From the FECYT – SPANISH FOUNDATION FOR SCIENCE AND TECHNOLOGY and the “singing 2C, or not 2C” department comes this croaker of a press release from some researchers that have way too much time and grant money on their hands.
A classifier of frog calls for fighting against climate change
The sounds of amphibians are altered by the increase in ambient temperature, a phenomenon that, in addition to interfering with reproductive behaviour, serves as an indicator of global warming. Researchers at the University of Seville have resorted to artificial intelligence to create an automatic classifier of the thousands of frog and toad sounds that can be recorded in a natural environment.
One of the consequences of climate change is its impact on the physiological functions of animals, such as frogs and toads with their calls. Their mating call, which plays a crucial role in the sexual selection and reproduction of these amphibians, is affected by the increase in ambient temperature.
Jaime Bosch (MNCN-CSIC)
When this exceeds a certain threshold, the physiological processes associated with the sound production are restricted, and some calls are even actually inhibited. In fact, the beginning, duration and intensity of calls from the male to the female are changed, which influences reproductive activity.
Taking into account this phenomenon, the analysis and classification of the sounds produced by certain species of amphibians and other animals have turned out to be a powerful indicator of temperature fluctuations and, therefore, of the existence and evolution of global warming.
To capture the sounds of frogs, networks of audio sensors are placed and connected wirelessly in areas that can reach several hundred square kilometres. The problem is that a huge amount of bio-acoustic information is collected in environments as noisy as a jungle, and this makes it difficult to identify the species and their calls.
To solve this, engineers from the University of Seville have resorted to artificial intelligence. “We’ve segmented the sound into temporary windows or audio frames and have classified them by means of decision trees, an automatic learning technique that is used in computing”, explains Amalia Luque Sendra, co-author of the work.
To perform the classification, the researchers have based it on MPEG-7 parameters and audio descriptors, a standard way of representing audiovisual information. The details are published in Expert Systems with Applications magazine.
This technique has been put to the test with real sounds of amphibians recorded in the middle of nature and provided by the National Museum of Natural Sciences. More specifically, 868 records with 369 mating calls sung by the male and 63 release calls issued by the female natterajck toad (Epidalea calamita), along with 419 mating calls and 17 distress calls of the common midwife toad (Alytesobstetricans).
“In this case we obtained a success rate close to 90% when classifying the sounds,” observes Luque Sendra, who recalls that, in addition to the types of calls, the number of individuals of certain amphibian species that are heard in a geographical region over time can also be used as an indicator of climate change.
“A temperature increase affects the calling patterns,” she says, “but since these in most cases have a sexual calling nature, they also affect the number of individuals. With our method, we still can’t directly determine the exact number of specimens in an area, but it is possible to get a first approximation.”
###
References:
Amalia Luque, Javier Romero-Lemos, Alejandro Carrasco , Julio Barbancho. “Non-sequential automatic classification of anuran sounds for the estimation of climate-change indicators”. Expert Systems With Applications 95: 248-260, 2018.
It is possible their research is a result of being affected by the Hypnotoad:
We can’t forget about the internet meme of the ‘Alaskan Tree Frog” freezing in place for the winter.
With the attached cute Costa Rican tree frog photoshopped to have ice crystalls on his head.
There is of course a grain of truth to the frozen alaskan frog, but it doesn’t look like a tree frog. It is well prepared for winter as in wiggles down into the muddy ground, and yes it partially freezes and become immobile but that is its cycle.
These frogs sounding different in varying temps, maybe exactly what has been happening forever, temp swings of over 20 degrees I am sure have been happening everywhere and investigating their songs in normal swings probably wasn’t done until there was climate funding!
What a poster child study for how well peer review works. How could this study have been passed by reviewers when there is no way to obtain the conclusions from the data collected?
Temperatures vary by how much during 24 hours? How long do these frogs/toads have each day to call and mate at the correct temperature, 30 minutes. Have temperatures gotten so bad that instead of calling/mating at 4:00pm, there is no longer a time when the right temperature occurs during a 24 hour period? These are all things reviewers should have asked!
Which came first, the advocacy or the frog?
Maybe next they could load the frog up with a bunch of cocaine, like that chimp they’ve been doping up since the 70’s. Maybe a little LSD. Then play ‘Jeremiah was a bullfrog’ in the background and see what happens.
