Scientists Try Listening to Learn about Wildlife
2023-10-20
LRC
TXT
大字
小字
滚动
全页
1A 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.
2When scientists want to measure new forest growth, they can study large areas of land with tools like satellites and lidar.
3But understanding how fast and in what amount wildlife is returning to an area is more difficult.
4Sometimes it requires an expert to listen through sound recordings and pick out animal calls.
5Jorg Muller is a field expert on birds at the University of Wurzburg Biocenter in Germany.
6He wondered if there was a different way.
7Muller 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."
8So, he turned to bioacoustics, which uses sound to learn more about animal life and the environments in which they live.
9The tool has been used by scientists for some time.
10But more recently, researchers are using it with computer learning to study large amounts of data more quickly.
11Muller and his team recorded wildlife sounds at sites in Ecuador's Choco area.
12The environments they recorded included areas that were once used for agriculture and raising livestock to old-growth forests.
13They first had experts listen to the recordings and index the sounds of different animals.
14Then, they examine the sound quality to measure the environment.
15Finally, they ran two weeks of recordings through an AI computer program trained to understand 75 different bird calls.
16The program was able to pick out the calls on which it was trained.
17However, scientists wondered if the program could correctly identify the number of different kinds of plants and animals in each environment.
18To see if the program could do that, the team used two different controls.
19One 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.
20Since 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.
21But it was still able to correctly measure biodiversity levels in each environment, the study said.
22The research was published recently in Nature Communications.
23The study said the scientists' results show that the AI program is a powerful tool to measure the recovery of animal communities in tropical forests.
24The research noted that biodiversity found from recordings can be quantified in a cost-effective and complete way.
25And it said that it can measure environments, "... from active agriculture to recovering and old-growth forests."
26There are still areas for improvement, including the lack of animal sounds on which to train AI models.
27And the method can only capture animals that use sound to communicate.
28I'm Gregory Stachel.
1A 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. 2When scientists want to measure new forest growth, they can study large areas of land with tools like satellites and lidar. 3But understanding how fast and in what amount wildlife is returning to an area is more difficult. Sometimes it requires an expert to listen through sound recordings and pick out animal calls. 4Jorg Muller is a field expert on birds at the University of Wurzburg Biocenter in Germany. He wondered if there was a different way. 5Muller 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." 6So, he turned to bioacoustics, which uses sound to learn more about animal life and the environments in which they live. 7The tool has been used by scientists for some time. But more recently, researchers are using it with computer learning to study large amounts of data more quickly. 8Muller and his team recorded wildlife sounds at sites in Ecuador's Choco area. The environments they recorded included areas that were once used for agriculture and raising livestock to old-growth forests. 9They first had experts listen to the recordings and index the sounds of different animals. Then, they examine the sound quality to measure the environment. 10Finally, they ran two weeks of recordings through an AI computer program trained to understand 75 different bird calls. 11More recordings needed 12The program was able to pick out the calls on which it was trained. However, scientists wondered if the program could correctly identify the number of different kinds of plants and animals in each environment. 13To see if the program could do that, the team used two different controls. 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. 14Since 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. But it was still able to correctly measure biodiversity levels in each environment, the study said. 15The research was published recently in Nature Communications. 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. 16The research noted that biodiversity found from recordings can be quantified in a cost-effective and complete way. And it said that it can measure environments, "... from active agriculture to recovering and old-growth forests." 17There are still areas for improvement, including the lack of animal sounds on which to train AI models. And the method can only capture animals that use sound to communicate. 18I'm Gregory Stachel. 19Agence France-Presse reported this story. Gregory Stachel adapted the story for VOA Learning English. 20_________________________________________________ 21Words in This Story 22lidar - n. a remote sensing method that uses light in the form of a pulsed laser to measure ranges (variable distances) to the Earth 23gap - n. a missing part 24quantify - v. to find or calculate the quantity or amount of (something) 25diversity - n. the quality or state of having many different forms, types, or ideas 26conservation - n. the protection of animals, plants, and natural resources 27tropics - n. the part of the world that is near the equator where the weather is very warm