Page 213 - AI for Good Innovate for Impact
P. 213
AI for Good Innovate for Impact
Use Case 7: LLM empowered smart hydrology Change 4.2-Climate
Organization: ZTE Corporation
Country: China
Contact Person:
Primary: Liya Yuan, yuan.liya@ zte .com .cn
Secondary: Wang Wang, wang.wang@ zte .com .cn
1 Use Case Summary Table
Item Details
Category Climate Change/Natural Disaster
Problem Addressed Traditional hydrology struggles with slow data analysis, complex flood
planning, and costly terrain surveys caused by manual-based methods.
The integration of hydrology LLM facilitates the intelligent transformation
and greatly improve the efficiency of water management system.
Key Aspects of Solu- Based on hydrology LLM, building a smart hydrological assistant deliver-
tion ing expertise and auto-reporting for water professionals; AI applications
handling critical tasks like river modelling and engineering calculations;
AI agents automating flood strategy design and emergency planning,
optimizing entire operational chains.
Technology Hydrology, LLM, multi-modal, agent, water governance
Keywords
Data Availability Private
Metadata (Type of text, visual
Data)
Model Training and PEFT fine-tuning and instruction tuning based on the Nebula LLM with
Fine-Tuning hydrology data
Testbeds or Pilot N/A
Deployments
2 Use Case Description
2�1 Description
This case demonstrates a hydrology-specific LLM developed based on ZTE Nebula large
model, designed to address core challenges in water conservancy. It focuses on optimizing
177
