New article online: Comparison of passive acoustic soniferous fish monitoring with supervised and unsupervised approaches

Comparison of passive acoustic soniferous fish monitoring with supervised and unsupervised approaches

The Journal of the Acoustical Society of America 143, EL278 (2018)
https://doi.org/10.1121/1.5034169

Tzu-Hao Lin
Department of Marine Biodiversity Research, Japan Agency for Marine-Earth Science and Technology, 2-15, Natsushima, Yokosuka City, Kanagawa, 237-0061, Japan

Yu Tsao
Research Center for Information Technology Innovation, Academia Sinica, Number 128, Section 2, Academia Road, Taipei 115, Taiwan, Republic of China

Tomonari Akamatsu
National Research Institute of Fisheries Science, Japan Fisheries Research and Education Agency, 2-12-4 Fukuura, Yokohama, Kanagawa 236-8648, Japan

Passive acoustics has been used to investigate behavior and relative abundances of soniferous fish. However, because of noise interferences, it remains challenging to accurately analyze acoustic activities of soniferous fish. This study proposes a multi-method approach, which combines rule-based detector, periodicity-coded non-negative matrix factorization, and Gaussian mixture models. Although the three methods performed well when used to detect croaker choruses in quiet conditions, inconsistent results are observed in noisy conditions. A consistency matrix can provide insights regarding the bias of acoustic monitoring results. The results suggest that the proposed approach can reasonably improve passive acoustic monitoring of soniferous fish.

Advertisements

A new dive @ JAMSTEC !

From this month, I will start my new position at JAMSTEC as an international postdoctoral research fellow. At JAMSTEC, I will keep working on the soundscape-based biodiversity monitoring. Of course, most of the efforts will focus on marine ecosystem.

However, I do believe that the tools we developed should be able to facilitate the ecoacoustics researches in terrestrial ecosystems. So please contact me if you are interested in ecoacoustics or ecological informatics! I am very happy to collaborate with researchers from different disciplines!

從這個月開始,我將會從中研院資創中心轉換工作到日本國立研究法人海洋研究開發機構(JAMSTEC),擔任國際博士後研究員。在JAMSTEC我還是會持續以聲景為基礎的生物多樣性監測,只是大部分的時間都會主要專注於海洋生態系上(才不會不務正業…XD)。

不過,就如同我過去在資創中心進行的工作,我們未來開發的分析工具都還是會希望可以應用於各種不同環境,不管是海域或是陸域。如果是對於生態聲學、生態資訊學有興趣的朋友,都歡迎與我聯繫,我非常希望能夠和各種不同領域的研究人員一起合作、學習!

Monitoring of coral reef ecosystem: an integrated approach of marine soundscape and machine learning

Presented in International Symposium on Grids & Clouds 2018

Monitoring of coral reef ecosystem: an integrated approach of marine soundscape and machine learning

 Tzu-Hao Lin1, Tomonari Akamatsu2, Frederic Sinniger3, Saki Harii3, Yu Tsao1

1Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan
2National Research Institute of Fisheries Science, Japan Fisheries Research and Education Agency, Yokohama, Japan
3Tropical Biosphere Research Center, University of the Ryukyus, Okinawa, Japan

Coral reefs represent the most biologically diverse marine ecosystem, however, they are vulnerable to environmental changes and impacts. Therefore, information on the variability of environment and biodiversity is essential for the conservation management of coral reefs. In this study, a soundscape monitoring network of shallow and mesophotic coral reefs was established in Okinawa, Japan. Three autonomous sound recorders were deployed in water depths of 1.5 m, 20 m, and 40 m since May 2017. To investigate the soundscape variability, we applied the periodicity-coded nonnegative matrix factorization to separate biological sounds and the other noise sources displayed on long-term spectrograms. The separation results indicate that the coral reef soundscape varied among different locations. At 1.5 m depth, biological sounds were dominated by snapping shrimp sounds and transient fish calls. Although not knowing the specific source, noises were clearly driven by tidal activities. At 20 m and 40 m depths, biological sounds were dominated by nighttime fish choruses and noises were primary related to shipping activities. Furthermore, the clustering result indicates the complexity of biological sounds was higher in mesophotic coral reefs compare to shallow-water coral reefs. Our study demonstrates that the integration of machine learning in the analysis of soundscape is efficient to interpret the variability of biological sounds, environmental and anthropogenic noises. Therefore, the conservation management of coral reefs, especially those rarely studied such as mesophotic coral reefs, can be facilitated by the long-term monitoring of coral reef soundscape.

