Local | PANORAMA

To formulate and implement, based on science, the Master Plan of Changbaishan Reserve

Changbaishan UNESCO Biosphere Reserve has established an effective management system. The Changbaishan Conservation and Sustainable Development Zone Administration Committee is the decision-making body, and under it is the Changbaishan Reserve Management Bureau, which consists of a management office and relevant operational departments responsible for the daily management of the park. It also includes a Expert Committee and a Community Committee, who also participate in decision-making and policy formulation.Changbaishan Reserve engaged representatives of the stakeholders, the public, and the rights-holders in the amendment of the Reserve’s management regulations and conservation-related work. Changbaishan Reserve values comments and suggestions from stakeholders. Extensive consultation was held with right-holders and stakeholders in major decision-making and planning, and adopted any sensible suggestions.

Local

East Europe

Addressing marine invasive alien species in Turkish seas

Mehmet

Gölge

Formulation of an effective national policy framework on IAS

Capacity building, knowledge and information-sharing systems to address the IAS threats

Investment in sustainable management, prevention, eradication, and control of IAS and restoration of IAS-degraded habitat at key marine and coastal areas.

East Europe

Addressing marine invasive alien species in Turkish seas

Mehmet

Gölge

Formulation of an effective national policy framework on IAS

Capacity building, knowledge and information-sharing systems to address the IAS threats

Investment in sustainable management, prevention, eradication, and control of IAS and restoration of IAS-degraded habitat at key marine and coastal areas.

Delopment of the SIREN App

Fisher using SIREN

AMMCO

This building block is to explain how I developped an App that allow fishers to contribute to marine science knowledge in Africa.

Initially we gave fishers a pre-printed form to report opportunistic sightings they encountered. However, the form was getting lost most of the time.

We decided to move to a digital solution. The existing App by then required internet to work and was just too complicated for fishers. So we thought we shoud develop an App that will be more userfriendly for fishers.

We wrote the algorithm (workflow) of the App and then contracted an Indian development company to write the code.

Later we had to bring the development of SIREN back to Cameroon to reduce the cost of developement.

We work with volunteer around the world that will continuously support with the development of the SIREN

passion and determination
availability of seed fund to develop an initial version of the SIREN App
Collaboration with local App developpers
Extending the collaboration to international volunteers
understand

The first developper company I contracted for the development of SIREN was a foreign company based in India. The cost of develpment was very high and there was a lot of miscomunication due to language barriers. When we started working with local developpers, the cost of development decreased importantly and it was easier to communicate.
Before giving a smarphone to fisher for data collection you must develop a trust relationship with him before otherwise the phone will never be used by the fisher to report sightings.

Documentation and dissemination of results

Capacity Development through Technology Training

Student training

creative commons

Student presentation

creative commons

Student presentation

creative commons

Student training

creative commons

Student presentation

creative commons

Students on field

creative commons

Students on field

creative commons

Team of students in charge of developing the algorithm

creative commons

Students on field

creative commons

This building block emphasizes the importance of training students and local actors in advanced technologies for conservation purposes. In Bio-Scanner, students from the Universidad Politécnica de Yucatán are trained in using AI algorithms, camera-trap data processing, and decision-support tools, fostering a new generation of professionals equipped to address biodiversity challenges.

The purpose of this building block is to build local capacity by providing hands-on training in cutting-edge technologies. This ensures that local actors can independently use, maintain, and replicate the solution in other contexts while fostering professional development among students.

Enabling factors:

Access to training resources and mentoring from experts in AI and conservation.
Collaboration with academic institutions to recruit and support students in applying their skills to real-world projects.
Ongoing support and capacity-building to ensure trainees can effectively use the tools and scale their applications.

Practical, hands-on training is more effective than theoretical approaches in building capacity for conservation technologies.
Partnerships with academic institutions provide a sustainable pipeline of trained professionals for long-term conservation efforts.
Regular follow-up and support after training help trainees apply their skills effectively and adapt to challenges.
Integral overview of the project, helps trainees to gain an overall vision of the entire initiative and notice the impact of their work in the project.