Makes as much sense as the original study!
I thought Jeremiah was only interested in a little wine?
I would not be so quick to dismiss this theory out of hand.
I have lived all of my 56 years in Temple, TX. There is only one species of Grackle (black bird) that lives in Bell county, TX.
Over time, I noticed that the mating call of the male grackles had changed. Their call used to be a complicated “Awk, awk, awk”, then an adulating “AH-ah-AH-ah-AH-ah” and ending with an “Ah-Awk!”
Mid 80s or so I noticed the grackles no longer sang their entire song.
They began to shorten it or to leave parts out. Only two beginning “awks” and leaving either the middle “AH-ah-AH” or “Ah-Awk” ending out.
It has only been in the last five years or so that the birds seem to be slowly returning to their old call. Using all three beginning “Awks” and adding back the other sections.
Only a few have returned to the entire old song as of yet but I will continue to listen.
A few years ago I read a study where the authors claimed that changes in ambient noise (cities getting louder) was causing bird songs to change and I first followed this line of thinking when considering how the grackles had changed their call.
But now they are apparently transitioning back to their previous song.
Temple has gone from a population of 35,000 in the late 1970s to close to 80,000 today.
I can’t see how Temple got first louder and then quieter as the population grew.
But what is curious is that the change in calls seems to have followed the shifts in the natural 60-70 year cooling/warming cycle.
The up/down/”back” radiation greenhouse gas energy loop of the radiative greenhouse effect theory is pencil on paper, a spreadsheet cell, a “what if” scenario and NOT a physical reality.
Without this GHG energy loop, radiative greenhouse theory collapses.
Without RGHE theory, man-caused climate change does not exist.
And with a snap of the fingers and “Presto!!” the bazillion dollar global climate change fantasy is suddenly unemployed.
Must be why nobody is allowed to talk about this possibility. Not newsworthy enough? Or too far outside the fake news narrative?
The good thing about this technology is that it can be used to detect temperature changes. No change in sound, no temperature change.
If the sounds don’t change, he has to publish the results anyway.
But…but….I thought the enviros were alarmed about frogs dying off.
If they’re not croaking like they used too, wouldn’t that be a good thing?
Have these researchers nailed down yet what is frog-speak for “not tonight darling, I’m feeling a bit cold” or “It’s simply too hot, I don’t have the energy”? Or maybe even “I don’t like to do it when humans are listening. The heat makes them smell bad and it puts me off”.
Joking aside, what I can’t see, in the abstract quoted at least, is an acknowledgement that the frogs might actually be communicating with each other, linguistically, about the environment. Put more simply, they might change something about their mating calls as the weather changes, and humans are not yet knowledgeable enough about the language of frog-love to tell the difference.
Warmer temperatures seem to be causing women to croak like frogs, as an epidemic of “vocal fry” — a pathological speech pattern characterized by speaking in the lowest voice register — infects their ranks.
Vocal fry inhibits women’s mating chances because it’s annoying as $#%@ur momisugly!
Perhaps Kristi can move solving this crisis to the top of her busy to-do list.
Vocal fry is everywhere. Here are excerpts from just a few minutes of NPR.
Beware. Once you hear vocal fry there is no un-hearing it.
Not quite as annoying as California up-talking where every statement ends with the inflection of a question.
I got up in the morning?
At 10:30?
Like earlier than normal?
And I went to the mall?
To get my nails done?
…
Rich Davis, replying to Max Photon
And they talk that way because today’s millinieums and teen-techno-university grads have been programmed out of making positive, facts-based statements to others. EVERYTHING has to be “peer-approved” and fit within a “safe space” in front of others! Thus, EVERYTHING, every sentence, and every statement made in public needs to be phrased as a question, so others hearing it are not “challenged” by any stray “fact” they “might” disagree with or be “offended hearing”.
omg, I never thought of that? Of course that’s your opinion? I’m not triggered by it though?
My 27 year old niece is a riot. She has a beautiful voice, but to amuse me she’ll combine nasal up-speak with vocal fry. It is just so damn funny.
Kim’s stepdad Bruce/Caitlyn OTOH goes the other way.
A normal culture seeks to emphasize sex differences, which process is a lot more fun and interesting. Perverted “culture” seeks to unisexize everything, which is sick, twisted and no fun at all.
