# AI for Science Domain: Artificial Intelligence · 250 papers indexed · newest 2026-10-28 Machine learning that accelerates discovery: protein structure, machine-learned force fields, materials discovery, weather and autonomous laboratories. Key concepts: machine learning interatomic potential, materials discovery, scientific discovery, autonomous laboratory, neural network potential, AI for science, foundation model science ## Most influential - **[Recent advances and applications of machine learning in solid-state materials science](https://space-kitty.com/papers/doi:10.1038/s41524-019-0221-0)**. Jonathan Schmidt, Mário R. G. Marques, Silvana Botti et al. · 2019 · npj Computational Materials (doi:10.1038/s41524-019-0221-0 · 2,636 citations). Source: > Abstract One of the most exciting tools that have entered the material science toolbox in recent years is machine learning. This collection of statistical methods has already proved to be capable of considerably speeding up both fundamental and applied research. At present, we are witnessing an explosion of works that develop and apply machine learning to solid-state systems. We provide a comprehensive overview and analysis of the most recent research in this topic. As a starting point, we introduce machine learning principles, algorithms, descriptors, and databases in materials science. We co… > _Abstract excerpt by Jonathan Schmidt et al., CC-BY, https://doi.org/10.1038/s41524-019-0221-0; truncated._ - **[Water electrolysis: from textbook knowledge to the latest scientific strategies and industrial developments](https://space-kitty.com/papers/doi:10.1039/d0cs01079k)**. Marian Chatenet, Bruno Georges Pollet, Dario R. Dekel et al. · 2022 · Chemical Society Reviews (doi:10.1039/d0cs01079k · 2,022 citations). Source: > footprint. The viability of water electrolysis still hinges on the availability of durable earth-abundant electrocatalyst materials and the overall process efficiency. This review spans from the fundamentals of electrocatalytically initiated water splitting to the very latest scientific findings from university and institutional research, also covering specifications and special features of the current industrial processes and those processes currently being tested in large-scale applications. Recently developed strategies are described for the optimisation and discovery of active and durable … > _Abstract excerpt by Marian Chatenet et al., CC-BY, https://doi.org/10.1039/d0cs01079k; truncated._ - **[Materials Design and Discovery with High-Throughput Density Functional Theory: The Open Quantum Materials Database (OQMD)](https://space-kitty.com/papers/doi:10.1007/s11837-013-0755-4)**. James E. Saal, Scott J. Kirklin, Muratahan Aykol et al. · 2013 · JOM (doi:10.1007/s11837-013-0755-4 · 2,540 citations). Source: - **[Inverse molecular design using machine learning: Generative models for matter engineering](https://space-kitty.com/papers/doi:10.1126/science.aat2663)**. Benjamín Sánchez-Lengeling, Alán Aspuru‐Guzik · 2018 · Science (doi:10.1126/science.aat2663 · 2,071 citations). Source: - **[An autonomous laboratory for the accelerated synthesis of inorganic materials](https://space-kitty.com/papers/doi:10.1038/s41586-023-06734-w)**. Nathan J. Szymanski, Bernardus Rendy, Yuxing Fei et al. · 2023 · Nature (doi:10.1038/s41586-023-06734-w · 1,037 citations). Source: > , we introduce the A-Lab, an autonomous laboratory for the solid-state synthesis of inorganic powders. This platform uses computations, historical data from the literature, machine learning (ML) and active learning to plan and interpret the outcomes of experiments performed using robotics. Over 17 days of continuous operation, the A-Lab realized 41 novel compounds from a set of 58 targets including a variety of oxides and phosphates that were identified using large-scale ab initio phase-stability data from the Materials Project and Google DeepMind. Synthesis recipes were proposed by natural-la… > _Abstract excerpt by Nathan J. Szymanski et al., CC-BY, https://doi.org/10.1038/s41586-023-06734-w; truncated._ - **[Machine-learning-assisted