Efficient urban flood control and drainage management framework based on digital twin technology and optimization...

Area of Science:

• Environmental Engineering
• Water Resource Management
• Computer Science

Background:

• Urban flood control faces challenges coordinating drainage with river-lake systems.
• Rising river levels cause backwater effects, increasing urban flood risk.
• Traditional methods suffer from data delays and inadequate decision support.

Purpose of the Study:

• To develop a digital twin experimental platform for enhanced urban flood control and drainage management.
• To optimize drainage pump scheduling rules using deep learning and multi-objective optimization.
• To evaluate the platform's effectiveness in reducing flood risks and operational costs.

Main Methods:

• Developed a digital twin platform integrating physical systems with a virtual model using PLC and Unity3D.
• Implemented a novel deep learning and multi-objective optimization model for pump scheduling.
• Conducted comparative analysis of flood risks and costs before and after optimization.

Main Results:

• The digital twin platform achieved high accuracy in water level prediction (NSE > 95.18%) and pump operation timing (error < 4.11%).
• The optimization strategy significantly reduced water level targets by up to 51.61% under various scenarios.
• The backwater effect was identified as primarily driven by river flow and downstream lake levels.

Conclusions:

• The digital twin platform provides a robust solution for comprehensive urban flood protection and drainage management.
• The proposed optimization model effectively balances water level control and operational objectives.
• This framework offers strong technical support for optimizing flood control and drainage operations.