AI-driven solutions for mitigating human-wildlife conflict in biodiversity hotspots
Publication details: Hyderabad IUP Publications 2024Edition: Vol.17(1), FebDescription: 43-53pSubject(s): Online resources: In: IUP Journal of telecommunicationsSummary: Human-wildlife conflict (HWC) is a rising concern in biodiversity hotspots such as Wayanad, Kerala, where agricultural loss, property damage, and human casualties due to wildlife incursions have intensified. With elephant intrusions alone contributing to over 60% of reported conflict events in the region, traditional mitigation strategies—like trenching and electric fencing— have proven both reactive and limited in effectiveness. This paper explores AI-driven solutions as a proactive and scalable response. By combining satellite imagery, GPS tracking, and realtime sensor data, it has developed a predictive model capable of detecting conflict risk zones and alerting stakeholders in near real time. The approach improves prediction accuracy over legacy systems by 23% and enables faster mobilization of response teams. The findings underscore the viability of integrating Edge AI and remote sensing into conservation efforts, offering a sustainable model for managing HWC across India’s forest fringes.| Item type | Current library | Status | Barcode | |
|---|---|---|---|---|
Articles Abstract Database
|
School of Engineering & Technology Archieval Section | Not for loan | 2025-1292 |
Human-wildlife conflict (HWC) is a rising concern in biodiversity hotspots such as Wayanad, Kerala, where agricultural loss, property damage, and human casualties due to wildlife incursions have intensified. With elephant intrusions alone contributing to over 60% of reported conflict events in the region, traditional mitigation strategies—like trenching and electric fencing— have proven both reactive and limited in effectiveness. This paper explores AI-driven solutions as a proactive and scalable response. By combining satellite imagery, GPS tracking, and realtime sensor data, it has developed a predictive model capable of detecting conflict risk zones and alerting stakeholders in near real time. The approach improves prediction accuracy over legacy systems by 23% and enables faster mobilization of response teams. The findings underscore the viability of integrating Edge AI and remote sensing into conservation efforts, offering a sustainable model for managing HWC across India’s forest fringes.
There are no comments on this title.