You can also check the slides of this talk.

Improving biodiversity monitoring through soundscape information retrieval

Presented in International Symposium on Grids & Clouds 2018

Improving biodiversity monitoring through soundscape information retrieval

 Yu Tsao1, Tzu-Hao Lin1, Mao-Ning Tuanmu2, Joe Chun-Chia Huang2, Chia-Yun Lee2, Chiou-Ju Yao3

1Research Center for Information Technology Innovation, Academia Sinica
2Biodiversity Research Center, Academia Sinica
3National Museum of Natural Science

Passive acoustic monitoring has been suggested as an effective tool for investigating the dynamics of biodiversity. For instance, automatic detection and classification of sounds can acquire information of species occurrences and behavioral activities of vocalizing animals. However, current methods of automatic acoustic identification of species remain uncertain for most taxa, which constrains the application of remote acoustic sensing in biodiversity monitoring. One challenge is that most of the training samples more-or-less contains undesired sound signals from non-target sources. To overcome this issue, we developed a source separation algorithm based on a deep version of non-negative matrix factorization (NMF). Using multiple layers of convolutive NMF to learn spectral features and temporal modulation of sound signals from a spectrogram, vocalizations of different species can be effectively separated in an unsupervised manner. Based on the pre-trained features, acoustic activities of target species can be efficiently separated from long-duration field recordings. Besides, spectral features of each vocalizing species can also be archived for further utilizations. In this presentation, we will demonstrate the application of deep NMF on separating sounds from different species for both birds and bats. Our results show that the proposed deep NMF approach can be used to establish recognition database of vocalizing animals for soundscape-based biodiversity monitoring, confirming its promising applicability for the field of soundscape information retrieval.

Improving the evaluation of soundscape variability via blind source separation

Presented in 174th Meeting of the Acoustical Society of America @ New Orleans, USA

Improving the evaluation of soundscape variability via blind source separation

Tzu-Hao Lin, Yu Tsao
Research Center for Information Technology Innovation, Academia Sinica

Tomonari Akamatsu
National Research Institute of Fisheries Science, Japan Fisheries Research and Education Agency

Mao-Ning Tuanmu, Joe Chun-Chia Huang
Biodiversity Research Center, Academia Sinica

Chiou-Ju Yao
National Museum of Natural Science

Shih-Hua Fang
Department of Electrical Engineering, Yuan Ze University

Abstract

Evaluation of soundscape variability is essential for acoustic-based biodiversity monitoring. To study biodiversity change, many researchers tried to quantify the complexity of biological sound. However, the analysis of biological sound remains difficult because the soundscape is made up of multiple sound sources. To facilitate the acoustic analysis, we have applied non-negative matrix factorization (NMF) to separate different sound sources in an unsupervised manner. NMF is a self-learning algorithm which factorizes a non-negative matrix as a basis matrix and an encoding matrix. Based on the periodicity information learned from the encoding matrix, biological chorus and the other noise sources can be efficiently separated. Besides, vocalizations of different species can also be separated by using the encoding information learned from multiple layers of NMF and convolutive NMF. In this presentation, we will demonstrate the application of NMF-based blind source separation in the analysis of long-duration field recordings. Our preliminary results suggest that NMF-based blind source separation can effectively recognize biological and non-biological sounds without any learning database. It can also accurately differentiate different vocalizing animals and improve acoustic-based biodiversity monitoring in a noisy environment.

