Shenzhen students' goose AI may have lifted survival 30%

AI system

System: AI goose-breeding program (recognition and tracking algorithms on farm cameras)
Model: Not assessed
Release: Not assessed
Application developer: Sixteen students of the Shenzhen University-Tencent Cloud AI BEng program, guided by university teachers and Tencent engineers
Role: Not assessed
Configuration: Not assessed
Inputs and outputs: Not assessed
Autonomy: Not assessed
Workflow: Existing farm cameras and 6,000 manually labeled images of 300,000 geese. Stillness duration as the sickness proxy, with fever detection in goslings. Over 4,000 geese in a 500 m² space.
Human oversight: Not assessed
Relation to AI: The system's real-time alerts are the only mechanism described for the survival gain. The reports do not separate the AI's effect from other changes on the farm. Sources are independent news reports (Xinhua, CGTN) with named sources. No veterinary or peer-reviewed confirmation was found.
AI contribution: The system's real-time alerts are the only mechanism described for the survival gain. The reports do not separate the AI's effect from other changes on the farm. Sources are independent news reports (Xinhua, CGTN) with named sources. No veterinary or peer-reviewed confirmation was found.

Studies: Not assessed
Study design: Not assessed
Measurement: Not assessed
Setting and sample: Not assessed
Measures: helped the farm increase survival of lion-head geese by 30 percent
Comparison: Assumed alternative: the farm's survival rate before the AI program (no baseline figure is given)
Results: Assumed comparison. Result: survival rate of lion-head geese increased by 30 percent.
Additional value from AI: Not assessed
Limitations: Not assessed
Denominators: Not assessed
Materials for replication: Not assessed

Participants: Developer: Sixteen students of the Shenzhen University-Tencent Cloud AI BEng program, guided by university teachers and Tencent engineers. Operator: Jin Shutao's lion-head goose farming cooperative, Houxi Village, Chenghai District, Shantou.
Jurisdictions: Benefit: Shantou, China. Developer: China.
Ownership and control: Not assessed
Dependencies: Not assessed
Cross-border connections: Not assessed
Geopolitical implications: Not assessed

Conditions for replication: Camera coverage in dense flocks. Continued tuning of the algorithm to the specific farm (the students found no one-size-fits-all algorithm).
Replication attempts: Not assessed
Later findings: No later report on the cooperative or the program after October 2023 was found.
Availability: Not assessed
Institutional decision: Not assessed
Grounds: Not assessed
Action and result: Not assessed
Success criterion: Not assessed

Assessed benefits: Organizations. People.
Depth: Organizations: 2. People: Not assessed.
Reasons: Organizations: Xinhua states the program “has helped the farm increase the survival rate of lion-head geese by 30 percent”. No baseline, period or verification is given. People: Farmer Jin Shutao is named but no personal outcome beyond the farm figure is reported.
Observed or intended: Not assessed
Rubric: Not assessed
Assessor and date: Not assessed
Alternative assessments: Not assessed
Fill: Independently reported

Kind: Not assessed
Related entries: Not assessed
Field: Livestock health. Goose farming.
Purpose: Identify sick geese from camera footage by how long they stay still (and fever in goslings) and alert breeders in real time.
Dates: Date basis unassessed: 2023 (precision unassessed). Updated: 21 October 2026.
Stage: Not assessed
Version: SHA-256: d6635139496c…

News report Independent author

Xinhua. Across China: AI program developed by students benefits goose farm. Xinhua, Shenzhen, 13 October 2023.
News report Independent author

CGTN. AI program developed by Chinese college students benefits goose farm. CGTN, 14 October 2023.
Registry label Independent author

OECD.AI AI Incidents and Hazards Monitor. AI System Developed by Students Boosts Goose Survival Rates in China. Record 2023-10-13-d63c.