For his doctoral investigation, Bat Kadambari Biologist undanded made night recordings of the calling of bats in Western Ghats. A “good night” would generate around 30 GB or 11 hours of recording with a bat detector. To process the data, undand would go through several recordings of one minute, scanning every millisecond for bats of bats and would take notes about the species and other information about their behavior and ecology.
“It took me for 11 months to process 20 nights of data,” said Undone. “Batechomon can probably give me that in a few hours.”
Batechomon, abbreviation for “Murciélagos Ecolocation Monitoring”, is an autonomous system capable of detecting and analyzing batter calls in real time. It is the first automated automated bat monitoring system in India, developed by Desshpande and Vedant Barje under the guidance of Jagdish Krishnaswamy, as part of the long -term urban ecological observatory at the School of Environment and Sustainability), Ben’s Institute Fortute Fory.
DSHPande is a postdoctoral fellow at the Observatory and the School; Barje, who runs the Wildtech project at Wildlife Conservation Trust, is a consultant there.
Batechomon marks a new chapter for bat investigation in the country, according to Ubpande. The monitoring system allows chiropterologists, scientists studying bats, “go beyond data processing and ask interesting questions about the ecology of bats.”
“Not only will it lead to a softer workflow, but will help people to transition to bats registered in different parts of the country, which allows us to obtain more information about the natural history and ecology of the different species of bats,” said Rohit the Natevarty, ELID said, Elachert said.
“I don’t know any international device with a Bolt recording call classification unit. If my knowledge serves me well, Batechomon is a milestone in Bat research worldwide.”
The bat in the machine
Batechomon is more than a bat detector. In addition to a recording device, it includes components that can register, store, process and analyze the activity of species -shaped bats in the march. Bat detectors are only specialized recording devices that can convert ultrasonic ecolocation calls of insectivorous bats into an audible sound for humans. “In [BatEchoMon]Audiomoth, a popular low -cost ultrasonic detector, has a bone configured to function as an ultrasonic microphone, “Barje said.
Batechomon is programmed to automatically activate at sunset, some bats begin to fly and listen and continually analyze the audio. The brain of the device is a Raspberry Pi microprocessor, which processes the data captured by Audiomoth. “First, the calls of bats of other ultrasound, such as insects or anthropogenic and in in in in in in in in in in in in in in in in in in in in in in in in in in in in in in in in in in in in in in in in in in in in in in in in in in in in in in in in in in in in in in in in any of
“The system uses a [convolutional neural network] Algorithm based on doing this, ”added Barje. The device output is a spectrogram, a visual representation of the frequencies of an audio signal as it varies over time, or all the calls of dedicated bats, together with the audio records. It has been more active during the night, what species it was active when, and so on.
“Previously, all this had to be interpreted by the craft, after combing through data hours,” said Undone.
The Raspberry Pi and its associated processing components are locked in a box that measures 200 mm × 80 mm × 80 mm. Other auxiliary components in the device include a more battery panel and a WiFi communication unit for the power supply and data transmission, respectively. In the absence of the sun, the device can last up to eight days, according to Barje.
Batechomon also has a modular design, and its battery, load device and the level of automation and data relay can be customized in the space in which it is installed. But the team was reluctant to reveal more about the configuration process at this time.
‘Suddenly, it became possible’
Bat Ecology and Acoustics is a nascent field in India, with only a handful of bat researchers who record calls from bats and analyzing them for ecological studies. The global databases of calls from bats such as Chirovox and Xeno-Canto have few recordings presented by Indians.
DSHPande has been using bat detectors since 2008 and has observed its evolution throughout the world. In Europe, he said, detectors equipped with the associated software and reference libraries have saved scientists a lot of time. Since then, he wanted to develop in a similar, but personalized way for insectivorous bats that are more common in India.
A casual meeting with a research partner and engineer from his hometown in Nashik, Maharashtra, began the Batechomon project. “Meeting [Barje] He only revolutionized all the thought. Suddenly, it became possible, “said undand.
The duo went through numerous iterations, testing different microprocessors, algorithms and power solutions, a “great challenge”, according to Barje, before reaching the current version of Batechomon. Its main objective was to include all the desired functionality in a low -cost package easy to use.
The Central Batechomon system costs a third of advanced detectors and similar systems, according to Barje. However, they do not want to reveal exact numbers.
The main challenge
In recent months, Batechomon has successful the pilot tests completed in a IIHS site in Nashik. The equipment plans to test it for longer and several conditions, as well as to test the device with selected users outside the organization.
“Everyone comes with their own experiences of acoustics and different species. Therefore, we would like our colleagues to try it for themselves and share their experiences so that we can improve the existing system,” said Ubpande.
The main obstacle to Batechomon is the limited availability of reference libraries for calls from many bat species. “Currently, the system can identify six to seven species of common Indian bats. In the future, we would like to include as many bat species as possible,” said Uncandande.
They also said that they hope that the device in their current form can identify species commonly seeing in urban, peri -urban and modified forest areas. The main challenge is to create robust and robust training data sets to make good detection models for different species, a challenge that they expect to overcome collaborating with other Bat researchers.
Fortunately, collaborations between Indian researchers are improving because or initiatives such as the workshop of the “State of the Bats of India” carried out by the Nature Conservation Foundation and Bat Conservation International, according to Chakravarty.
“One of the key knowledge gaps identified by the participants in the workshop was the lack of an exhaustive reference call library,” he said. “We also need more funds to conduct surveys in different parts of the country. It will allow researchers to identify more species and gather more recordings for training data sets.”
Nikhil Sekekandan is an independent journalist.
Published – April 14, 2025 05:30 am isth