以國際技術指引探討我離岸風場水下噪音監測評估適用方法

論文發表於2017台灣風能協會會員大會暨學術研討會與科技部成果發表會

以國際技術指引探討我離岸風場水下噪音監測評估適用方法

湛翔智、蕭婷宇、潘柔安
知洋科技有限公司

連永順、王珮蓉、胡芳瑜
工業技術研究院

林子皓
中央研究院

我國政府採「先示範、次潛力、後區塊」三階段離岸風電推動策略,示範獎勵辦法在2012年公告,評選出3案離岸示範風場,接著於2015年公告潛力場址,目前有超過20件開發案提出申請,首先均需通過環評審查。然而各項環評審查項目中,風場開發產生水下噪音對海洋動物影響的問題較為複雜,主要原因是水下噪音監測方法尚無國際標準,困難處是要在海上取得足夠且有效數據,必須有詳實規劃和充分準備,才能利用測量資料來分析水下噪音影響程度。歐洲離岸風電有超過10個國家投入開發,但各國有不同的水下噪音影響評估方式,其中以德國政府提出的技術指引,在監測要求與開發限制上較為嚴格。而歐盟自2008年提出「良好環境狀態(GES)」綱要,提供給歐盟成員國作為管制參考依據,包含離岸風能開發的監測與評估要求。美國投入離岸風能的前期研究多年,直到2016年完成首座風場正式商轉,同年也公告「海洋哺乳類動物聽覺技術指引」,將水下噪音對數種鯨豚的各種影響程度,制訂出水下噪音傷害管制門檻。本研究將探討國際上最新的水下噪音監測與評估技術指引,並依循國內離岸風場的發展情況,提出適用方式的建議供各界參考。

The government devised the offshore wind promotion strategy with 3 phases, which include Demonstration Incentive Program, Zone Application for Planning, and Zonal Development. The demonstration incentive program was announced in 2012, and three projects have been selected accordingly. Then, the Directions of Zone Application for Planning (DZAP) was announced in 2015. More than 20 projects have applied for the DZAP, and they are required to pass environmental impact assessments (EIA) to obtain the first step approval for construction. However, the impact of underwater noise on marine mammal during construction and operation phases are very complex. The key issue is that the underwater noise monitoring method has no international standards and it is difficult to measure sufficient and valid data at sea. Moreover, EIA needs very detailed planning and comprehensive preparation to obtain data and analyze the impact assessment from underwater noise. More than 10 countries in Europe already installed offshore wind farms and employ different assessment methods for underwater noise impact. The requirement of the German government’s technical guidelines for underwater noise monitoring and assessment is most rigid and strict. Since 2008, the EU has proposed the “Good Environmental State (GES)” framework for the member states to achieve requirements for the offshore wind energy development monitoring and evaluation. The United States announced the Marine Mammal Acoustic Technical Guidance in 2016, which provides several acoustic thresholds on different species of marine mammal. This study will discuss the latest international technical guidelines for underwater noise monitoring and assessment. Finally, we carried out the report included the applicable method of underwater noise monitoring and assessment based on the development of offshore wind farms in Taiwan.

論文全文 (pdf)

Deblending of simultaneous-source seismic data via periodicity-coded nonnegative matrix factorization

Article for IEEE MLSP 2017 DATA CHALLENGE

Deblending of simultaneous-source seismic data via periodicity-coded nonnegative matrix factorization

Tzu-Hao Lin, Yu Tsao
Research Center for Information Technology Innovation, Academia Sinica

Abstract

To increase the efficiency of seismic acquisition, one needs to break down the simultaneous-source seismic data into single source responses by a procedure called deblending. In this study, we employed the periodicity-coded non-negative matrix factorization (PC-NMF) to separate the primary and the secondary sources recorded in Petroleum Geo-Services dataset. Due to the application of random delay times between consecutive shots, the two sources displayed different patterns among various shots. By combining the response matrices of successive receivers, the PC-NMF can learn the basic components and group the basic components into two clusters according to the periodicity among shot index. Therefore, the deblending of simultaneous-source seismic data can be effectively achieved in an unsupervised manner.

The full paper can be accessed in IEEE DATA PORT.