Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Recurso digital |
| Language: | |
| Published: |
Zenodo
2026
|
| Online Access: | https://doi.org/10.21474/IJAR01/22705 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Table of Contents:
- <p>Zoonotic diseases are emerging at an increasing rate as human activities reshape natural ecosystems and intensify contact around the human wildlife interface. Various practices like deforestation, illegal trade, habitat fragmentation, and rapid urban expansion weaken natural barriers that previously confined pathogen transmission and create environments where spillover events can take place.Most current surveillance systems work reactively and tend to look at ecological or trade-related factors in isolation, thus limiting their capabilities for early detection of risk signals. In this paper, we introduce the use of our project, Wild Sentinel, an integrated predictive solution for identifying country pairs with a high risk of hosting an animal-to-human disease outbreak event. It does so by combining data on the records of wildlife trade, species distribution, satellite-derived land-use patterns, historical data of outbreaks, and biosafety indicators using machine learning models, network graph analysis, and geospatial processing to forecast spillover probabilities and visualize hotspot risk maps. Translating large-scale environmental and anthropogenic datasets into actionable bio-surveillance insights, Wild Sentinel underlines targeted preventive interventions based on the One Health approach. The developed framework therefore demonstrates the role of technology-driven early warning systems in reinforcing global preparedness, informing policy decisions, and ensuring a safer coexistence between humans and wildlife.</p> <p> </p>