AI Helps Predict and Prevent Elephant Poaching
A new artificial intelligence (AI) system developed by researchers at Cardiff University could significantly aid in the prevention of elephant poaching, specifically in the Malaysian state of Sabah. The innovative tool, called PoachNet, uses advanced machine-learning techniques to predict poaching risks by analyzing elephant movement data and understanding elephant behavior.
Image Credit: Pixabay from Pexels
PoachNet leverages deep learning, GPS data from elephants, and insights into elephant behavior to create a system capable of predicting poaching hotspots. The research, titled “PoachNet: Predicting Poaching Using an Ontology-Based Knowledge Graph,” published in the journal Sensors, outlines the system’s capabilities.
Naeima Hamed, a doctoral researcher from Cardiff University’s School of Computer Science and Informatics, explained the system’s operation. “Elephant GPS data is analyzed with a special type of AI—a sequential neural network—to predict their movements. These predictions are added to the knowledge graph in a meaningful way—then PoachNet uses a rule-based system to apply poaching rules and detect hidden patterns in the data. We found that, when tested, PoachNet was more accurate than other leading methods, consistently performing better. By handling the complexity of time and space data and turning predictions into practical rules, PoachNet offers a big improvement in tracking and protecting elephants.”
Professor Omer Rana, International Dean for the Middle East and Professor of Performance Engineering at Cardiff University School of Computer Science and Informatics, added, “PoachNet integrates semantically modeled regional data sources with emerging machine learning algorithms and semantic reasoning. This novel approach addresses a critical challenge impacting communities supporting endangered species. Climate change and economic pressures are significantly affecting the relationship between human activity and natural habitats. The data-driven approach adopted in PoachNet can be generalized to support similar localities and national parks, enabling more efficient use of law enforcement and government resources.”
Professor Benoit Goossens, director of the Danau Girang Field Centre and Professor at Cardiff University’s School of Biosciences, highlighted the urgency of the situation: “Habitat loss, human-elephant conflict, and poaching threaten Bornean elephants. Despite global anti-poaching efforts, the illegal ivory trade continues to drive poaching, reducing the population to fewer than 1500. We hope that PoachNet can assist in poaching prevention methods, therefore helping to ensure the safety of the elephant population in Sabah for the future.”
The research team intends to expand PoachNet’s capabilities by incorporating data from other sources, such as acoustic sensors to detect gunshots or vehicle noise and satellite imagery for monitoring. The system’s predictive capabilities could inform strategic resource allocations and the deployment of motion-activated camera traps in high-risk zones.
This innovative AI-driven approach represents a significant step in conservation efforts and offers a promising tool for protecting endangered species against poaching threats.
Reference Hamed, N., et al. (2024). PoachNet: Predicting Poaching Using an Ontology-Based Knowledge Graph, Sensors. DOI: 10.3390/s24248142
