Tuesday, March 10, 2026

Merlin in Japan, March 2026: the new age of bird watching III

 


Grrrrrrrrrrrrrrrrrrrrrrrrrrrrrrr TAX! … So sorry skipping last week for telling my forest adventure with AI. Anyway, this week is for my impression from Merlin in the nearby forests. First, you download the App from Apple Store or Google Play Store on your cellphone. To use the apps fully, please create your account in eBird and tell Merlin you’ll use your eBird account for Merlin. (More to it later.) And don’t forget you keep logging in both eBird and Merlin when you bird-watch with these two AI app. The starting page of Merlin would look like this (Sorry, in Japanese again).


The three icons in the middle of the page tell you the options we can choose to identify a bird somewhere near. From the left,


The icon is to identify bird (single or plural) with flow-chart. You report where you find this bird (address, or GPS data your cellphone report), time (calendar and time the cellphone report to the system), and, if you can see the bird, the size, the most prominent color of it, and finally the activity the bird is doing. When you report them, and tap Next, Merlin replies back the possible candidates based on your saying like this


A part of the list from my reporting.
I saw
Brown-eared bulbul and
Merlin reported back this.
An apparent mistake.

When none of the suggestions fit your sighting, Merlin gives you opportunities to adjust your reporting at the end of the suggestion page, like this

They are the items you reported.
Maybe the size I told Merlin was not exact …

You continue this exercise until you’re sure the bird you’re watching is “This,” just like searching in the pages of reference books. If you think none matches of your finding in the end, you click the bar (directed by the red arrow in above photo), and AI will remember the problem which will be utilized by the next identification exercise in its artificial brain.


The right logo (above) is to identify a bird by photo. I think the way of this approach is basically the same as the usage of picture reference books. AI Merlin sees the picture, searches its huge picture data book, and decides the most likely species for the image. In the training by Wild Bird Society, we tried it with ppt slide showing professionally taken phot of birds like this.



i.e. the bird shown was already identified by pros, and the photo was taken by a pro. Merlin replied to us exactly the “right” answer. For the above it was Eastern Buzzard (Buteo japonicus). The problem is, can we take the above level photo with our cellphone in a field when a bird suddenly comes out in front of us? That is the question, oh yeah. Maybe you have iPhone 17 Pro Max, and the machine will give you the best shot … lucky you. I’ve never tried it in the field. In any case, seeing a bird in a forest and taking a nice photo is difficult at best. The best way would be to sit down quietly, hold your cellphone steady (that would be difficult unless you use supporting gears), wait for a long long time until a bird comes in the frame, and press the shutter button of your cellphone at the right moment. Good luck.


So, the most useful approach to ask help from AI in forests should be the middle icon, which is recording the voice of a bird and Merlin identifies it from its audio data. We tap the icon, and Merlin starts recording.


Recording and thinking …

When AI recognizes the voice matching to the data from its database, it will suggest the identification result like


It surely is a useful tool when the condition is right. I mean, when we’re surrounded by noises, not only from transportation traffic, chatting with our friends, etc., but also of winds and the resulting creaking of swaying bamboos of Niiharu, or babbling stream of Tanzawa, Merlin cannot identify the voice. I also tried the audio data recorded by TASCAM, cleaned the noise with Audible to extract birds’ voice, and played the adjusted data in front of my Merlin. Nah. The artificial brain requires the best sound condition to function … There are much room for Merlin to improvement, I guess …

It says, in Japanese,
“No suggestion.”
At least Merlin is honest
telling us it has no idea
for the owner of the voice.

In any case, unless enough data is stored in its database, even if Merlin stays in the best condition to listen to birds’ voices it cannot identify the species correctly. We must help by trying many times and reporting the data. I suppose Merlin’s main database is eBird, and so we need to keep signing-in both. The process goes like this. When we think we’ve done the recording session, we stop the mike. Merlin will ask whether to store the recording in your cell phone. We tap “Store the data” button. Your sound data is stored in your phone as .wav file. Mind you. “.wave” file is large. Merlin certainly has a function to send this data to your email or cloud storage with “share” icon. But your storage will quickly be occupied by the recording, and you may find problems with the other tasks.

