Scope
AI for Science (AI4Sci) is an interdisciplinary journal committed to publishing high-impact original research, reviews, and perspectives that highlight the transformative applications of artificial intelligence (AI) in driving scientific innovation. The journal strives to bridge gaps among disciplines, foster collaboration among researchers, and accelerate the development of AI-driven tools and methodologies that can fundamentally reshape how science is conducted. It provides a platform for the publication of impactful works spanning all domains where AI intersects with scientific discovery and applications. Topics of interest include but are not limited to the following:
AI algorithms for science
Highlights the methodologies that enhance AI models for scientific research, such as materials science, physics, biology, etc. Key topics include but are not limited to:
• AI-driven approaches to improve simulations in fields such as materials science, physics, biology, mathematics, and information science.
• Development of novel AI algorithms/methods to improve the predictive power, accuracy, and efficiency of models for scientific applications.
• AI-assisted data processing and interpretation for physical science, including the optimization of design of experiments, and data analysis.
• Enhancement or optimization of existing AI algorithms for specific scientific challenges including AI itself.
AI software and toolkit for science
Focuses on development, application, and dissemination of AI-driven software, frameworks, and toolkits specifically designed to address challenges and opportunities in scientific research. Examples include but not limited to:
• Design and implementation of open-source or proprietary AI software tailored for scientific applications.
• Creation of specialized libraries, APIs, or platforms to facilitate the integration of AI techniques in research workflows.
• AI-powered tools for solving domain-specific problems, such as protein structure prediction in biology or reaction optimization in chemistry.
• Collaborative software platforms fostering interdisciplinary efforts that makes benchmarking, validation, and collaboration easy.
AI-ready datasets for science
Emphasizes on the creation, curation, sharing, and utilization of high-quality, AI-ready datasets that enable cutting-edge scientific research and discovery. AI-ready datasets are structured to seamlessly integrate with artificial intelligence (AI) models, offering features such as accessibility, standardization, and scalability. These datasets are critical for advancing AI applications in diverse scientific domains by providing reliable and well-annotated data for training, testing, and validation. Key topics can be:
• Creation and publication of domain-specific world-class datasets optimized for AI research in fields such as physics, chemistry, biology, materials science, environmental science, etc.
• Promotion of open-access, AI-ready datasets to support transparency, reproducibility, and collaboration across scientific communities.
Embodied AI for science
Explores AI systems with a physical or virtual presence that interact with the environment—in advancing scientific discovery, experimentation, and implementation. Embodied AI integrates perception, reasoning, learning, and physical interaction, offering unique opportunities for automating complex tasks, advancing experimental methodologies, and solving real-world scientific challenges, which include but are not limited to the following:
• Design and use of autonomous robots and AI agents to perform laboratory experiments, analyze results, and optimize experimental workflows.
• Embodied AI for dynamic adjustments to experimental conditions, enabling real-time decision-making and adaptation.
• Physical AI agents for precise control, measurement, and monitoring in sophisticated experiments, such as in materials characterization or biological assays.
• Integration of physical models, simulations, and real-world interaction for embodied AI learning, enabling more reliable scientific predictions.
• Collaborative embodied AI systems bridging multiple scientific disciplines, such as robotic platforms for integrated chemical, biological, and physical experiments.
AI for Science (AI4Sci) serves as a hub for forward-thinking researchers, offering a platform to share significant breakthroughs and innovative methodologies. It is committed to advancing the role of AI in uncovering new scientific frontiers while fostering interdisciplinary collaboration and innovation in science and technology.