“Taking into account this phenomenon, the analysis and classification of the sounds produced by certain species of amphibians and other animals have turned out to be a powerful indicator of temperature fluctuations and, therefore, of the existence and evolution of global warming.”
Have they tried using thermometers? it’s what put the frogmometers out of business.
I didn’t know whether to laugh or cry. Using auditory processing to identify frog species is pretty obvious, it’s how frogs do it and how we do it. Doing it computationally is a nice piece of engineering. But I used to live beside a river with lots of banjo frogs, and there is quite a lot of temperature variation over a night which really did not seem to bother the frogs. So what does the paper actually say? https://www.sciencedirect.com/science/article/pii/S0957417417307662 is not behind a paywall. A quick skim through it revealed a paper that does a pretty good job of explaining and evaluating their technique but has NOTHING to say about temperature or climate except this: we can detect/measure frog calls and frog calls are affected by temperature so we MIGHT be able to use our technique to tell something about climate some day maybe perhaps. They report no experiments relating to temperature whatsoever.
Richard,
The first four paragraphs of the intro are directly or indirectly about climate change. There is relevant research referenced in the citations. This provides context for the research presented in the paper, which is about a method.
“They report no experiments relating to temperature whatsoever”???
“However, sound production in ectotherms is strongly influenced by the ambient temperature (Bellis, 1957; Gayou, 1984; Gerhardt & Mudry, 1980; Márquez & Bosch, 1995; Pires & Hoy, 1992; Schneider, 1974; Walker, 1957, 1962), which can also affect various features of the acoustic communication system. In fact, the ambient temperature, once it exceeds a certain threshold, can restrict the physiological processes associated to the production of the sound, and may even inhibit behavior calls.”
An artificial intelligence has also been programmed to look at the effect of climate change on the clothing of human females. This clothing, which plays a crucial role in the sexual selection and reproduction of human beings, is affected by the increase in ambient temperature.
Taking into account this phenomenon, the analysis and classification of the clothes women are wearing has turned out to be a powerful indicator of temperature fluctuations and, therefore, of the existence and evolution of global warming.
To capture the changes in clothing worn by women, networks of video cameras are placed in places where women change their clothes. The problem is that a huge amount of video information is collected in environments as busy as a woman’s changing room, and this makes it difficult to identify the types of garments being worn.
To solve this engineers have resorted to artificial intelligence. “We’ve segmented the video into small clips and have classified them by means of decision trees before putting them on the internet.
This technique has been put to the test with real videos of women changing their clothes provided by the National Museum of Natural Sciences.
“In this case we obtained a success rate close to 90% when classifying the videos”. In addition to the type of clothing, the number of individuals observed in certain geographical regions like beaches can also be used as an indicator of climate change.
When temperature exceeds a certain threshold, the clothing worn by women becomes restricted, and the wearing of some types of clothing like coats is even actually inhibited. In fact, the clothing worn by both females and males is changed, which influences reproductive activity.
OMG Ian,
It’s so much worse than we thought! All those coatless bodies will surely inhibit all reproductive activities among the bipeds, don’t you think? Did you check with any biologists? Wait, why?
I heard some snarky comments from some climate D-nier that the work is invalid because a mere 40% of the cameras were set up in the shower stalls at health clubs. They’re absurdly referring to an urban nakedness island.
But clearly there’s a solution which I am here to offer. Reprogram the AI to focus attention on adjusting the raw data from the past, by programmatically adding shawls and heavy woolen sweaters in proportion to years in the past. To take an example from our Australian dataset, in 1970, beach-goers in Sydney were wearing trenchcoats, and in the 40s, head-to-toe woolen goods were prevalent as was the norm going back to the early 12th century. (We have proxies to detect patterns prior to the 1780s written record).
A few technical difficulties that we’re working through- seeing a strange counter-seasonal effect. It seems that even as temperatures are rising in North America in mid-spring, there is an inexplicable apparent cooling in Sydney. To prevent any errors, the Australian sensors will be moved to an indoor nudist camp, to more accurately reflect conditions averaged with our next closest station in Papua New Guinea.
Please keep us updated on your exciting work, I’m particularly interested in reviewing some of the raw data as you post it. I only read the abstracts though. It’s not the naked pictures.
Forgot to mention, this Toronto firm is working with us on the charts. https://www.nhl.com/mapleleafs