“Oh I know.
I think it is a voice from a long tailed tit,”
Merlin said.
Stop button is that red one
 in the middle of the screen.

“Save” button.

So, I just stored the data in my pixel and moved the data to eBird manually. I open my eBird account to report my findings with sound data. The way to upload sound data to eBird offers us two options. On is upload the data as “Soundscape,” and another is to designate a particular data for a specific bird. Even if we have only one recording, we can upload the data for all the cases like this.


But it is cumbersome way for reporting the result. Instead, we can upload the data just once for “Soundscape,” then edit the reporting memo like


We’ve done the recording, and keep crossing our fingers Merlin’s ability to identify birds will be improved using eBird database. I hope reporting process from Merlin to eBird becomes less burdensome someday soon. Let’s keep crossing our fingers. Playing with Merlin is not useless, I wish. But … not all agree with me, it seems.


Last month there was an annual symposium held by Tanzawa-Oyama Nature Restoration Committee. This year, the theme of the talks was to promote Nature Positive by mobilizing people power for data collection. The panellists were upbeat to use cell phones and aggregating reports in GBIF and iNaturalist. (eBird is feeding the data to GBIF.) But many audience (who were regulars for such gatherings, and so, it seems to me, veterans, aka senior citizen males) were VERY sceptical in the usage of AI and collaborate with the movement. One leader of an organization in Ebina City 海老名市 proudly said “We don’t care what’s going on in the other forests, and do not see the point of sharing our data globally by taking our time from learning whateva of AI and reporting our findings. What’s wrong with writing a private memo of our flowering, and keep it private?” The other attendees said “To begin with, we don’t trust such AI or something. We do not find the merit of using such. Our familiar way of using reference books must be the best.” The speakers of the meeting were all professors or senior researchers of Tanzawa who were staying in their laboratory normally and do not come out much from there, I guess. They looked a bit embarrassed by reactions from the congregation.

The occasion held a panel session as well.

Probably, it is just a matter of generation gap, and the incidence at the symposium is common when a new technology enters a scene. I simply hope Merlin will learn more and more, and someday soon we can use it more easily in our forest nearby. Let us see how things turn out.



If you have any questions about Yokohama’s Green Tax and Green Up Plan, please make a contact with

Strategic Planning Division, Green Environment Bureau, City of Yokohama
横浜市みどり環境局戦略企画課

Phone: 045-671-2712
FAX: 045-550-4093

Sunday, February 22, 2026

We Want to Help AI: How to report eBird, the new age of bird watching II




To use eBird, first you download the app and register yourself at eBird site by creating your account. Next, install the app and sign in. The first task you’re assigned is logging in to eBird with your account info. After clearing this, the app will ask your permission to use phone’s GPS info. You tap “Yes” then eBird shows you a suitable Bird Pack for your location. Bird Pack is the list of the bird for your location, say if you’re in Japan the list is for Japan. Please download the Pack of your choice, and you’re ready to report your bird-watching session to eBird. When you open eBird, you’ll find a bar at the bottom to start reporting.
 


You tap it, then it will show you the list of possible birds you could meet according to the GPS data of your phone, which may look like this. Sorry! It’s in Japanese and the bird pack is for birds in Japan. But you can choose the language at the very beginning with eBird. Also, if you do this in your place, the language will be adjusted accordingly, and I guess the place of bars etc on the screen is the same anyway.


Say, if you report you met five large-billed crow, you can scroll the list or tap in “large-billed crow” in the search bar of the above list. It comes like the below. The number in the box left of the “crow” is the number of birds you’ve met. You can either tap this square to increase the number (in this case five taps), or simply write “5” here. When you’ve done, tap the check in the bottom right-hand corner (yellow arrow), and the first step for reporting is done.


When you complete your reporting draft from the bird-watching session, tap the bottom right-hand corner with yellow arrow in the photo before the last. The screen will ask you to confirm the end of bird-watching session. To end the draft, please tap the bottom right-hand corner (yellow arrow in the below photo).


The screen proceeds to the next step to report your session to the database. First it will ask you if you name the place where you’ve done the observation session, in the third line from the top with “!” mark. You tap it, then the cellphone ask you if you want to name the place instead of latitude and longitude.


