Conservation Edge AI Lab: Design a Real-Time Wildlife & Threat Alert System

To develop an AI-driven, real-time wildlife and threat alert system using edge devices and sensor networks that can automatically detect, classify, and flag potential risks (poaching, habitat encroachment, animal distress) to enable faster, data-driven conservation decisions and on-ground intervention.

• Introduce participants to real-world challenges in wildlife conservation, including poaching, human–wildlife conflict, and bycatch detection.
• Demonstrate how camera traps, sensors, and basic AI/ML models can be combined into a practical, field-ready detection workflow.
• Equip participants to prototype simple, interpretable alert rules that can run on edge devices with limited connectivity and power.
• Build system-thinking skills by mapping actors, data flows, devices, and policies for a conservation area.
• Embed ethics, governance, and community considerations into the design of AI-enabled conservation systems.
• Foster collaboration between ecologists, conservation practitioners, and technologists working on data-driven conservation.

• Undergraduate and postgraduate students in Wildlife Biology, Ecology, Environmental Science, Forestry, Geography, GIS/Remote Sensing, Computer Science, ECE, AI/ML, or related fields.
• PhD scholars, postdocs, and early-career researchers working on conservation, human–wildlife conflict, biodiversity monitoring, or environmental data analytics.
• Professionals from conservation NGOs, wildlife trusts, government departments, forest/wildlife agencies, protected area management, and impact-driven startups.
• Data scientists, engineers, and technologists interested in deploying AI/ML solutions in low-resource, edge-computing environments for conservation.
• Basic familiarity with programming and data handling (preferably in Python) is recommended, but no prior deep learning expertise is required.

• Understand how camera traps, sensors, and basic AI models can support wildlife monitoring and anti-poaching operations.
• Build a simple end-to-end wildlife detection pipeline using camera-trap images and a pre-trained model.
• Design and implement rule-based alert logic for prioritising threats (e.g., human intrusion, animals near boundaries).
• Gain practical insight into edge vs cloud deployment constraints: latency, connectivity, energy, and device limits.
• Develop a system design canvas for a real or hypothetical conservation area, including data flows, actors, and policies.
• Integrate ethics and governance into system design, addressing privacy, false positives, ranger workload, and safety.
• Take away reusable artefacts: Jupyter notebooks, alert logic templates, and a draft concept note for a deployable edge-AI conservation system.