Conference: Artificial Intelligence for Multidisciplinary Exploration and Discovery (AIMED) in Heterogeneous Catalysis: A Workshop

人工智能多学科探索和发现多相催化研讨会（AIMED CWS）由Hongliang Xin（弗吉尼亚理工大学），John Kitchin（卡内基梅隆大学），Neil Schweitzer（西北大学）和Núria López（加泰罗尼亚化学研究所）共同组织。本次研讨会探讨了人工智能在加速多相催化科学探索和发现方面不断发展的作用。特别强调人工智能在解决相关条件下界面催化过程和材料行为的复杂性方面的多学科性质。主要目标是评估人工智能在该领域的现状，并确定挑战和潜在的增长机会。该研讨会将深入研究人工智能和催化的交叉点，并将涵盖广泛的主题，从人工智能在催化方面的历史发展和自动驾驶实验室兴起的算法的最新进展，到数据管理，共享，利用和再利用的复杂性和最佳实践。本次研讨会致力于为人工智能在多相催化中的大胆愿景，强调人工智能在整个研究领域的整合，在教育和劳动力培训环境中，以及在实际应用中。AIMED CWS将联合学生，早期职业研究人员和来自工业，工业，和国家实验室，以调查利用人工智能加快科学探索和发现的机遇和挑战。多相催化在广泛的化学合成和制造过程中发挥着至关重要的作用，特别是在不断增长的清洁能源和可持续化学技术领域。催化环境的多样性和复杂性，包括界面过程和材料设计的挑战，往往回避传统的实验或纯理论的方法。人工智能已经成为一套全面的方法，当与实验和计算策略相结合时，可以显着增强催化剂在合成，表征和部署方面的开发。该研讨会将分三个阶段展开：1）社区参与，收集来自催化社区的见解和建议; 2）面对面研讨会，包括主题演讲，小组讨论和早期职业研究人员的海报展示，以探索人工智能在催化中的作用;和3）后续活动，重点是创建和传播教育材料，包括AIMED催化网络研讨会系列。总体而言，AIMED CWS将在讨论和实践环节中吸引广泛的催化研究社区，鼓励多学科合作，推动该领域在人工智能时代走向新的视野。该研讨会由ENG/CBET和MPS/CHE共同资助。该奖项反映了NSF的法定使命，并被认为值得通过使用基金会的知识价值和更广泛的影响审查标准进行评估来支持。

The Artificial Intelligence for Multidisciplinary Exploration and Discovery in Heterogeneous Catalysis Workshop (AIMED CWS) is co-organized by Hongliang Xin (Virginia Tech), John Kitchin (Carnegie Mellon University), Neil Schweitzer (Northwestern University), and Núria López (Institute of Chemical Research of Catalonia). This workshop explores the evolving role of AI for accelerating scientific exploration and discovery in heterogeneous catalysis. Special emphasis is placed on the multidisciplinary nature of AI endeavors in tackling the complexities underpinning catalytic processes at interfaces and material behaviors under relevant conditions. The primary objectives are to evaluate AI’s current state in this field and to identify challenges and potential growth opportunities. The workshop will delve deep into the intersection of AI and catalysis and will cover a broad spectrum of topics from AI’s historical development in catalysis and recent advancements in algorithms for the rise of self-driving labs, to the intricacies and best practices in data management, sharing, utilization, and repurposing. This workshop is committed to a bold vision for AI in heterogeneous catalysis, highlighting the integration of AI across the research spectrum, in educational and workforce training settings, and in practical applications.The AIMED CWS will unite students, early-career researchers, and senior-level technical experts from academe, industry, and national laboratories to investigate the opportunities and challenges in leveraging AI to expedite scientific exploration and discovery. Heterogeneous catalysis plays a vital role in a wide array of chemical synthesis and manufacturing processes, particularly in the growing fields of clean energy and sustainable chemical technologies. The diverse and intricate nature of catalytic environments, encompassing interfacial processes and material design challenges, often eludes traditional experimental or purely theoretical approaches. AI has emerged as a comprehensive suite of methods that, when combined with experimental and computational strategies, significantly enhances catalyst development across synthesis, characterization, to deployment. The workshop will unfold in three phases: 1) Community Engagement, gathering insights and recommendations from the catalysis community; 2) In-Person Workshop, featuring keynote lectures, panel discussions, and poster presentations by early career researchers to explore AI’s role in catalysis; and 3) Follow-Up Activities, focusing on creating and disseminating educational materials, including an AIMED Webinar Series in Catalysis. Collectively, the AIMED CWS will engage a broad catalysis research community in discussions and hands-on sessions, encouraging multidisciplinary collaborations that drive the field towards new horizons in the age of AI.This workshop is jointly funded by ENG/CBET and MPS/CHE.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.