It's great that citizen science space for collecting ecological or biodiversity data is is growing. I'm curious why the consortium members behind Pl@ntNet are all French. Compare that to iNaturalist, which features partner organizations in 21 countries. That kind of widespread buy-in is attractive and I'm not sure what is limiting Pl@ntNet:
Personally I've found iNaturalist to be the optimum for me since it partners with 4 major Canadian organizations; it allows for local conservation authorities to have access to location data for vulnerable species observation. It's also every branch of the tree of life, not just plants, so it's allowed me to learn to identify more kinds of species.
> It's great that citizen science space for collecting ecological or biodiversity data is is growing.
As great as would be having less professional physicians, promoting cheap children soldiers instead professional ones or using trained monkeys to build the brakes of our car and manage the economy
The so called "Citizen science" means more amateurs and less professionally trained people really focused in solving real problems that are difficult and complex. Solutions that are required to survive at long term
But, yeah, lets assign this task to scholars in their spare time and we will have it for free. In the end what you will have is databases corrupted with fake data. A set of "true scientific facts" for democrats and another set of "true facts" saying exactly the opposite for republicans.
Biggest issue with inaturalist is the extremely limited scope of their api.
I'll be checking this one out, but inaturalist is extremely tight fisted with both their data and the service, which is extremely disappointing.There is a wide range of utility that could be built on it's back if it were open source.
Sadly, this tendency to keep the data proprietary instead of open is found in almost all projects, ususally because of simple US or European copyright reasons.
There are ways around this, for example in other countries the copyrights have expired, the copyrights don't always apply, people can be contacted and asked to waive copyrights and new pictures could be made to replace the copyrighted ones, etc. You can 'quote' much of the copyrighted material. There have been government (over)rulings of copyrights.
All that implies work that the citizen scientists can do as well.
The PlantNet Consortium is mostly made up of French organizations, which may be why it hasn't gained as much traction internationally. However, it's still a valuable resource for plant identification and data collection.
Plantnet is cool, but there's a lot of missed potential for adding discrimination questions. For example, when the result isn't clear-cut, it could ask you the standard identification questions and narrow it down to a specific species instead of making you guess based on photos.
I'd be willing to help you. The largest dychotomic key [1] is partially digitised but we could transform it into a proper dataset. Copyright no longer applies to part on the Flora. There are many other sources. I remember dychotomic key in hypercard [2].
Scanning 81 million science paper pdfs will yield most of the data in [1] and [2]. It would be possible to get a grant to make these transformations and add them to Plantnet and iNaturalist.
It is also possible to add DNA material to field observations. A DNA scanner cost around $1000 and attaches to laptops and cellphones so they could be used in the field. I'm not sure if amateurs can handle the software yet, but that could be fixed.
The most progress could come from my speciality: data mining scientific papers. This requires a few hundred terabyte of harddisks and a fast computer plus 2000 hours of programming. This would require a minimum of $20K or more in grants, crowdfunding or donations but it would yield an enormous boost of data.
Another addition could be scanning all the herbaria and botanical gardens, both photo's and DNA samples. Crowdsourcing by thousands of citizen scientist would be the way to go.
I've downloaded almost 2 million photo's from several bird, insect and plant databases this weekend and (partially) compared them with the Plantnet and iNaturalist datasets. And I looked at the dozens of other databases with mosses, lichen, bacteria, etc. Still, no where near the >8,7 million species of the world are in those databases.
The most complete list would be the plants of Europe (only a few thousand out of 400K species), most other regions and kingdoms are only partially identified.
As we can see from dozens of papers, new species have been found through the iNaturalist collecting. Making better software and more data would certainly boost the rate of new species discovery. And that is vital, as we are in the middle of the 6th mass exinction event of the last 570 million years. Species go extinct before we even have photographed or identified!
I also have my dad's Flora research photo's from 30 year field trips and my own, of which 3000 plants where identified with Flora Europeae dychotomic key (a day's work per flower).
Yes, I know of quite e list of libre sources, only some of which are digitised and online. So (continuously) exporting data from the hundreds of small observation or collection databases or going our and scanning the old offline materials would be what you could organize with better software.
There are also ways to increase the collection of libre data. You could auto-generate field trips for holiday makers or school trips. Give them an auto-generated itinerary leading them past places with flowers, insects or birds with a list of things they should look out for and photograph or determine with keys. Make it into a game like geocaching or a treasure hunt. You generate it based on individual tastes (walking, bicycle, car tour, camper, bustour), individual or group size, age and knowledge level, temperature, season, time of day, climate, location, etc.
The US Department of Fish and Wildlife has a really useful service called the Feather Atlas for identifying bird feathers by their color, size, and shape:
That's correct, there's plenty of incorrectly identified plants, but the app says 89% accuracy for the first result and 11% for the second, so it's hard to argue. I've many times encountered plants that don't in live in the UK but the app say they do.
The high accuracy results are not always, well, accurate. Several times I've had an 85+ percent result then looked closer and gone "ah shit, the leaf pattern is wrong, these are alternating instead of side-by-side" or similar.
Is this what iOS photos uses under the hood when it goes into plant detection mode? I was photographing some bugs on a plant in the garden yesterday and noticed a leaf annotation on the photo. It was accurate with the “Siri knowledge result” of cucumis. I wonder if Apple is contributing to this repository as it did with Open Street Maps if I understood that history correctly.
For species native to Europe there's the ObsIdentify app as well. It identifies not only plants, but birds, insects, mushrooms and other species groups too.
It would have been nice if they also provided info about the state of the plant you've got, e.g. needs more/less water, sun, etc.
I've got a payed app called PictureThis, which often misidentifies the plants, however have extensible sections for care and problem diagnosis and mitigation. I, however, cannot confirm if those are trustworthy, but it helped me cure some of my plants.
Hope this foss API (alongside their mobile clients) would expand with such info.
Mushroom Observer is the first that comes to mind, it doesn’t have an identification api but it does have tons of training data to build your own model
I use seek by inaturalist for plant identification [0]. It claims to support fungi identification also, but I have not used it for that personally. It's a very popular app, so perhaps someone else will offer their direct experience using it with fungi.
About two years ago, I posted mushrooms twice on iNaturalist (not Seek) and quickly got updates with a more specific identity from other users, so I think there is an active community out there. They were amanita muscaria -> american amanita muscaria and oyster mushroom -> summer oyster mushroom.
The only non-mushroom confirmation / corrections I've gotten on iNaturalist were a spider and a snail.
That said, it may be tricky to get a good identity on mushrooms. There are some varieties need spore prints or very careful attention to structure to identify.
- https://plantnet.org/en/plntnet-consortium/
- https://www.inaturalist.org/sites/network
Personally I've found iNaturalist to be the optimum for me since it partners with 4 major Canadian organizations; it allows for local conservation authorities to have access to location data for vulnerable species observation. It's also every branch of the tree of life, not just plants, so it's allowed me to learn to identify more kinds of species.