海归学者发起的公益学术平台
分享信息，整合资源
交流学术，偶尔风月
随着材料科学技术的不断进步，功能性材料的设计与发现始终处于创新的前沿。然而，材料的性能往往依赖于几何特征、成分、加工条件和环境因素等多种设计因素，这导致了设计空间的极大复杂性。传统的实验和模拟方法由于耗时且昂贵，难以全面搜索如此庞大的设计空间。
Fig. 1 | Schematics of PML TRC structure design.
随着计算科学和数据科学的发展，机器学习算法开始改变材料设计领域。一系列基于深度学习的正向建模与逆向设计相结合的算法已被提出并应用于实践，然而面对日益庞大的设计空间，传统的算法难以有效地找到全局最优解。受量子计算理论的启发，一些启发式算法被提出作为经典算法的增强解决方案，与传统方法相比，可实现更高的精度和更强的全局搜索能力。
Fig. 2 | The evolution of FOM for N = 6 in QGA-facilitated active learning optimization.
来自美国圣母大学航空航天工程和机械工程系的博士生徐志昊，罗腾飞教授和韩国庆熙大学电子工程系的Eungkyu Lee教授团队通过结合机器学习替代模型和量子启发的遗传算法，开发了一个基于主动学习的功能材料设计算法。该算法针对平面多层光子结构设计这一复杂离散的优化问题，结合了量子计算和遗传算法的优势，有效地搜索性能最佳的光学结构。
Fig. 3 | Evolution of the best FOM in QGA and CGA.
相较于经典遗传算法（CGA），提出的基于量子启发遗传算法（QGA）种群规模更小、收敛速度更快、全局优化能力更强。此外，选择随机森林（RF）作为替代模型放宽了其他量子计算优化算法中对代理模型类型的限制，从而能够更加准确地映射设计空间，提高算法收敛的速度。
Fig. 4 | Energy saving analysis for design PML TRC structures.
该研究展示了经典算法和量子算法结合的潜力，同时指出了当前基于QA的优化方案的瓶颈。该文近期发表于npj Computational Materials 10: 257 (2024)，英文标题与摘要如下，点击左下角“阅读原文”可以自由获取论文PDF。
Quantum-inspired genetic algorithm for designing planar multilayer photonic structure
Zhihao Xu, Wenjie Shang, Seongmin Kim, Alexandria Bobbitt, Eungkyu Lee* & Tengfei Luo*
Quantum algorithms are emerging tools in the design of functional materials due to their powerful solution space search capability. How to balance the high price of quantum computing resources and the growing computing needs has become an urgent problem to be solved. We propose a novel optimization strategy based on an active learning scheme that combines the Quantum-inspired Genetic Algorithm (QGA) with machine learning surrogate model regression. Using Random Forests as the surrogate model circumvents the time-consuming physical modeling or experiments, thereby improving the optimization efficiency. QGA, a genetic algorithm embedded with quantum mechanics, combines the advantages of quantum computing and genetic algorithms, enabling faster and more robust convergence to the optimum. Using the design of planar multilayer photonic structures for transparent radiative cooling as a testbed, we show superiority of our algorithm over the classical genetic algorithm (CGA). Additionally, we show the precision advantage of the Random Forest (RF) model as a flexible surrogate model, which relaxes the constraints on the type of surrogate model that can be used in other quantum computing optimization algorithms (e.g., quantum annealing needs Ising model as a surrogate).
扩展阅读
