Active Learning-Based Guided Synthesis of Engineered Biochar for CO₂ Capture.

Area of Science:

• Materials Science
• Environmental Science
• Chemical Engineering

Background:

• Engineered biochar from biomass waste offers a sustainable solution for carbon dioxide (CO2) capture and waste management.
• Optimizing biochar synthesis for high CO2 adsorption capacity is challenging due to time and labor intensity.

Purpose of the Study:

• To develop an active learning strategy to expedite the synthesis of engineered biochar with improved CO2 adsorption capacities.
• To maximize the narrow micropore volume of biochar, which correlates linearly with CO2 adsorption.

Main Methods:

• An active learning framework was employed, iteratively learning from experimental data to recommend optimal synthesis parameters.
• Experimental validation of active learning predictions and iterative retraining established a closed-loop system.
• 16 engineered biochar samples were synthesized over three active learning cycles.

Main Results:

• The active learning strategy successfully guided the synthesis process, leading to significant improvements in CO2 uptake.
• CO2 adsorption capacity nearly doubled by the final round of active learning.
• A data-driven workflow was demonstrated for accelerating the development of high-performance engineered biochar.

Conclusions:

• Active learning provides an efficient method for optimizing engineered biochar synthesis for enhanced CO2 capture.
• This approach accelerates the development of functional materials for climate change mitigation and waste management.
• The developed workflow shows potential for broader applications in materials design and discovery.