Drones and machine-learning for monitoring dugong feeding grounds and gillnet fishing

Bioturbation is a process caused by animals that move particles and water in sediments. This influences gas and solute exchange, and organic matter concentrations through the sediment column. Bioturbators play an important role in biogeochemistry and ecosystem functioning. To date, bioturbation research has focused on the invertebrate macrofauna present in the sediment. However, many larger marine animals (e.g. rays, sharks, whales) display foraging behaviours that disturb the sediment and thus potentially affect sediment biogeochemistry. We propose a categorization of vertebrate megafauna bioturbation based on their reworking behaviours, classifying them as ‘pit creators’, ‘bulldozers’, and ‘trench diggers’. These categories underscore the diversity of impacts on sediment structure and biogeochemical processes. The need to investigate the topic comes from the limited knowledge surrounding the extent to which sediment biogeochemistry is influenced by megafauna activities. Additionally, the declining population of vertebrate megafauna due to climate change, overfishing, bycatch, and habitat loss and modification makes discerning the functional roles of these animals in the sediment a pressing issue. Understanding the ecological implications of megafauna bioturbation will be critical to support conservation strategies and protect marine ecosystems and the animals that shape them.

show abstract

Integration of Unmanned Aerial Vehicle Systems With Machine Learning Algorithms for Wildlife Monitoring and Conservation

Raffik,

Mahima Swetha,

Sathya

et al. 2024

Applications of Machine Learning in UAV Networks

View full text Add to dashboard Cite

Two cutting-edge technologies, unmanned aerial vehicle (UAV) systems and deep learning algorithms, have the potential to completely change how wildlife is monitored and conserved. Data collection across wide areas, in challenging locations, and in real time are all possible with UAVs. Data collection via UAVs is possible in locations that are difficult or impossible to reach using conventional human approaches. Along with spotting strange behavior by wild creatures, the UAV can also spot it in human activity. Deep learning algorithms can be used to recognize certain animals, follow their motions, and categorize their behavior. The ecology of wildlife populations may be better understood using this knowledge, which can also be utilized to create more successful conservation plans. A novel technique that has promise for wildlife monitoring and conservation is the fusion of UAV systems and deep learning algorithms. The anticipation is even more creative and successful methods to use UAVs and deep learning to protect animals as technology progresses.

show abstract

Drones and machine-learning for monitoring dugong feeding grounds and gillnet fishing

Cited by 3 publications

References 48 publications

Patch age alters seagrass response mechanisms to herbivory damage

Patch age alters seagrass response mechanisms to herbivory damage

Megafauna: the ignored bioturbators

Integration of Unmanned Aerial Vehicle Systems With Machine Learning Algorithms for Wildlife Monitoring and Conservation

Contact Info

Product

Resources

About