Local | PANORAMA

Southeast Asia

Provision of Livelihood Benefit To Local Communities Through Co-Manage of Forest Reserve

Rio Peter

Gatulik

Identifying high-priority restoration opportunities and interventions through participatory ROAM processes

Through participatory Restoration Opportunities Assessment Methodology (ROAM) processes, TRI was able to outline restoration potential by identifying high-priority restoration opportunities, noting feasible restoration intervention types, and assessing finance and investment options. Activities identified included promoting the production of ecological charcoal, developing a plant production sector, and constructing water points in restoration sites. TRI conducted these ROAM assessments in three pilot sub-national landscapes, Waza, Mbalmayo, and Douala-Edea, where local and national stakeholders have been engaged. Pre-validation workshops occurred in each landscape with representatives of government ministries, local council representatives, local community representatives, and community chiefs, while a final report explaining the findings of the assessments was finalized in October, 2021 through a national validation workshop that included representatives from government ministries, international organizations, as well as local representatives and chiefs. Once finalized, a leaflet with the main findings was shared with stakeholders to quickly disseminate information and ensure those who do not have access to the internet can understand the ROAM assessments.

An inclusive and participatory assessment process allowed for findings and recommendations to appropriately consider and represent all of the present and relevant stakeholders. Comprehensive stakeholder consultation meetings included traditional chiefs, heads of community development institutions, local council representatives, women and youth associations, and individual innovators. They covered the needs of restoration, best uses of local knowledge, existing experience gaps, and ongoing restoration activities.

Overall, the participatory ROAM processes provided information on FLR opportunities and options. Through the assessments, TRI Cameroon learned what the priority restoration areas are, which restoration intervention types should be prioritized, what the costs and benefits of the different restoration types are, what the finance and investment options for restoration are, as well as what strategies exist for addressing major policy and institutional bottlenecks in the three pilot landscapes. These findings also presented lessons to be learned around how FLR actions could be modified in implementation on the field and provided real from-the-field data that could be considered in the elaboration of policy tools. Additionally, as one of the first activities undertaken by TRI Cameroon, the ROAM assessments were part of the learning by doing process and provided insight in how the participatory process could be better done in other landscapes.

Implementation

Local

Capacity building and informed decision-making for the monitoring of species

Domain of the male Bonelli’s eagle according to GPS locations

IUCN Centre for Mediterranean Cooperation / Francesc Parés & Rafael Bosch

Domain of the female Bonelli’s eagle according to GPS locations

IUCN Centre for Mediterranean Cooperation / Francesc Parés & Rafael Bosch

The implementation of the technical architecture and monitoring programme has ensured the availability of a big database of information both of the species and its environment. Data availability is key to ensure that park staff (managers, rangers, technicians, etc.) makes informed decisions when it comes to territory and species management strategies. Besides, the local design of the monitoring programme and the parameters within it, has increased the capacity of the park staff not only to manage it, but also to improve it and eventually apply it to the monitoring of different species and even other phenomena.

It is fundamental to ensure a co-design process, so that park technicians are not only the beneficiaries and end-users of the solution, but are also able to own and self-adapt the monitoring programme. To that end, an initial diagnosis of the capacities of the staff needs to be done, followed by specific training targeting the weaknesses that have been identified.

Currently, camera data is stored within the cameras themselves and technicians have to access and download the data manually. In order to fully implement this architecture, it is desirable to integrate a dual data storage device using both the device’s storage and a cloud service. The goal is to complete this integration to allow for an automatic process that reduces the time allocated to the monitoring process.

Monitoring

Local

Acoustic monitoring and analyses

Jaguar Spectrogram

Tech4Nature Mexico

The acoustic component of the project holds special significance, as it played a pivotal role in the automatic detection of over 138 species, with 95 of them being integrated into our pattern matching algorithms. This forms a robust foundation for the continuous monitoring of the region over the upcoming years, allowing us to observe how various environmental factors influence species presence

Our success in species detection was made possible through the data collected from the devices and the strategic partnerships we established, particularly with Rainforest Connection. Additionally, local experts played a crucial role in validating species presence.

