Method for optimizing coating properties based on an evolutionary algorithm approach.

Area of Science:

• Materials Science
• Chemical Engineering
• Data Science

Background:

• Multivariable multiresponse systems are common in industry and research, posing optimization challenges.
• Optimizing materials, like sensor coatings, requires balancing multiple properties and minimizing experimental effort.
• Existing high-throughput methods accelerate discovery but need efficient experimental design.

Purpose of the Study:

• To evaluate a novel evolutionary model-based multiresponse approach (EMMA) for efficient materials optimization.
• To demonstrate EMMA's ability to minimize experiments while optimizing material properties.
• To apply EMMA to the development and optimization of amino-methyl-silane coatings for sensor arrays.

Main Methods:

• Developed and applied the evolutionary model-based multiresponse approach (EMMA).
• Utilized a sol-gel synthetic route for amino-methyl-silane coating production and optimization.
• Monitored spotting performance using fluorescent dye and laser scanning for response variable measurement.

Main Results:

• EMMA successfully optimized coating response variables for micro- and macro-array surfaces.
• Optimization was achieved by exploring less than 2% of potential experiments.
• The approach identified the most influential compositional variables for the coating.

Conclusions:

• EMMA is a promising tool for simultaneously optimizing and modeling multivariable multiresponse systems.
• The method significantly reduces the number of experiments required for materials optimization.
• EMMA enhances efficiency in discovering and refining materials for applications like sensor arrays.