#China #Huawei #AI Solutions #Xiamen #Chinese White Dolphins

A Breakthrough for Chinese White Dolphins in Xiamen Bay

In a significant advancement for marine conservation, Huawei and its partners have recently announced the initial results of an innovative AI solution aimed at studying and protecting the endangered Chinese white dolphins in Xiamen Bay. The project, launched three months ago under Huawei's TECH4ALL initiative, is already yielding promising outcomes.

Swift Identification and Enhanced Monitoring

Utilizing a combination of over 2,820 images and videos, researchers have successfully identified 13 individual dolphins with an impressive accuracy rate exceeding 90%. Furthermore, the AI system displays an 85% recognition rate for complex behaviors, significantly improving data labeling efficiency by an astounding 400%. This advancement has led to a 65% increase in response times for law enforcement, particularly concerning vessels that are speeding or encroaching on protected areas.

Cui Yangyang, director of the TECH4ALL Program Office at Huawei, noted, "The data-driven insights generated by AI are instrumental in helping conservationists formulate targeted protection measures. Understanding the threats faced by this iconic dolphin species is crucial for their survival and prosperity in the wild."

Chinese white dolphins are a nationally protected species classified as vulnerable on the IUCN Red List. The Xiamen Bay, which is home to 51% of the country's dolphin population, poses significant threats from shipping, fishing, and coastal construction projects. Factors such as noise pollution, entanglement in fishing gear, and habitat loss threaten their long-term existence.

Partnership and Technological Integration

The project, in collaboration with the Third Institute of Oceanography under China's Ministry of Natural Resources and China Mobile, utilizes a recognition system to identify individual dolphins based on their dorsal fin markings. Wang Xianyan, leader of the endangered marine species research and conservation team at the Third Institute, stated, "With AI technology, our research is now more efficient, and conservation efforts are becoming more precise. The data on individual survival, reproductive dynamics, and social interactions provided by the AI recognition system lays a crucial foundation for developing conservation strategies."

This solution incorporates image preprocessing, AI-assisted inference, dorsal fin image cropping, data classification, and cloud display. Each dolphin is assigned a unique file, which allows researchers to track the status of individual animals. Long-term data crucial for crafting protective measures can now be analyzed, focusing on population numbers, distribution, age structure, reproductive behavior, and the challenges these dolphins face.

Previously common manual monitoring techniques were time-consuming and lacked the reliability needed for tracking population dynamics and formulating targeted protective strategies.

A Critical Decade Ahead

According to the Third Institute of Oceanography, the next 10 to 15 years are critical for the dolphin population's growth. This species plays an essential role in marine ecosystems along the coast and contributes to the ocean's carbon storage capability. They feed on fish that consume plankton, which absorbs CO2 and captures carbon through photosynthesis. Thus, protecting the dolphin population is vital for maintaining the ocean's ecological integrity and combating climate change.

The project also utilizes a 5G-A network with ten base stations covering 330 square kilometers of the bay, enabling seamless coverage of critical protective zones. By integrating detection and communication capabilities of 5G-A and combining data from radars, visual terminals, satellites, and the Automatic Identification System (AIS), real-time tracking of vessel movements within a 20-kilometer radius is possible. The system provides real-time AI-driven alerts for violations such as border breaches or speed infringements. Enforcement agencies can swiftly verify violations and locate offending vessels.

So far, 12 vessels have been investigated for potentially endangering the dolphins. Continuous research efforts combined with AI applications are gradually revealing the hidden lives of the Chinese white dolphin population in Xiamen Bay, providing hope for their future survival.