Whatever your choice, you tap when you confirm the location data, and the next step appears. First you say “Yes” if you report your observations to eBird database by tapping the bar of the yellow arrow in the below photo. After this, please tap “Send” bar for the red arrow. eBird will tell you your data has been sent to Cornell Lab.


The sent data will refine the list we downloaded at the beginning. According to the rangers of Wild Bird Society of Japan, people in Cornell will check if the data is worthwhile to believe it. If it passes the screening the reported result is added to the global data set. If the list includes some endangered species, and so it would be better to limit the people who can see the database for this bird with the reporting location, eBird automatically set the access for this info only to the reporter, so the rangers said. In any case, when the AI receives more data, the accuracy of its identification based on the data will become more reliable, or so I hope. The point becomes more important when we use to Merlin. I tell you my adventure with Merlin next week with magic wand, nope, via my cellphone.


If you have any questions about Yokohama’s Green Tax and Green Up Plan, please make a contact with

Strategic Planning Division, Green Environment Bureau, City of Yokohama
横浜市みどり環境局戦略企画課

Phone: 045-671-2712
FAX: 045-550-4093

Email: mk-kikaku@city.yokohama.lg.jp


Sunday, February 15, 2026

Hello AI: Merlin, eBird, and new age of bird watching?

 


The standard says winter to early spring is good for birdwatching. Especially in the forest of deciduous trees, leaves are absent during this season, which makes finding birds easier. Silence in winter forest is also helpful to listen chirping of wild birds. Waiting a bit for March, some early birds would start singing to find their mate while leaves are not yet fully opened. So far obvious, right? The next issue is, we often want to identify the bird when we find it in our birdwatching session.

Varied Tit

Not many people are satisfied with only watching / listening the birds. Almost naturally, next question arises. “What is the name of that bird?” This is a human tendency which would make Claude Levi Strauss grin. We start to learn the way to identify birds. I mean remembering characteristic look of species and checking youtube to search for that particular chirping or singing … You know the routine, don’t you? The difficult part is in applying what we’ve learned in the field. When their voice and look are very obvious like crows, we can say that bird is a crow for sure. But more often we start to discuss who’s the owner of this specific voice, or pretty brown feather. When we’re with a connoisseur the discussion could end quickly with a final voice from that person. Otherwise, we often conclude “Er … we don’t know.” Frustration.


My field guide to the birds, published by Wild Bird Society.
For Japanese birds, it covers more or less all.

So, if there is some help from AI or something, it is welcome. Some of you may know, there are several such apps that can connect its database to the photo or the sound from the microphone and tell us the name of the owner. The point is to learn how to use it. The other day in January, rangers of Wild Bird Society of Japan who station in Yokohama Nature Sanctuary held a weekend session to tell us exactly that. It was fun!

Er, it’s not bird’s nest, but a nest for Pallas’s Squirrel
 in Yokohama Nature Sanctuary.

By the way, the damage done by
the squirrels for Nature Sanctuary is serious.
 This tree is denuded by the animal
which ate the bark for their winter meal.
Surely, the tree will die soon.

Wild Bird Society of Japan collaborates with Cornnell Lab of Ornithology to promote the usage of eBird and Merlin to improve the database and ultimately promote the protection of avian species which globally observes alarming speed of extinction. To do anything, the first step is to learn the conditions of the thing, right? Having said that, the rangers said “The recognition of these apps are still limited in Japan. AI needs lots of exact data as possible. If the data eBird can accumulate is not big enough, the accuracy of Merlin’s search is not much either. Please join our global community to improve our data in Japan.” Well, OK. Corollary: the answer AI Merlin gives us is not reliable, but if we can feed in accurate data more, someday, probably soon, Merlin will become useful tool ... Alright. Let’s try. We have to start from somewhere, right?

Birds love such seeds during winter.
So, this spot in Nature Sanctuary could be
 a good place to wait for them to come.
Please be quiet …

And before that, for some of you not familiar with eBird and Merlin, I tell you about them a bit. eBird was a global database for birds whose custodian is Cornell Lab. I guess it was first created for professional researchers but quickly they decided to receive info from amateurs to accumulate enough data. So, it accepts reports of avians from anybody who accesses their reporting system and the pros in Cornell Lab check if the report has a certain level of accuracy. I guess if they received an input saying a person observed an Emperor Penguin in Waikiki Beach, the Lab sheds such report. Due to this history eBird is still more PC friendly for reporting than mobile phones. As the main usage of the database is for scientific research, I guess these characteristics of eBird with PC remain for quite some time. That’s that.

