高效的晶體結(jié)構(gòu)預(yù)測（CSP）是材料科學(xué)中的一項重要挑戰(zhàn)，其涉及在復(fù)雜的構(gòu)型空間中尋找亞穩(wěn)態(tài)晶體多形體的結(jié)構(gòu)–性質(zhì)關(guān)系。隨著AI和機器學(xué)習(xí)技術(shù)的應(yīng)用，特別是強化學(xué)習(xí)（RL），在高維搜索空間中的優(yōu)化過程得以提升效率和準(zhǔn)確性，推動了材料設(shè)計和發(fā)現(xiàn)的新范式。這些方法不僅加速了全局最優(yōu)解的發(fā)現(xiàn)，還有助于探索和利用局部最小值，為材料創(chuàng)新提供更廣闊的可能性。
Fig. 1 Schematic illustration of the nature of the search space (discrete vs. continuous) in materials applications.
阿貢國家實驗室納米材料中心的Subramanian K. R. S. Sankaranarayanan教授及其團隊開發(fā)的CASTING，是一個針對高維搜索空間內(nèi)約束滿足問題（CSP）的工作流程，它采用了基于連續(xù)動作空間樹的強化學(xué)習(xí)（RL）搜索算法。
Fig. 2 MCTS working as crystal structure optimizer.
該研究團隊對蒙特卡洛樹搜索（MCTS）算法進行了關(guān)鍵的算法改進，使其能夠成功地應(yīng)用于與結(jié)構(gòu)和拓撲預(yù)測相關(guān)的連續(xù)搜索空間逆問題。
Fig. 3 Schematic depicting the workflow of the CASTING framework for performing inverse design.
通過對CASTING框架的效能進行展示，此項工作將該技術(shù)應(yīng)用于各種代表性系統(tǒng)，包括單一成分的金屬系統(tǒng)如銀（Ag）和金（Au）、共價系統(tǒng)如碳（C）、二元系統(tǒng)如氮化硼（h-BN）和碳氫化合物（C-H），以及多組分鈣鈦礦系統(tǒng)如摻雜的鎳鈮氧化物（NNO）。
Fig. 4 Exploring the performance and scalability of CASTING framework using an example metal polymorph.
此外，研究還采用了多目標(biāo)優(yōu)化策略，對超硬碳相進行逆向設(shè)計。研究顯示，CASTING在處理復(fù)雜材料科學(xué)問題上顯示出良好的擴展性、采樣準(zhǔn)確度以及快速的收斂能力。
Fig. 5 Effect of tree hyperparameter on the sampling, convergence, and solution quality of Ag polymorphs.
同時，還對不同的強化學(xué)習(xí)超參數(shù)如何影響搜索性能進行了深入探討。CASTING也被用于在不同維度系統(tǒng)中采樣穩(wěn)定和亞穩(wěn)態(tài)的多態(tài)性，涵蓋從三維（塊體）到低維系統(tǒng)如零維（團簇）和二維（片層）。
Fig. 6 Comparison of structure prediction for carbon polymorphs with an empirical potential model.
與其他元啟發(fā)式搜索算法進行比較時，如遺傳算法、盆地跳躍和隨機抽樣，MCTS在解決方案的質(zhì)量和收斂速度方面顯示出了明顯的優(yōu)勢。這項技術(shù)被認為特別適合于解決那些具有多重目標(biāo)、多種組分和多維度的復(fù)雜搜索問題。
Fig. 7 Structural diversity of sampled Carbon(C) polymorphs using CASTING.
整體上，該研究成功地證明了強化學(xué)習(xí)技術(shù)如MCTS在結(jié)構(gòu)和拓撲預(yù)測的逆向材料設(shè)計和發(fā)現(xiàn)問題中的應(yīng)用潛力。該文近期發(fā)表于npj Computational Materials 9: 177 (2023).
Fig. 8 Convergence with size-dependent diversity in nanoclusters of Gold (Au).
Editorial Summary
To reverse design of materials? Please ask the AIEfficient crystal structure prediction (CSP) is a key challenge in materials science, which involves finding structure-property relationships for substable crystalline polymorphs in a complex configuration space. With the application of AI and machine learning techniques, especially reinforcement learning (RL), the optimization process in high-dimensional search spaces has been able to improve efficiency and accuracy, driving a new paradigm in materials design and discovery. These methods not only accelerate the discovery of globally optimal solutions, but also help to explore and utilize local minima, providing broader possibilities for materials innovation. 
Fig. 9 Exploring 2D polymorphs with CASTING.
A team lead by Prof. Subramanian K. R. S. Sankaranarayanan from Center for Nanoscale Materials, Argonne National Laboratory, introduced CASTING which is a workflow that implements a continuous action space tree-based RL search algorithm for CSP in a high-dimensional search space. 
Fig. 10 Comparison of the performance of CASTING with commonly used optimizers in crystal structure prediction.
