Harnessing a Novel Machine-Learning-Assisted Evolutionary Algorithm to Co-optimize Three Characteristics of an Electrospun Oil Sorbent

Machine Learning-Assisted Design of Material Properties

Designing functional materials requires a deep search through multidimensional spaces for system parameters that yield desirable material properties. For cases where conventional parameter sweeps or trial-and-error sampling are impractical, inverse methods that frame design as a constrained optimization problem present an attractive alternative. However, even efficient algorithms require time- and resource-intensive characterization of material properties many times during optimization, imposing a design bottleneck. Approaches that incorporate machine learning can help address this limitation and accelerate the discovery of materials with targeted properties. In this article, we review how to leverage machine learning to reduce dimensionality in order to effectively explore design space, accelerate property evaluation, and generate unconventional material structures with optimal properties. We also discuss promising future directions, including integration of machine learning into multiple stages of a design algorithm and interpretation of machine learning models to understand how design parameters relate to material properties. Expected final online publication date for the Annual Review of Chemical and Biomolecular Engineering, Volume 13 is October 2022. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.

Bayesian optimization for goal-oriented multi-objective inverse material design

Bayesian optimization (BO) can accelerate material design requiring time-consuming experiments. However, although most material designs require tuning of multiple properties, the efficiency of multi-objective (MO) BO in time-consuming experimental material design remains unclear, due to the complexity of handling multiple objectives. This study introduces MO BO method that efficiently achieves predefined goals and shows that by focusing on achieving the goals, BO can efficiently accelerate realistic MO design problems with small efforts. Benchmarks showed that the proposed BO method dramatically reduced the number of experiments needed to achieve goals relative to a baseline method. Virtual MO inverse design experiments with realistic material design problems were also performed, during which the proposed method could achieve goals within only around ten experiments in average and showed over 1000-fold acceleration relative to the random sampling for the most difficult case. The introduction of goal-oriented BO will precede real-world application of BO.

Multifunctional Photothermal Conversion Nanocoatings Toward Highly Efficient and Safe High-Viscosity Oil Cleanup Absorption

Efficient and safe cleanup for the high-viscosity heavy oil spill has been a worldwide challenge due to its sluggish flowability, while classic absorption methods by electric/solar heating are seriously limited by low efficiency and high fire hazards during heating of highly flammable oil. Facing this dilemma, we reported a novel flame-retardant photothermal conversion nanocoating to endow commercial foams with highly efficient and safe heavy oil cleanup absorption. This multifunctional nanocoating consisting of nano-Fe₃O₄ and reduced graphene oxide (rGO) that both showed photothermal conversion ability and non-flammable nature can be firmly deposited on the polymer foam skeletons via facile coprecipitation and dip-coating processes. The composite foam showed a tough morphology with high hydrophobicity and low density, thus leading to selective high absorption for various oils and organic solvents. Due to the double photothermal conversion effects of nano-Fe₃O₄ and rGO, the temperature of the foam can be rapidly heated at a rate of ∼103.5 °C/min (the fastest rate ever) under 1 sun irradiation. Consequently, the foam with a high absorption capacity of 75.1 times its weight demonstrated a rapid absorption rate of 9000 g m^-2 min^-1 for large-viscosity oil under 1 sun irradiation, which was 3 times faster than previously reported. Furthermore, benefitting from high flame retardancy, elasticity, and magnetism, the foam can be safely and repeatedly used for magnetically controllable oil cleanup absorption, which effectively avoids oil spill hazards.