In her PhD study, BAT biologist Kadambari Deshpande performed overnight recordings of BAT echo call in the Western Ghats. “Good Night” will generate about 30 GB of data through 11-hour recording of the bat detector. To process the data, DeShpande will undergo several minutes of recording, scanning bat calls every millisecond, and noting down the species and other information about its behavior and ecology.
“It took me 11 months to process the data for 20 nights,” Deshpande said. “Batechomon will probably give it to me in a few hours.”
Batechomon is the abbreviation of “BAT echolocation monitoring”, an autonomous system capable of detecting and analyzing BAT calls in real time. This is the first in India developed by Deshpande and Vedant Barje under the guidance of Jagdish Krishnaswamy, part of the long-term urban environment and sustainability college of the Indian Institute of Human Settlement in India (IIHS), the Indian Institute of Environment and Sustainability in Bengalurululu.
Deshpande is a postdoctoral fellow at the Observatory and School; Barje, who leads the Wild Technology Project at the Wildlife Conservation Foundation, is a consultant there.
According to Deshpande, Batechomon marks a new chapter in BAT research in the country. The monitoring system allows the hand ruling scientists (scientists who study bats) to “go beyond data processing and ask interesting questions about BAT ecology”.
“It will help people transition to bat transitions in different parts of the country, allowing us to have more insight into the natural history and ecology of different bat species,” said Rohit Chakravarty, a bat researcher and conservationist at the Nature Conservation Foundation. ”
“I don’t know that there is any device with built-in recording as well as calling taxa internationally. If my knowledge serves me well, then Batechomon is a milestone in global BAT research.”
Bats in the machine
Bad Jomon is more than just a bat detector. In addition to the recording device, it also includes components that can record, store, process and analyze species bat activity. The BAT detector is just a specialized recording device that can convert ultrasound echo calls from insects and bats into human sounds. “exist [BatEchoMon]”AudioMoth is a popular low-cost ultrasound detector that has been configured as an ultrasonic microphone,” Barje said.
Batechomon is programmed to automatically activate at sunset, when the bats start flying and constantly listen to and analyze the audio. The device’s brain is a Raspberry Pi microprocessor, which processes data captured by AudioMoth. “It first separates bat calls from other ultrasounds, such as insect calls or artificial and ambient noise. Then, the peak frequency and structure of bat calls are analyzed to match known pretrained models, which helps identify bat species.”
“System usage [convolutional neural network] Barje added that the algorithm-based algorithm is a spectrum graph—a visual representation of the frequency of the audio signal that changes over time—and all detected audio records of the frequency of the call. The system also generates statistics at night, at night and when, and in which species, and when.
“Earlier, all of this required manual interpretation after a carefully planned data combing,” Deshpande said.
The Raspberry Pi and its associated machining components are enclosed in a box measuring 200 mm x 80 mm x 80 mm. Other auxiliary components in the device include solar panel plus battery and WiFi communication units for power and data transmission, respectively. According to Barje, the device can last up to eight days without the sun.
Batechomon also has a modular design, its battery, charging device and the ability to customize the levels of automation and data relays into the installed space.
“Suddenly it becomes possible”
Bat ecology and acoustics are a new field in India, with only a few bat researchers recording bat calls and analyzing them for ecological studies. There are few recordings submitted by Indians in global bat call databases such as Chirovox and Xeno-Canto.
Deshpande has been using BAT detectors since 2008 and has observed their evolution worldwide. She said that in Europe, detectors equipped with related software are saved by reference libraries for scientists a lot of time. Since then, she wanted to develop something similar, but has customized it for the more common insect bats in India.
An accidental meeting with researchers and engineers from her hometown in Nashik, Maharashtra started the Batechomon Project. “Meeting [Barje] It just completely changed the whole idea. Suddenly, this becomes possible. ” Deshpande said.
The duo went through many iterations, tried different microprocessors, algorithms and power solutions (which, according to Barje, was a “big challenge”) before they could reach the current version of Batechomon. Their main goal is to include all the required features in a user-friendly low-cost package.
According to Barje, Batechomon’s core system costs one-third of the cost of advanced detectors and similar systems. However, he did not want to disclose the exact number.
Key Challenges
Over the past few months, Batechomon successfully completed the pilot test on Nashik’s IIHS website. The team plans to test it over longer and under different conditions and test the device in certain users outside the organization.
“Everyone has their own experience with acoustics and different species. So, ultimately, we want colleagues to test it themselves and share their experiences so that we can improve existing systems,” Deshpande said.
The main obstacle to bat nerves is the limited availability of references for calling in many bat species. “Currently, the system can identify six to seven common Indian bat species. Further, we want to include as many bat species as possible,” Deshpande said.
They also said they hope to identify species common in urban, suburbs and human-decorated forest areas in their current form. The main challenge is to create strong training datasets to build good detection models for different species, which they hope to overcome by working with other BAT researchers.
Fortunately, according to Chakravarty, it is due to initiatives like the “Indian Bat Country” seminar by Indian researchers and the “Indian Bat Council” seminar for International Bat Conservation International.
“One of the key knowledge gaps identified by participants at the workshop was the lack of a thorough reference library,” he said. “We also need more funding to conduct surveys in different regions of the country. It will allow researchers to identify more species and collect more records of training datasets.”
Nikhil Sreekandan is an independent journalist.
publishing – April 14, 2025 at 05:30 am IST
