Monitoring Urban Wetland Bird Migrations using IoT and ML Techniques

Over the past decade, the sightings of numerous migratory bird species that were once common have become increasingly rare. These birds often reside high in the canopy or deep within reed beds, making ground-based observations challenging and prone to misclassification. Additionally, traditional monitoring methods require substantial manpower and time resources. To address these challenges, our paper aims to develop an Internet of Things and machine learning-based system for monitoring bird populations in urban wetland habitats. This system will employ strategically placed modules equipped with various sensors to collect data. Furthermore, we will integrate machine learning algorithms to analyze this data, allowing for the automated and accurate identification of different migratory bird species within the habitat. By utilizing IoT technology and machine learning, we can achieve more accurate and efficient identification of different migratory bird species within the habitat while conserving valuable resources and time.