NpjComput.Mater.：複雜功能材料的高效設計：量子啟發演算法+機器學習

海歸學者發起的公益學術平臺

分享資訊，整合資源

交流學術，偶爾風月

隨著材料科學技術的不斷進步，功能性材料的設計與發現始終處於創新的前沿。然而，材料的效能往往依賴於幾何特徵、成分、加工條件和環境因素等多種設計因素，這導致了設計空間的極大複雜性。傳統的實驗和模擬方法由於耗時且昂貴，難以全面搜尋如此龐大的設計空間。

Fig. 1 | Schematics of PML TRC structure design.

隨著計算科學和資料科學的發展，機器學習演算法開始改變材料設計領域。一系列基於深度學習的正向建模與逆向設計相結合的演算法已被提出並應用於實踐，然而面對日益龐大的設計空間，傳統的演算法難以有效地找到全域性最優解。受量子計算理論的啟發，一些啟發式演算法被提出作為經典演算法的增強解決方案，與傳統方法相比，可實現更高的精度和更強的全域性搜尋能力。

Fig. 2 | The evolution of FOM for N = 6 in QGA-facilitated active learning optimization.

來自美國聖母大學航空航天工程和機械工程系的博士生徐志昊，羅騰飛教授和韓國慶熙大學電子工程系的Eungkyu Lee教授團隊透過結合機器學習替代模型和量子啟發的遺傳演算法，開發了一個基於主動學習的功能材料設計算法。該演算法針對平面多層光子結構設計這一複雜離散的最佳化問題，結合了量子計算和遺傳演算法的優勢，有效地搜尋效能最佳的光學結構。

Fig. 3 | Evolution of the best FOM in QGA and CGA.

相較於經典遺傳演算法（CGA），提出的基於量子啟發遺傳演算法（QGA）種群規模更小、收斂速度更快、全域性最佳化能力更強。此外，選擇隨機森林（RF）作為替代模型放寬了其他量子計算最佳化演算法中對代理模型型別的限制，從而能夠更加準確地對映設計空間，提高演算法收斂的速度。

Fig. 4 | Energy saving analysis for design PML TRC structures.

該研究展示了經典演算法和量子演算法結合的潛力，同時指出了當前基於QA的最佳化方案的瓶頸。該文近期發表於npj Computational Materials10: 257 (2024)，英文標題與摘要如下，點選左下角“閱讀原文”可以自由獲取論文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).