Smart Environmental Surveillance Using AI and Remote Sensing for Enforcement of Wildlife Protection Laws

Abstract

Smart environmental surveillance is increasingly important for protecting wildlife habitats and strengthening the enforcement of conservation laws against illegal activities such as poaching, deforestation, encroachment, and habitat destruction. This study proposes an AI- and remote-sensing-based environmental surveillance framework for automated wildlife monitoring and evidence-driven legal enforcement. The framework integrates multispectral satellite imagery, unmanned aerial vehicle observations, Geographic Information System data, and environmental indicators to continuously assess protected regions. Machine-learning and deep-learning techniques, including Random Forest, Convolutional Neural Networks, and YOLO-based object detection, are employed to identify land-cover changes, unauthorized human activities, wildlife presence, and potential habitat threats. Detected environmental violations are geotagged, temporally recorded, and mapped to applicable wildlife protection regulations to support regulatory investigation and enforcement. Experimental evaluation demonstrates that the proposed framework achieves 96.78% detection accuracy, 96.21% precision, 95.84% recall, and 96.02% F1-score, indicating reliable identification of environmentally suspicious activities. The novelty lies in connecting AI-derived remote-sensing evidence directly with legal compliance monitoring rather than limiting analysis to ecological observation. The framework contributes a scalable decision-support mechanism for conservation authorities, enabling faster violation detection, transparent documentation, and data-driven enforcement. Overall, the approach strengthens wildlife protection through intelligent, continuous, and legally actionable environmental surveillance.