The authors discuss the important algorithmic modifications that are needed in the MCTS to successfully apply it to continuous search space inverse problems associated with structure and topology predictions. To showcase the efficacy of the CASTING framework, the authors apply CASTING to a wide range of representative systems—single-component metallic systems such as Ag and Au, covalent systems such as C, binary systems such as h-BN and C-H, and multicomponent perovskite systems such as doped NNO.
Fig. 11 Exploration of the configurational space of hydrogen doped Neodymium Nickel Oxide (NNO) with CASTING framework.
Additionally, the authors perform the inverse design of super-hard carbon phases using multi-objective optimization. The authors demonstrate the scalability, accuracy of sampling, and speed of convergence of CASTING on complex material science problems. The authors discuss the impact of the various RL hyperparameters on search performance. CASTING is also deployed to sample stable and metastable polymorphs across systems with dimensionality ranging from 3D (bulk) to low dimensional systems such as 0D (clusters) and 2D (sheets). Comparisons to other metaheuristic search algorithms such as genetic algorithms, basin hopping, and random sampling are also shown—the MCTS is demonstrated to have a superior performance in terms of the solution quality and the speed of convergence.
Fig. 12 Inverse design of super hard phases of Carbon (C).
The authors expect MCTS to perform well, especially for complex search landscape with multiple objectives, multiple species, and multi-dimensional systems. Overall, the authors successfully demonstrate the development and application of an RL techniques such as MCTS for inverse materials design and discovery problems related to structure and topology predictions. This article was recently published in npj Computational Materials 9: 177 (2023).
原文Abstract及其翻譯
A Continuous Action Space Tree search for INverse desiGn (CASTING) framework for materials discovery（連續(xù)動作空間樹搜索用于材料發(fā)現(xiàn)的逆向設(shè)計（CASTING）框架）
Suvo Banik, Troy Loefller, Sukriti Manna, Henry Chan, Srilok Srinivasan, Pierre Darancet, Alexander Hexemer & Subramanian K. R. S. Sankaranarayanan
Abstract
Material properties share an intrinsic relationship with their structural attributes, making inverse design approaches crucial for discovering new materials with desired functionalities. Reinforcement Learning (RL) approaches are emerging as powerful inverse design tools, often functioning in discrete action spaces. This constrains their application in materials design problems, which involve continuous search spaces. Here, we introduce an RL-based framework CASTING (Continuous Action Space Tree Search for inverse design), that employs a decision tree-based Monte Carlo Tree Search (MCTS) algorithm with continuous space adaptation through modified policies and sampling. Using representative examples like Silver (Ag) for metals, Carbon (C) for covalent systems, and multicomponent systems such as graphane, boron nitride, and complex correlated oxides, we showcase its accuracy, convergence speed, and scalability in materials discovery and design. Furthermore, with the inverse design of super-hard Carbon phases, we demonstrate CASTING’s utility in discovering metastable phases tailored to user-defined target properties and preferences.
摘要文章來源：http://www.zghlxwxcb.cn/news/detail-833566.html
材料的性能與其結(jié)構(gòu)特征息息相關(guān)，這種關(guān)聯(lián)性促使逆向設(shè)計成為尋找具備特定功能新材料的關(guān)鍵手段。最近，強化學(xué)習(xí)（RL）方法作為逆向設(shè)計的強有力工具慢慢嶄露頭角，通常這些方法在離散的動作空間內(nèi)發(fā)揮作用。然而，這種做法限制了它們在材料設(shè)計中的應(yīng)用，因為這通常涉及到連續(xù)的搜索空間。在此，我們介紹一個基于RL的新框架——CASTING（連續(xù)動作空間樹搜索逆向設(shè)計），它采用了一種基于決策樹的蒙特卡洛樹搜索（MCTS）算法，并且經(jīng)過策略調(diào)整和采樣改良，使其適應(yīng)連續(xù)空間。我們通過一系列代表性案例，如金屬中的銀（Ag）、共價體系中的碳（C）、以及復(fù)合材料系統(tǒng)，例如石墨烯、氮化硼和復(fù)雜的相關(guān)氧化物，來展現(xiàn)CASTING框架在材料發(fā)現(xiàn)和設(shè)計中的高準(zhǔn)確度、快速收斂性和良好的擴展性。此外，通過針對超硬碳相材料的逆向設(shè)計實例，我們證明了CASTING在探索符合用戶指定目標(biāo)性能和偏好的亞穩(wěn)態(tài)材料方面的實用價值和有效性。文章來源地址http://www.zghlxwxcb.cn/news/detail-833566.html
到了這里，關(guān)于想做材料逆向設(shè)計？問問人工智能吧的文章就介紹完了。如果您還想了解更多內(nèi)容，請在右上角搜索TOY模板網(wǎng)以前的文章或繼續(xù)瀏覽下面的相關(guān)文章，希望大家以后多多支持TOY模板網(wǎng)！
