Our goal is that our core portfolio of standardized training materials are delivered by female experts recruited from the local region, who we further engage in mentoring and leadership activities. By centering these role models throughout our programming, we provide our participants with a vision of their future careers. We strive to foster an inclusive environment for honest dialogue and encourage ongoing mentorship even after the program concludes. However, the very gender gap we aim to address often presents a challenge when it comes to recruiting female educators and role models for our programs. This situation has helped us to differentiate three leadership roles: “mentors” (female role models, who participate in training and mentorship), “allies” (male trainers and facilitators), and “trainers” (support from international organizing team). Participation of each to these types of individuals is critical to develop and support our participants.

This program aims to equip women with practical skills that are actionable within their local context, enabling them to seize opportunities such as funding and career advancement within their specific regions. To achieve this, we collaborate closely with local partners and host institutions to adapt our core training materials, ensuring they align with local challenges, processes, and institutions. By tailoring our trainings to address the unique needs and contexts of the women we support, we maximize the relevance and impact of our programming. 

This building block leverages Declas, an open-source AI tool, to automate vulture monitoring. By analyzing images or videos, it detects and classifies species with high accuracy. The system eliminates manual counting, enabling scalable, cost-effective wildlife tracking. Users—researchers, rangers, or conservationists—simply upload visual data, and the tool generates real-time insights for informed decision-making. Built on YOLOv11 (Ultralytics) and trained on crowdsourced data.

The framework ensures that the AI model is robust and generalizable across different regions and habitats. Data collected is used to test the model’s ability to recognize vulture species in diverse conditions, providing feedback for further optimization.

The building block aims to automate vulture monitoring by developing a model to detect and classify four vulture species (Gyps africanus, Gyps coprotheres, Gyps rueppelli, Torgos tracheliotos) from visual data, reducing manual effort, speeding up analysis, and ensuring consistency. It leverages Google Colab Pro+ to run Python code and train the model on large image datasets, utilizing the Ultralytics package with YOLOv11 for vulture classification. Images are stored on a 2 TB Google Drive, sourced from the iNaturalist database via the rinat R package and supplemented by data from the Southern African Wildlife College and Endangered Wildlife Trust. The CVAT Team plan enables collaborative image annotation, allowing multiple users to label and export images with annotations for training and validation.

This building block democratizes access to cutting-edge technology, enabling scalable and cost-effective wildlife monitoring. Users can upload images or videos, and the application automatically detects and classifies species, providing actionable insights for decision-making.

The framework ensures that the AI model is robust and generalizable across different regions and habitats. Data collected is used to test the model’s ability to recognize vulture species in diverse conditions, providing feedback for further optimization.

The purpose of this building block is to automate the traditionally manual process of wildlife monitoring. The model works by analyzing visual data, detecting the presence of vultures, and classifying them into species with high accuracy. This reduces human effort, accelerates data analysis, and ensures consistency in monitoring.