HP of eBird, Japanese version.
The detailed way to use them can be find in their HP.

And Merlin. This is an app suitable for mobile phones. You go to Apple Store or Google Play and download Merlin. Its usage is in the field. When you open the app, it gives you 3 choices for you to decide the identification method you use. The first one is to use question-and-answer type of sequence to have a list of possible candidates for a bird you’ve observed in the field. The second way is to open microphone in Merlin to let the AI analyze the voice of a bird. The third approach is to take a photo of a bird and let Merlin search for the possible candidates from that photo. When the Merlin concludes these analysis, we can send the result to eBird directly.

Merlin’s HP. The usage of it is explained in their HP.

So far, it sounds easy, as long as we are able to use internet. One big caveat in this AI approach for birdwatching is, we need internet to use especially Merlin. Hence, we cannot employ this approach in deep mountains like Yadoriki Water Source Forest where the cellphone coverage is VERY patchy at best. There is more even with internet. It’s due to the learning process of AI. More to it next week.

No internet here.

If you have any questions about Yokohama’s Green Tax and Green Up Plan, please make a contact with

Strategic Planning Division, Green Environment Bureau, City of Yokohama
横浜市みどり環境局戦略企画課

Phone: 045-671-2712
FAX: 045-550-4093 

Sunday, February 8, 2026

Snow

 


It’s snowing today in Yokohama.





But, spring is near.



If you have any questions about Yokohama’s Green Tax and Green Up Plan, please make a contact with

Strategic Planning Division, Green Environment Bureau, City of Yokohama
横浜市みどり環境局戦略企画課

Phone: 045-671-2712
FAX: 045-550-4093

Sunday, February 1, 2026

I Do Not Want to Inhale: Finding microplastics in Shonan Beach

 


So, one fine January morning, scientists for Kanagawa Environmental Research Center gathered us, the registered ESD instructors, in a beach where Shonan Bellmare soccer team trained themselves during off-season. It was a beautiful day. The beach volleyball players engaged in their daily training routine while neighbors brought their pooches for morning stroll. A scientist instructed us, “First we situate 40cm*40cm codrato on beach.” “Please aim the collection point along the line where tide reached max, then retreated. They leave the debris on sand.” OK.

We can recognize
how far the tide came at this point with debris.
Nearer to the sea, the tidal flow washed
the fragments several times and
the beach became “seemingly” smooth and clean.
40cm*40cm was like this.

“Next, please scoop the sand within the square for about 3cm deep, and filter the contents in the sieves. We use a combination of two sieves. Above is a tool of coarser mesh with 4.74mm2. Join up a finer sieve with 2mm2 mesh below. Microplastic has, by definition, the size of 5mm less in its longest length which is often the diagonal. 4.75mm mesh could let pass a particle of this size. The lower sieve would release smaller bits, which would be defined as nanoplastics. Collecting nanoparticles is totally different issue, so we skip it today.” Sure. Let’s start sand play!

Two-story sieve system

Ready …

Go!

On the line where the tide reached max, there were lots of fragments of wood, bamboo, hard pampas grasses, and garbage of apparently artificial materials. At the point where I collected the sand not many glasses, beer cans or cigarette butts were found. Maybe, that’s good news. We collected large trash from a codrato before start scooping. In the first sieve, there remained relatively large fragments of wood and shells, and we returned them to the sand. The below is where our target remained. We damped them in a (Ahem) plastic Ziploc and brought it to the lab.

The “above” sieve.

The “below.”
They contain the thing of probably more than 5mm in size.
But they could go through 4.75mm mesh.

You may think the selection for the point of codrato would measure the level of plastic contamination higher than the average of the beach. Scientists for the Center thought the same thing and they did exhaustive study for the same beach before. “We tried several points if there is the optimum point where we can collect the microplastics in the most efficient way. Our conclusion is statistically speaking there is not much difference among locations in one beach and the amount of sand scooped. This means microplastics are scattered evenly and widely without difference in depth. Operationally, it’s good news. To think about the level of contamination, it’s VERY serious finding.” Oh yeah.

