Machine-Learning-Assisted Autonomous Humidity Management System Based on Solar-Regenerated Super Hygroscopic Complex.

Area of Science:

• Environmental Science
• Materials Science
• Engineering

Background:

• High humidity levels cause thermal discomfort and health issues.
• Atmospheric water harvesting can address water scarcity.
• Existing dehumidification systems are often energy-intensive.

Purpose of the Study:

• To develop a low-energy, highly efficient humidity control system.
• To enable simultaneous dehumidification and freshwater production.
• To improve thermal comfort and resource utilization.

Main Methods:

• Development of a novel desiccant dehumidifier utilizing a super hygroscopic complex (SHC).
• Integration of machine-learning-assisted, low-cost hygrometers for autonomous operation.
• Performance evaluation of water uptake, regeneration, energy consumption, and relative humidity reduction.

Main Results:

• The SHC demonstrated high water uptake (4.64 g g⁻¹) and facile regeneration.
• The system reduced relative humidity from 75% to 60% in 15 minutes with 0.05 kWh energy consumption.
• Harvested 10 L of atmospheric water in 24 hours, saving over 60% energy compared to commercial units.
• Reduced apparent temperature by ~7°C, enhancing thermal comfort.

Conclusions:

• The developed system offers an energy-efficient solution for humidity control and freshwater production.
• Autonomous operation enhances usability and efficiency.
• The technology effectively improves indoor thermal comfort and addresses water scarcity concerns.