export_ofoct.com

[00:00.44] A team of scientists is studying the sound of the forest in Ecuador to learn how artificial intelligence (AI) could follow animal life in recovering environments.

[00:16.97] When scientists want to measure new forest growth, they can study large areas of land with tools like satellites and lidar.

[00:28.72] But understanding how fast and in what amount wildlife is returning to an area is more difficult.

[00:38.30] Sometimes it requires an expert to listen through sound recordings and pick out animal calls.

[00:47.40] Jorg Muller is a field expert on birds at the University of Wurzburg Biocenter in Germany.

[00:56.76] He wondered if there was a different way.

[01:01.02] Muller told the French news agency AFP: "I saw the gap that we need, particularly in the tropics, better methods to quantify the huge diversity... to improve conservation actions.”

[01:18.40] So, he turned to bioacoustics, which uses sound to learn more about animal life and the environments in which they live.

[01:29.90] The tool has been used by scientists for some time.

[01:34.97] But more recently, researchers are using it with computer learning to study large amounts of data more quickly.

[01:45.39] Muller and his team recorded wildlife sounds at sites in Ecuador’s Choco area.

[01:53.40] The environments they recorded included areas that were once used for agriculture and raising livestock to old-growth forests.

[02:05.42] They first had experts listen to the recordings and index the sounds of different animals.

[02:13.44] Then, they examine the sound quality to measure the environment.

[02:19.56] Finally, they ran two weeks of recordings through an AI computer program trained to understand 75 different bird calls.

[02:31.60] The program was able to pick out the calls on which it was trained.

[02:36.96] However, scientists wondered if the program could correctly identify the number of different kinds of plants and animals in each environment.

[02:49.24] To see if the program could do that, the team used two different controls.

[02:54.83] One was from the experts who listened to the audio recordings, and the second was based on examples from each environment, which can be used to understand biodiversity.

[03:07.92] Since the amount of available sounds used to train is limited, the AI program could only identify one-fourth of the bird calls that experts could.

[03:26.85] But it was still able to correctly measure biodiversity levels in each environment, the study said.

[03:30.04] The research was published recently in Nature Communications.

[03:37.52] The study said the scientists’ results show that the AI program is a powerful tool to measure the recovery of animal communities in tropical forests.

[03:50.04] The research noted that biodiversity found from recordings can be quantified in a cost-effective and complete way.

[04:00.20] And it said that it can measure environments, “… from active agriculture to recovering and old-growth forests.”

[04:10.08] There are still areas for improvement, including the lack of animal sounds on which to train AI models.

[04:18.08] And the method can only capture animals that use sound to communicate.