Documentation and dissemination of results

Local

Subnational

Collaborative Partnerships for Conservation

Collecting data on field

creative commons

Selecting data on field

creative commons

Symbolical signature of Tech4nature Mexico Phase 2

creative commons

Collecting data on field

creative commons

Training on feline characteristics

creative commons

This building block focuses on the establishment of strong partnerships between academic institutions (Universidad Politécnica de Yucatán), local governments (Secretaría de Desarrollo de Sustentable del Estado de Yucatán), and conservation organizations (International Union for Conservation of Nature and Natural Resources), private sector (Huawei), and local communities (Dzilam de Bravo) to enhance the collection and analysis of biodiversity data, access to technological infrastructure, government program instrumentation and application, and local ownership and execution.

The purpose of this building block is to foster cooperation among diverse stakeholders to ensure the effective implementation of conservation technologies. These partnerships enable the sharing of resources and expertise, empowering local actors to participate in conservation projects and creating a framework for sustainability.

Enabling factors:

Strong engagement and alignment between stakeholders, including academic institutions, government agencies, conservation organizations, private sector and local communities.
Signed agreements that define clear roles, responsibilities, and benefits for all parties involved.
Access to local knowledge and expertise to ensure the relevance and effectiveness of conservation actions.

Transparent communication between stakeholders is crucial to build trust and ensure the long-term success of partnerships.
Including academic institutions fosters innovation and provides opportunities for student involvement in meaningful projects.
Government involvement helps to create conservation policies and facilitates execution in the community.
Partnerships with conservation organisations strengthen the scalability and visibility of conservation initiatives by pooling resources and knowledge.
Community of Dzilam de Bravo provides data on field and by taking ownership of the project, they contribute to efficient project execution
Private sector provides infrastructure and expertise to facilitate the development of the technology

https://www.forclimate.ai/tech4nature

Advanced Image Recognition Algorithms for Jaguar Monitoring

Siames autoencoder architecture

creative commons

Dense siamese network trainning results

creative commons

Gradient cam

creative commons

Algorithm implementation

creative commons

Individual detection results

creative commons

Individual similarity results

creative commons

This building block is centered on the use of Convolutional Neural Networks (CNNs), including Siamese and Autoencoder architectures, to detect and identify individual jaguars based on unique features such as rosette patterns and morphology. These algorithms process camera-trap data efficiently, reducing the time required for analysis and providing critical insights for decision-making in conservation.

The purpose of this building block is to enhance the monitoring and understanding of jaguar populations by automating the identification process. The algorithms detect jaguars in camera-trap images and classify individuals, contributing to understanding population size, distribution patterns, and behaviors. This facilitates conservation planning and policy-making by decision-makers. Additionally, the models are scalable and can be adapted to other species and ecosystems, expanding their applicability beyond the Yucatán Peninsula.

Enabling factors:

Availability of high-quality camera-trap data for training and validating the algorithms.
Technical expertise in AI and machine learning for developing and fine-tuning models.
Collaborative partnerships with local institutions for field data collection and algorithm design, development and testing.
Access to sufficient computational resources to train and deploy the algorithms effectively.

High-quality and diverse datasets are critical for achieving accurate and reliable results.
Community and academic involvement, such as the participation of the Dzilam de Bravo community and the Universidad Politécninca de Yucatán, enhances project outcomes by ensuring local capacity and ownership, and technological expertise to design the necessary algorithms.
Explainability in AI models (e.g., through Gradient Cam) is essential to build trust and ensure the results are accessible to decision-makers.

scientific divulgation article (page 25-29)

Geospatial Planning and Risk Mapping

Dynamic risk maps, built using GIS and geospatial analysis, identify high-risk areas and guide resource allocation. This tool can be used for urban planning, disaster risk reduction, or managing natural resources like water or land.

Regularly refreshed data on terrain, vegetation, and weather is crucial for accuracy.
Trained personnel must operate geospatial tools and interpret risk maps.
Risk maps should inform planning and resource allocation at local and regional levels.

The expertise is crucial to help you build the correct framework in order to be scalable.

Monitoring

Documentation and dissemination of results

Data Sources

The system combines data from drones, satellites, camera traps, and geospatial tools to create a comprehensive monitoring framework. This approach can be adapted for other environmental challenges, such as flood monitoring, by integrating relevant data sources specific to those contexts.

Reliable access to real-time data from sensors, satellites, drones, and cameras is critical.
High-quality sensors and data processing systems must be available to collect and analyze diverse data types.
Systems must use compatible formats to integrate data seamlessly.