Editorial Board
Editors-in-Chief
Gian-Marco Rignanese
Ecole Polytechnique de Louvain (EPL), Belgium
Materials informatics for electronic, optical, vibrational, and transport properties
Weihua Wang
Institute of Physics, Beijing, Chinese Academy of Science; Songshan Lake Materials laboratory, Dongguan, China
Advisory Board
Silvana Botti
Research Center Future Energy Materials and Systems; Ruhr University Bochum, Germany
Theoretical spectroscopy, materials for energy, density functional theory, machine learning
Roberto Car
Princeton University, Princeton, USA
Electronic and atomistic structure of material and molecular systems, ab-initio molecular dynamics, numerical simulations, liquid and amorphous systems, hydrogen bonds in water, nuclear quantum dynamics, quantum systems, electronic correlation
Gerbrand Ceder
University of California, Berkeley, USA
Materials design, computational modeling, energy storage, autonomous laboratories, machine learning
Wenhui Duan
Tsinghua University, Beijing, China
AI Electronic structure of condensed matters, physics of low-dimensional and nano-structures, ferroelectrics physics
Weinan E
Peking University, Beijing, China
Numerical algorithms, machine learning and multi-scale modeling, with applications to chemistry, material sciences and fluid mechanics
Weihai Fang
Beijing Normal University, Beijing, China
AI for Theoretical and computational photochemistry
Xingao Gong
Fudan University, Shanghai, China
AI electronic structures, Molecular dynamics methods, materials design, structural and dynamic properties of surfaces and interfaces
Anubhav Jain
Lawrence Berkeley National Laboratory, Berkeley, USA
Computational materials science, machine learning, thermoelectric materials, thermal storage materials, and data analytics for solar installations
Kuijuan Jin
Institute of Physics CAS, Beijing, China
Photon interaction with dimensional oxides
Yousung Jung
Seoul National University, Seoul, Korea
Chemical and materials Informatics, computational chemistry, materials simulations and design
Haiqing Lin
Zhejiang University, Hangzhou, China
Computational physics, condensed matter physics
Yanming Ma
Jilin University, Changchun, China
CALYPSO method, crystal structure predictions, first-principles calculations, structural design of novel functional materials
Nicola Marzari
École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland
Paul Scherrer Institut (PSI), Villigen, Switzerland
Computational materials science, condensed matter physics, density-functional theory
Elisa Molinari
University of Modena and Reggio Emilia, Modena, Italy
Theoretical and computational condensed matter science, low-dimensional structures, electron-phonon interactions
Tao Xiang
Institute of Physics CAS, Beijing, China
AI for density-matrix and tensor-network renormalization, AI Quantum physics
Jianxin Xie
University of Science and Technology Beijing, Beijing, China
AI technology in materials development, Theory and technologies of materials genome engineering, Advanced materials processing
Kristin Persson
University of California, Berkeley, USA
Electrodes
for next-generation batteries, dynamics of battery electrolytes,
modeling solid-electrolyte interphase formation, materials synthesis
Alexandre Tkatchenko
University of Luxembourg, Luxembourg
Intermolecular interactions, AI for science, chemical physics, materials physics
Christopher M Wolverton
Northwestern University, Evanston, USA
Computational materials science, materials informatics, energy materials, materials discovery, materials design
Tongyi Zhang
Materials Genome Institute of Shanghai University, Shanghai, China
Materials/mechanics
informatics, AI for materials/mechanics, AI materials/mechanics
laboratories, and AI materials/mechanics computations
Ya-Qin Zhang
Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China
AI in transportation, healthcare and IOT, big data, computational intelligence, intelligent robotics
Associate Editors
Nongnuch Artrith
Utrecht University, Utrecht, The Netherland
Computational materials science, artificial neural networks, machine learning, electrocatalysis, energy storage
Yongqing Cai
University of Macau, Macau, China
Phonon, computational materials, computational physics, materials informatics
Wei Chen
The State University of New York, Buffalo, USA
Data-driven and physics-based modeling of material systems, computational design of multi-principal element materials, materials informatics for accelerated materials and knowledge discovery
Pengfei Guan
Ningbo Institute of Materials Technology & Engineering CAS, Ningbo, China
Computational materials science, AI-driven multiscale materials simulation & design, disordered materials, non-equilibrium physics
Yang-Hui He
London Institute for Mathematical Sciences, Royal Institution &
Merton College, University of Oxford, Landon, UK
Mathematical physics, algebraic geometry, number theory, AI-assisted discovery
Weile Jia
Institute of Computing Technology CAS, Beijing, China
AI-based Molecular Dynamics, HPC+AI
Haiguang Liu
Microsoft Research, Beijing, China
Membrane protein dynamics, protein engineering, antibacterial peptide design, protein dynamics/interactions
Sheng Meng
Institute of Physics CAS, Beijing, China
Excited state dynamics, molecules at surfaces, energy conversion, nano mechanics
Janosh Riebesell
Radical AI, New York, USA
Computational materials discovery, machine learning, software engineering, data visualization
David Rousseau
Université d'Angers, Angers, France
Computational imaging, AI based phenotyping of population (cells, animals, plants, humans), computer vision
Jonathan Schmidt
ETH, Zurich, Switzerland
Machine learning, materials science, condensed matter, density functional theory
Martin Uhrin
Université Grenoble Alpes, France
Physics-inspired
machine learning methods for atomistic systems, generative models and
inverse design algorithms for materials and molecules, machine-learning
assisted structure characterisation (NMR, Raman, infrared, XAS),
development of scientific software and data standards
Lei Wang
Institute of Physics CAS, Beijing, China
Deep learning and its application in scientific discoveries, new algorithms for quantum many-body computation, emergence and universal laws in many-body systems
Yong Xu
Tsinghua University, Beijing, China
Computational materials science, condensed matter physics, first-principles methods
Shuxin Zheng
Zhongguancun Institute of Artificial Intelligence, Beijing, China
General AI, generative AI, and its application in scientific discovery
Executive Editors
Miao Liu
Institute of Physics, Beijing, Chinese Academy of Science; Songshan Lake Materials Laboratory, Dongguan, China
Yuanchao Hu
Songshan Lake Materials Laboratory, Dongguan, China