| Project/Area Number |
19K21554
|
|---|
| Project/Area Number (Other) |
18H06491 (2018)
|
|---|
| Research Category |
Grant-in-Aid for Research Activity Start-up
|
| Allocation Type | Multi-year Fund (2019)
Single-year Grants (2018) |
|---|
| Review Section |
1002:Human informatics, applied informatics and related fields
|
|---|
| Research Institution | Japan Agency for Marine-Earth Science and Technology |
|---|
Principal Investigator |
Lin Tzu-Hao 国立研究開発法人海洋研究開発機構, 地球環境部門(海洋生物環境影響研究センター), ポストドクトラル研究員 (00824377)
|
|---|
| Project Period (FY) |
2018-08-24 – 2020-03-31
|
| Project Status |
Completed (Fiscal Year 2019)
|
| Budget Amount *help |
¥2,990,000 (Direct Cost: ¥2,300,000、Indirect Cost: ¥690,000)
Fiscal Year 2019: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2018: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
|
|---|
| Keywords | Soundscape / Information retrieval / Ecoacoustics / Machine learning / Deep sea / Underwater sound / Marine soundscape / Ecosystem dynamics / Bioacoustic diversity |
|---|
| Outline of Research at the Start |
Understanding the ecological pattern and variability is essential for the management of marine conservation. Soundscape, which contains biological, environmental, and human-made sounds, has been considered as a platform for the remote sensing of marine ecosystems. The purpose of this research is to integrate ecological knowledge in machine learning techniques for assisting the identification of underwater sounds. Outcomes of this project will facilitate the establishment of an open science platform of the marine soundscape, which allows international users to explore ecosystem dynamics.
|
| Outline of Final Research Achievements |
Soundscapes, which are composited by sounds of biological, environmental, and anthropogenic sources, have been considered as a remote sensing platform to monitor marine ecosystems. This project aims to facilitate the assessment of the spatial-temporal dynamics of marine ecosystems via soundscape information retrieval (SIR). During the project period, we developed techniques for audio visualization, source separation, and event identification. Long-duration recordings were collected from algal reefs, continental shelves, coral reefs, estuaries, and deep-sea environments. On the basis of SIR, single-channel audio can be transformed into multiple ecological dimensions, including the changes of acoustic environment, biodiversity, and anthropogenic interference. This project also enables the "Ocean Biodiversity Listening Project" and will further contribute a large amount of acoustic data for researchers who interest in using soundscape information for ecosystem monitoring.
|
| Academic Significance and Societal Importance of the Research Achievements |
Listening to natural sounds allows us to remotely acquire data of biodiversity and investigate the changes in response to human development. The outcome can help managers and stakeholders to use soundscapes in the ecosystem assessment and improve the decision making of conservation management.
|
