KAUST is hosting the Marine Megafauna Movement Workshop (October 19-20) featuring international speakers showcasing research on marine animal behavior using sensors and analytics. Enrichment in the Fall 2015 (October 16-24) at KAUST will focus on marine animal movement with lectures, trips, movies, and music. KAUST aims to merge research on marine animal movement with the study of human mobility to gain new insights. Why it matters: This interdisciplinary approach could advance understanding of both marine ecosystems and human behavior, while promoting marine conservation efforts in the Red Sea.
An international team including KAUST researchers tracked nearly 2,000 sharks using satellite tags to map their movement and space use. The study found that 24% of shark habitats overlap with pelagic longline fisheries, with higher overlap for commercially exploited species. For North Atlantic blue and shortfin mako sharks, the overlap was 76% and 62% respectively. Why it matters: This research highlights the vulnerability of sharks to industrial fishing and underscores the need for targeted conservation efforts in critical habitats.
Researchers in Abu Dhabi developed H-SURF, a swarm of bio-inspired robotic fish for underwater data collection. Funded by the Technology Innovation Institute (TII) and conducted at Khalifa University, H-SURF uses swarm intelligence and optical communication to minimize disturbance to marine life. The project was recently recognized with the Sheikh Hamdan bin Zayed Award for Environmental Research.
KAUST researchers developed a hybrid wireless communication system for non-invasive monitoring of marine animals, consisting of a lightweight, flexible, Bluetooth-enabled tag that stores sensor data underwater. The tag syncs data to floating receivers when the animal surfaces, which then relays the data via GSM or drones. The system is a collaboration between the Red Sea Research Center and KAUST's electrical engineering department. Why it matters: This technology provides researchers with detailed, near real-time data about marine animals, overcoming the limitations of invasive and impractical traditional tagging methods.
KAUST researchers developed a low-cost, AI-powered drone system to recognize and track camels, addressing challenges faced by local herders. The system uses commercial drones, cameras, and machine learning to monitor camel herds in real time without expensive GPS collars. The AI model revealed insights into camel migration patterns, showing coordinated grazing and sensitivity to drone sounds. Why it matters: This system offers an affordable solution to preserve Saudi Arabia's camel herding tradition while providing valuable insights into camel behavior and contributing to the local economy.
Researchers are exploring computer vision models to mitigate Camel-Vehicle Collisions (CVC) in Saudi Arabia, which have a high fatality rate. They tested CenterNet, EfficientDet, Faster R-CNN, and SSD for camel detection, finding CenterNet to be the most accurate and efficient. Future work involves developing a comprehensive system to enhance road safety in rural areas.
KAUST researchers, in collaboration with WHOI, studied whale shark movement patterns near the Shib Habil reef in the Red Sea over six years using visual census, acoustic monitoring, and satellite telemetry. The study monitored 84 sharks and found the aggregation to be highly seasonal, with sharks most abundant in April and May, returning yearly. The site may serve as a nursery for the wider Indian Ocean population, attracting juvenile females, which is unique to Shib Habil. Why it matters: Understanding whale shark behavior and critical habitats like Shib Habil is vital for future conservation efforts of this endangered species in the Red Sea and the broader Indian Ocean.
The paper introduces a framework for camel farm monitoring using a combination of automated annotation and fine-tune distillation. The Unified Auto-Annotation framework uses GroundingDINO and SAM to automatically annotate surveillance video data. The Fine-Tune Distillation framework then fine-tunes student models like YOLOv8, transferring knowledge from a larger teacher model, using data from Al-Marmoom Camel Farm in Dubai.