Today’s catch.

We brought the scooped materials to the lab and sorted the contents into organic things and plastics by hand, er, by tweezers to be exact. In our bag, there was no apparent porcelain and glass bits or steel wires, so the “artificial” debris was all plastics. At a glance neon green or the like of artificial coloring was not found much. So, the first impression was “Nah, problem is not serious.” Not so fast, please. The problem was, the originally white or transparent plastics absorbed or were smeared by some chemicals during their stay in water, and changed their color into similar to organic woods or the like. Deception. So, we have to identify the thing which was

a) Unnaturally geometrical, and/or

b) Looked a bit strange. 

Category b) is somehow easier to understand, isn’t it? We just trust our gut instincts. 😉

“A bit strange” things are apparent, don’t you think?

The particle in a) category was tricky as the beach was full of tiny rocks polished into something round tiny pebbles. As we know their origin was huge volcanic rocks created by tectonic movements, like andesites and tonalites, in Tanzawa. So, even when they are tiny, they keeps their characteristics of volcanic mineral. We patiently separated such pebbles from the “catch.” The plastic particles remained after this check was once the contents of beads cushions or beloved teddy bears. The main body of them was already trashed, but the staffing = plastic beads came out from the sac, drained into the stream, and ended up in the beach. During this process, they were exposed to sea water and uv-light which turned their color from white/transparent to something “organic-kind” brown. When left as such in the beach, they will be broken into smaller bits and become nanoplastics, or smaller. As they are small and light, when the wave splash kicks up them with sea water into the atmosphere, they can float in the air and end up at the bottom of the lung of mammals, humans included. Anyone cancer? Stroke? Heart attack?

The pebbles from Tanzawa, and a shell.
I plan to make them into an accessory with resin.

Another “unnaturally” plastics we’ve find looked briefly like some shell of seeds. They have a shape after the contents inside were squeezed out. Scientists told us, “It’s plastic.” Originally, they were slow-release fertilizer used massively even in commercial farms. Inside was active ingredients that seeped into the soil and one day they became empty. After reaching this stage, they started to be washed into water stream over ground, to the river, then to the sea. “Ideally, farmers side dressing their crops according to the conditions of their product. But aging problem is serious for the ag community in our prefecture. The grandparents do not have the stamina to tend their field regularly. So, they apply fertilizer contained in the plastic sac to skip regular dressing.” i.e. The problems are in forests, like Yadoriki community, and end up with the sea contamination of microplastics. Hmmmmmmmmm.

For the remnants of slow-release fertilizer,
the bit shown by the arrow is
the most easily identified in this pile of microplastics.
But here, there are roughly 10 such plastic husk.
Could you identify them?

We can analyze such debris for its chemical properties.

The result. It’s acetylcellulose.

According to the scientist of the Center, for Kanagawa Prefecture the level of microplastic contamination is apparently higher along the coast of Sagami Bay compared with the beaches to the direction of Tokyo Bay. Kanagawa’s beach facing to Tokyo Bay is almost at the exit of the Bay. Moreover, there are not many rivers pouring in. In contrast, Sagami Bay has several rivers that run down the large human settlements. Scientists surmised if the origin of the contamination is from open Pacific Ocean, there cannot be such huge difference among locale. Their conclusion is the problem in the sea is coming from the rivers passing through the land. Forests are lovers for sea. So they say. But …

Of course, we now cannot do away with the plastics for our life. We understand senior farmers need any help to continue their farming life. But, there must be some way to prevent inhaling nanoplastics that could cause any serious diseases eventually … Difficult. At least, let’s be careful before throwing away the tattered teddy bear with plastic beads …




If you find environmental issues in Kanagawa Prefecture, especially in cities and coastlines, please make contact with

Kanagawa Environmental Research Center
神奈川県環境科学センター
1-3-39 Shinomiya, Hiratsuka City, 254-0014
〒254-0014 平塚市四ノ宮1-3-39
Phone: 0463-24-3311
FAX: 0463-24-3300 
https://www.pref.kanagawa.jp/docs/b4f/index.html