Acoustic Monitoring for Improving the Conservation of Critically Endangered Hainan Gibbon

From late November 2021 to early December 2021, the Hainan Institute of National Park (HINP) conducted field research in and around the five family groups (group A - E) of gibbons in the reserve with the participation of relevant experts and staff from the Bawangling Reserve. The research has set up 8 stationed sites and 21 surveillance sites, covering the habitat of each Hainan gibbon population, with 48 team members participating simultaneously.

Based on the research results, combined with the coverage of 4G signal, a set of domestic automatic sound recording equipment with 4G signal, which has a real-time transmission function (product model: LBird-01211) was installed in the typical environment of Hainan gibbons in the Bawangling Reserve.  

Import the raw data of sound into Adobe Audition 3.0 or Avisoft-SASLab Pro sound analysis software, resampled (Sample size: 44100 Hz; Window size: 1024 points), and then saved separately in WAV format. High-quality waveforms and sonograms were selected to measure characteristics of Hainan gibbons’ calls, to analyze the differences in acoustic indexes between individuals, and to build a database of Hainan gibbon sound patterns on an individual basis. Then, perform individual sound recognition using the implemented sound recognition model. Finally, the effectiveness of the sound acquisition is evaluated, and the accuracy of the sound recognition is assessed. Among them, the evaluation of the sound recognition effect is done mainly by comparing with the field research and other sound monitoring results.

The manual screening of 532 Hainan gibbon acoustic sample has been completed, including those obtained during tracking and observation of gibbons using a portable recorder and those obtained using an automated recorder. During the screening process, three recording qualities were initially categorized, namely hight, medium, and low. 44 high-quality recordings from seven individual callers were obtained. The seven individual callers were GAM1、GBM1、GBSA、GCM1、GCM2、GDM1、GEM1, where the letter after “G” represents the family group number and the letter after “M/S” represents the individual number of adult male/subadult male individual number. Only about 40.9% of the recordings were made manually. The raw files of all automated recordings were provided by the team of professor Wang Jichao, and the related data were backed up at Hainan Institute of National Park.

Due to the excessive number of features, a 10-fold cross-validated SVM-RFE was used to rank the importance of the features after extracting them, and then the features were added sequentially for LDA classification to record the change in accurancy with the number of features selected, and finally the best number of features was recorded as the input for the subsequent classifications (see Fig. 8). The highest accurancy for LDA classification was 89.2% (pre) / 95.6% (pre + n×mR0).

Since none of the MFCCs extracted with a fixed number of windows achieved better results than the GMM fitting method for LDA classification (6-window: 86.6%; 10-window: 88.5%; 100-window: <80%), we tested the effectiveness of the other classifiers using only the features extracted by the GMM fitting method. In this test, we randomly selected 20% of the data as the test set, and the rest of the data were used to train the classifier, which were repeated 10 times for each kernel function to record the distribution of the accuracy. Among them, the classification effect of GMM is poor when using only pre as MRU, while the effect is generally better than using only pre when using pre + n×mR0 as MRU. 

The symposium was guided by Foreign Affairs Office of Hainan Province, Department of Natural Resources and Planning of Hainan Province, Department of Ecology and Environment of Hainan Province, Forestry Department of Hainan Province; and supported by the big data lab of Research Institute for Eco-civilization, CASS, the research think tank of Research Institute for Eco-civilization, CASS, Institute of Zoology Chinese Academy of Sciences, Xishuangbanna Tropical Botanical Garden Chinese Academy of Sciences, Institute for Carbon Neutrality, Tsinghua University, Advanced Interdisciplinary Institute of Environment and Ecology, Huawei Technologies Co., Ltd., Hainan University, Hainan Normal University, Federation of Hainan Academicians, the Sanya Research Base of the Internation Centre for Bamboo and Rattan.

The two-day symposium focused on the theme of “conservation of the flagship species of tropical rainforests-gibbons” “conservation of tropical rainforests’biodiversity, and was held in a combination of online and offline activities.