The integrated passive acoustic monitoring combined with AI techniques allowed for the identification of 95 species. There is a positive correlation between species richness and low-canopy forest cover. Furthermore, the soundscape analyses revealed variations tied to different seasons and habitat types. However, the pilot encountered the challenge of limited training data for rare species. To mitigate this, we conducted multiple rounds of sensor deployment across various seasons.

Implementation

Documentation and dissemination of results

Local

Arbimon dashboard

North America

The Sustainable Yucatán Plan 2030

Ana

Quinzaños

North America

Provision Electric Vehicles in Yellowstone

Jose

Madero

International Symposium

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.

On the occasion of the third anniversary of the establishment of the Hainan Institute of National Park and the 8th international gibbon day (24th October, 2022), the Forestry Department of Hainan Province, Wuzhishan municipai government, Hainan green island tropical rainforest public welfare foundation, and Hainan Institute of National Park co-sponsored the “2022 tropical rainforest international conservation symposium” themed “protecting tropical rainforest·realizing ecological values”, which was supported by Eco Foundation Global (EFG).

The Conference reached the following concrete results:

Signing of the GGN Charter (Global Gibbon Conservation Network Charter).
l Announcement of the establishment of the first GGN Secretariat at the Hainan Institute of National Park, and the global launch of the GGN Logo.
This is the first of China’s first five national parks, the first domestic conservation research organisations initiated the establishment of international organisations for the protection of cherished species protection, which is of historical significance.
Publish the Global Gibbon Network the declaration of conservation in the form of GGN joining hands with IUCN SSA, with the gibbon as the representative.
Introducing the List of Priority Species for Conservation in Hainan Tropical Rainforest National Park with the case of KBAs, and officially releasing the List of Priority Species for Conservation in Hainan Tropical Rainforest National Park.

Implementation

Local

Recognition Modelling

The test results of the classifier performance. Where GMM represents the direct use of GMM as a classifier, not a Gaussian kernel

HINP

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.

There are many classifiers that ca be used for individual recognition. Considering the performances and possibilities of the classifiers, this research compared the classification effectiveness of three classifiers that have been developed considerably in the field of gibbon bioacoustics or human sound pattern recognition, i.e., (1) linear discriminant analysis (LDA), (2) support vector machine (SVM) and (3) GMM (classification by determining the similarity between the data to be measured and the existing data).

The basic method of sound pattern characteristics extraction has been identified, and a preliminary system method for individual sound recognition of Hainan gibbons has been established. Our preliminary results show that the existing system method is relatively reliable, and is to achieve the expected goals of the project. Among them, using pre + n×mR0 as MRU, extracting sound pattern characteristics using GMM fitting method, and using linear SVM for classification would be more effective. In the follow-up work, the data of rare individuals will be constantly supplemented, and design of the algorithm system will be improved, the ability of the classifier to recognise unknown individuals will be given, and the performance of the system will be comprehensively evaluated, so as to ultimately realise the recognition of individual sound of Hainan gibbons.

Local

Sound pattern analysis

Fic 2

HINP

Fic 1

HINP

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.

Mel-frequency cepstrum coefficients (MFCCs) is a method of extracting frequency envelope features by cepstrum after weakening the high-frenquency information on the basis of human hearing[1], which has a wide range of applications in the field of human and bioacoustics. In this study, MFCCs and the first-order and second-order differences (△、△2) are used to achieve automated feature extraction.

5 signature notes of the male Hainan gibbon have been identified (Fig.1), including boom note, aa note, pre-modulated note, modulated-R0 note, and modulated-R1 note.

According to the acoustic niche hypothesis, the calls of different species are differentiated in the time and frequency domains (see Fig. 2), so extracting features in a specific frequency range can greatly reduce the influence of noise, and the smaller the frequency range delineated, the more likely it is that more noise will be excluded. In addition, when the structure of each minimum recognition units (MRUs) is the same, the difficulty of recognition is greatly reduced.

In view of the above situation, in this phase of the research, we tried (1) applying pre only and (2) using pre + n×mR0 as MRU, respectively, and comparing the classification results so as to determine the most appropriate feature extraction in the subsequent work. In the case of voice annotation, all the above steps can be implemented automatically by R language code.

Implementation

Local