Page 187 - AI for Good Innovate for Impact
P. 187
AI for Good Innovate for Impact
4�2� Category 2: Climate Change
Use Case 1: GeoGPT: AI-driven Marine Ecosystem Monitoring and Change 4.2-Climate
Protection
Organization: Zhejiang Lab
Country: China
Contact Person:
Primary: Dandan Huang, huangdandan@ zhejianglab .org
Secondary: Junhui Shi, junhuishi@ zhejianglab .org
Additional Contacts: Ying Zhou, zhouying@ zhejianglab .org
1 Use Case Summary Table
Item Details
Category Climate Change/Natural Disaster
Problem Addressed The use case addresses the challenge of monitoring and protecting
marine ecosystems, particularly in areas like deep-sea mineral explo-
ration and harmful marine biological disaster detection, which pose
significant environmental risks.
Key Aspects of Solution Use of AI system powered by large language models (LLMs) with
retrieval-augmented generation (RAG) technology; AI models for
marine ecosystem monitoring and protection; Improved perfor-
mance in prediction for microalgae distribution and the impacts
of climate change on marine ecosystems; Built upon a diversified
portfolio—Llama (USA) [3], Qwen (China)[4], Mixtral (Europe)[5], and
DeepSeek R1 (China)[6] — GeoGPT offers enhanced multi-modal and
scientific discovery capabilities.
Technology Keywords LLMs for marine ecosystem protection; Retrieval-augmented gener-
ation (RAG)
Data Availability Public
(repository: https:// github .com/ GeoGPT -Research -Project/ GeoGPT)
[7]
Metadata (Type of Data) Text; Visual (image recognition for species identification); Environ-
mental data (temperature, water quality, algae distribution)
151
