杨小康,许岩岩,陈露,王韫博,高岳,田济东,俞凯,金耀辉,梅宏.AI for Science：智能化科学设施变革基础研究[J].中国科学院院刊,2024,39(1):59-69.

AI for Science：智能化科学设施变革基础研究

AI for Science：AI enabled scientific facility transforms fundamental research

杨小康¹
上海交通大学 人工智能研究院 上海 200240
YANG Xiaokang¹
Artificial Intelligence Institute, Shanghai Jiao Tong University, Shanghai 200240, China
许岩岩¹
上海交通大学 人工智能研究院 上海 200240
XU Yanyan¹
Artificial Intelligence Institute, Shanghai Jiao Tong University, Shanghai 200240, China
陈露^1,2
上海交通大学 人工智能研究院 上海 200240;上海交通大学 计算机科学与工程系 上海 200240
CHEN Lu^1,2
Artificial Intelligence Institute, Shanghai Jiao Tong University, Shanghai 200240, China;Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
王韫博¹
上海交通大学 人工智能研究院 上海 200240
WANG Yunbo¹
Artificial Intelligence Institute, Shanghai Jiao Tong University, Shanghai 200240, China
高岳¹
上海交通大学 人工智能研究院 上海 200240
GAO Yue¹
Artificial Intelligence Institute, Shanghai Jiao Tong University, Shanghai 200240, China
田济东¹
上海交通大学 人工智能研究院 上海 200240
TIAN Jidong¹
Artificial Intelligence Institute, Shanghai Jiao Tong University, Shanghai 200240, China
俞凯^1,2
上海交通大学 人工智能研究院 上海 200240;上海交通大学 计算机科学与工程系 上海 200240
YU Kai^1,2
Artificial Intelligence Institute, Shanghai Jiao Tong University, Shanghai 200240, China;Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
金耀辉¹
上海交通大学 人工智能研究院 上海 200240
JIN Yaohui¹
Artificial Intelligence Institute, Shanghai Jiao Tong University, Shanghai 200240, China
梅宏^3*
北京大学 信息科学技术学院 北京 100871
MEI Hong^3*
School of Electronics Engineering and Computer Science, Peking University, Beijing 100871, China

         人工智能驱动科学研究;生成式人工智能;语言大模型;科学设施

        AI for Science;generative AI;large language models;scientific facility

        近年来，人工智能（AI）在前沿科技领域取得了诸如AlphaFold2、核聚变智能控制、新冠药物设计等诸多令人瞩目成果，表明AI for Science正在成为一种新的研究范式。实现智能时代的基础科学源头创新及其下游重大技术创新，需破解2个方面的核心问题：（1）如何利用新一代AI（特别是生成式AI及大模型）的通用性和创造性推动新范式的形成；（2）如何利用AI实现对传统科学设施的赋能与改造。文章提出一种智能化科学设施的建设构想，兼顾“高度智能化的科学新设施”和“AI赋能已有科学大设施”2个层面的需求，构筑AI for Science的科学设施体系，形成科学领域大模型、生成式模拟与反演、自主智能无人实验及大规模可信科研协作等创新功能，加速重大科学发现、变革性物质合成，以及重大工程技术应用。

        In recent years, artificial intelligence (AI) has achieved numerous disruptive breakthroughs in frontier scientific and technological fields, such as AlphaFold2 for protein structure prediction, intelligent control of nuclear fusion, and drug design for COVID-19. These achievements indicate that AI for Science is becoming a new paradigm in research. To achieve fundamental scientific innovation and major technological breakthroughs in the era of intelligence, two core issues should be addressed: 1) how to harness the generality and creativity of the new-generation of AI, especially generative AI and large language models (LLMs), to promote the formation of new paradigms; 2) how to empower and transform traditional scientific facilities using AI. To tackle these challenges, this study proposes a concept of AI-enabled scientific facility (AISF) that caters to the requirements of both establishment of totally new intelligent scientific facility and AI empowerment of existing scientific facilities. It aims to construct an infrastructure system for AI for Science, enabling innovative functionalities such as scientific large language models (LLMs), generative simulation and inversion, autonomous intelligent unmanned experiments, and large-scale trustworthy scientific collaboration. These advancements will accelerate scientific discoveries, synthesis of transformative materials, and application of related engineering technologies.