more species, we hoped to see an increase in accuracy for observations for species less represented in iNaturalist observations. One way we thought to get insight into that is to look at identifications made through vision suggestions that are current or improving (good) vs withdrawn or maverick (maybe less good). Here's a chart of such identifications for flies (Diptera) and spiders (Arachnida). The dotted red line represent with the web-based model changed. The difference isn't glaring, but it does look like for these groups vision-based IDs are sticking more.

The model was also trained more recently, so we hoped to see an increase in accuracy for observations in countries that have added a lot of observations since 2018. Here's a chart comparing the accuracy of the older model to the new model for a sample of random observations in California, Europe, Oceania, and South Africa (we could/should have included more countries with different observation and species densities, but these still show the trend). In this chart, "Right" means the model's best suggestion was consistent with the actual observation taxon (it suggested the right taxon or its ancestor), "Wrong" means the best suggestion was inconsistent with the actual taxon, and "Unable to determine" means the model was not confident enough to make a suggestion.

For observations from California, the models get nearly the exact same number right, with the older model making more specific suggestions. For observation from Europe, again the two models get nearly the same amount right, but this time the new model makes the more specific suggestions. In Oceania, the new model is getting more right and is more specific. And looking in South Africa, the new model gets a lot more right, with nearly double the amount of correct species recommendations (and fewer wrong).

Finally, the new model can now suggest taxa higher than species beyond the suggested common ancestor we've always had. This means the vision suggestions will be a mix of species and higher taxa. Here's a chart of the rank of all vision-based identifications over the last month or so. Nothing really stands out in this view of the data - there are maybe more identifications recently, and you can maybe see more at rank genus (the larger yellow bar).

By removing identifications at rank species, it’s clearer there have been more vision-based identifications of higher taxa since the new model went into effect.

By going even further and remove ranks below order, it's clear that there's been a vast uptick in vision-based identifications at these ranks. It should be noted that on May 31 the Seek app started to allow observations to be submitted to iNaturalist, and as explained above Seek will tend to recommend taxa at higher ranks than the web-based vision of the model, and we can see these higher taxon identifications really pick up after that. Better to have accurate but broad identifications, than inaccurate species identifications.

So that's an update on iNaturalist's vision models, and why some things may have appeared to change recently, like the addition of non-species recommendations. We think these changes are overall for the better, and hopefully you agree. We're interested to hear you thoughts. Did anyone notice the change? Now that you know the model should perform better for less observed species, I'd be interested to hear people's experiences with different taxa, or in different places.

Ingresado el 14 de junio de 2019 por pleary pleary | 9 comentarios | Deja un comentario

An alligator is swimming in a Texas lake with a knife in its head.

The American alligator populates nearly every swamp, lake and river (and occasional kitchen) in the southeastern US. But when Erin Weaver spotted one swimming near her Houston home, she suspected it was the one in danger.
"It looked like a steak knife that was sticking out of his head," she told CNN affiliate KTRK.


Ingresado el 14 de junio de 2019 por biohexx1 biohexx1 | 2 comentarios | Deja un comentario

Identification Guide: Zizeeria, Zizina, Zizula, Spot the Difference

(sorry for the pun)

Ingresado el 14 de junio de 2019 por cabintom cabintom | 1 comentarios | Deja un comentario

Identification Guide: Easily Confused Spialia in Central Africa

Also note the differences in the HW discal bands.

Ingresado el 14 de junio de 2019 por cabintom cabintom | 2 comentarios | Deja un comentario

Identification Guide: The Phalanta of mainland Africa

Ingresado el 14 de junio de 2019 por cabintom cabintom | 4 comentarios | Deja un comentario
36890 icon thumb

Goodbye spring, hello summer!

Thank you if you've already headed out to your local forest, or joined a Big Forest Find event, to record wildlife.

It'd didn't come as a big surprise to us that bluebells were the most recorded species through spring. Wildlife records for commonly occurring species are as important as rare species to monitor environmental change and protect habitats into the future

As we head into the summer months our forests are now alive with life and it's a great time to get out and see what you can discover - particularly look out for birds and dragonflies.

If you haven't already remember to put the date of a local Big Forest Find event in your calendar: www.forestryengland.uk/100/big-forest-find#join

Ingresado el 14 de junio de 2019 por rupertb-fc rupertb-fc | 0 comentarios | Deja un comentario
44371 icon thumb

Fungi as "flora"?

I don't want to step on an botanical toes (roots?), but do humbly propose that fungi are included in this project. To briefly justify: their distribution, taxonomy, and phenology is in need of study, and their ecology is often tightly linked to that of plants. Much of Panama's fungal diversity remains undescribed, and few mycologists are working to resolve this. Perhaps including fungi here could be a gentle reminder to make fungal observations when possible in a way that can contribute to mycological work down the road.

Ingresado el 14 de junio de 2019 por pkm pkm | 0 comentarios | Deja un comentario

Malaysia Check List

Added around 14 plant names from Flora Malesiana website into Malaysia Check List:

Ingresado el 14 de junio de 2019 por tansh91 tansh91 | 0 comentarios | Deja un comentario