materials discovery using failed experiments](https://space-kitty.com/papers/doi:10.1038/nature17439)**. Paul Raccuglia, Katherine C. Elbert, Philip Adler et al. · 2016 · Nature (doi:10.1038/nature17439 · 1,724 citations). Source: - **[A universal graph deep learning interatomic potential for the periodic table](https://space-kitty.com/papers/arxiv:2202.02450)**. Chi Chen, Shyue Ping Ong · 2022 · Nature Computational Science (arXiv:2202.02450 · doi:10.1038/s43588-022-00349-3 · 997 citations). Source: > Interatomic potentials (IAPs), which describe the potential energy surface of atoms, are a fundamental input for atomistic simulations. However, existing IAPs are either fitted to narrow chemistries or too inaccurate for general applications. Here, we report a universal IAP for materials based on graph neural networks with three-body interactions (M3GNet). The M3GNet IAP was trained on the massive database of structural relaxations performed by the Materials Project over the past 10 years and has broad applications in structural relaxation, dynamic simulations and property prediction of materi… - **[Materials discovery and design using machine learning](https://space-kitty.com/papers/doi:10.1016/j.jmat.2017.08.002)**. Yue Liu, Tianlu Zhao, Wangwei Ju et al. · 2017 · Journal of Materiomics (doi:10.1016/j.jmat.2017.08.002 · 1,276 citations). Source: - **[Unsupervised word embeddings capture latent knowledge from materials science literature](https://space-kitty.com/papers/doi:10.1038/s41586-019-1335-8)**. Vahe Tshitoyan, John M. Dagdelen, Leigh Weston et al. · 2019 · Nature (doi:10.1038/s41586-019-1335-8 · 1,123 citations). Source: - **[Machine learning–enabled high-entropy alloy discovery](https://space-kitty.com/papers/doi:10.1126/science.abo4940)**. Ziyuan Rao, Po‐Yen Tung, Ruiwen Xie et al. · 2022 · Science (doi:10.1126/science.abo4940 · 755 citations). Source: - **[Accelerating materials property predictions using machine learning](https://space-kitty.com/papers/doi:10.1038/srep02810)**. Ghanshyam Pilania, Chenchen Wang, Xun Jiang et al. · 2013 · Scientific Reports (doi:10.1038/srep02810 · 856 citations). Source: > The materials discovery process can be significantly expedited and simplified if we can learn effectively from available knowledge and data. In the present contribution, we show that efficient and accurate prediction of a diverse set of properties of material systems is possible by employing machine (or statistical) learning methods trained on quantum mechanical computations in combination with the notions of chemical similarity. Using a family of one-dimensional chain systems, we present a general formalism that allows us to discover decision rules that establish a mapping between easily acce… > _Abstract excerpt by Ghanshyam Pilania et al., CC-BY, https://doi.org/10.1038/srep02810; truncated._ - **[Accelerating the discovery of materials for clean energy in the era of smart automation](https://space-kitty.com/papers/doi:10.1038/s41578-018-0005-z)**. Daniel P. Tabor, Loı̈c M. Roch, Semion K. Saikin et al. · 2018 · Nature Reviews Materials (doi:10.1038/s41578-018-0005-z · 778 citations). Source: > The discovery and development of novel materials in the field of energy are essential to accelerate the transition to a low-carbon economy. Bringing recent technological innovations in automation, robotics and computer science together with current approaches in chemistry, materials synthesis and characterization will act as a catalyst for revolutionizing traditional research and development in both industry and academia. This Perspective provides a vision for an integrated artificial intelligence approach towards autonomous materials discovery, which, in our opinion, will emerge within the ne… > _Abstract excerpt by Daniel P. Tabor et al., CC-BY, https://doi.org/10.1038/s41578-018-0005-z; truncated._ - **[The rise of self-driving labs in chemical and materials sciences](https://space-kitty.com/papers/doi:10.1038/s44160-022-00231-0)**. Milad Abolhasani, Eugenia Kumacheva · 2023 · Nature Synthesis (doi:10.1038/s44160-022-00231-0 · 584 citations). Source: - **[Towards Universal Neural Network Potential for Material Discovery Applicable to Arbitrary Combination of 45 Elements](https://space-kitty.com/papers/arxiv:2106.14583)**. So Takamoto, Chikashi Shinagawa, Daisuke Motoki et al. · 2021 · Nature Communications (arXiv:2106.14583 · doi:10.1038/s41467-022-30687-9 · 444 citations). Source: > Computational material discovery is under intense study owing to its ability to explore the vast space of chemical systems. Neural network potentials (NNPs) have been shown to be particularly effective in conducting atomistic simulations for such purposes. However, existing NNPs are generally designed for narrow target materials, making them unsuitable for broader applications in material discovery. To overcome this issue, we have developed a universal NNP called PreFerred Potential (PFP), which is able to handle any combination of 45 elements. Particular emphasis is placed on the datasets, wh… - **[Accelerated discovery of stable lead-free hybrid organic-inorganic perovskites via machine learning](https://space-kitty.com/papers/doi:10.1038/s41467-018-05761-w)**. Shuaihua Lu, Qionghua Zhou, Yixin Ouyang et al. · 2018 · Nature Communications (doi:10.1038/s41467-018-05761-w · 725 citations). Source: > Rapidly discovering functional materials remains an open challenge because the traditional trial-and-error methods are usually inefficient especially when thousands of candidates are treated. Here, we develop a target-driven method to predict undiscovered hybrid organic-inorganic perovskites (HOIPs) for photovoltaics. This strategy, combining machine learning techniques and density functional theory calculations, aims to quickly screen the HOIPs based on bandgap and solve the problems of toxicity and poor environmental stability in HOIPs. Successfully, six orthorhombic lead-free HOIPs with pro… > _Abstract excerpt by Shuaihua Lu et al., CC-BY, https://doi.org/10.1038/s41467-018-05761-w; truncated._ ## Newest - **[Crystoria: A Large-Scale Crystal Dataset Linking Thermodynamic and Dynamical Stability for Materials AI](https://space-kitty.com/papers/arxiv:2610.38195)**. Ke-Xin Pang, Ze-Feng Gao, Yan Gao et al. · 2026 (arXiv:2610.38195). Source: - **[Learning Between the Lines: Interaction Interpolation in a Multi Element Machine Learning Interatomic Potential](https://space-kitty.com/papers/arxiv:2610.38876)**. Ademola Soyemi, Kipton Barros, Timothy C. Germann et al. · 2026 (arXiv:2610.38876). Source: - **[Development and application of a machine learning potential for diamond surfaces and their sliding interfaces with silicon nitride and silica: effect of passivation, orientation and load](https://space-kitty.com/papers/arxiv:2610.38937)**. Enrico Pedretti, Maria Clelia Righi · 2026 (arXiv:2610.38937). Source: - **[First-principles-based search for emergent topological spin textures in transition-metal dichalcogenide monolayers](https://space-kitty.com/papers/arxiv:2610.36542)**. Yuhyun Cha, Do Hoon Kiem, Myung Joon Han · 2026 · npj Comput. Mater. 12, 292 (2026) (arXiv:2610.36542 · doi:10.1038/s41524-026-02162-2). Source: - **[The Acridine Polymorph Landscape: Characterization and Selective Control by Additives](https://space-kitty.com/papers/arxiv:2610.37597)**. Adam Lahouari, Hengyu Zhou, Nikolaos Galanakis et al. · 2026 (arXiv:2610.37597). Source: - **[A unified coarse-grained neural network potential for the dynamics of biomolecular complexes](https://space-kitty.com/papers/arxiv:2610.37606)**. Antonio Mirarchi, Stephen E. Farr, Adrià Peréz et al. · 2026 (arXiv:2610.37606). Source: - **[Application of PDE emulators for a multi-material, multi-physics simulation problem](https://space-kitty.com/papers/arxiv:2610.37972)**. Diane Oyen, Morgan Jones, Adithan Kathirgamaraju et al. · 2026 (arXiv:2610.37972 · doi:10.1109/icmla69890.2026.00072). Source: - **[High-efficiency solid-state electrochemical thermal switching through phonon engineering of 2D materials](https://space-kitty.com/papers/arxiv:2610.35547)**. Harry Mclean, Steven Paul Hepplestone · 2026 (arXiv:2610.35547). Source: - **[Retention-constrained fine-tuning of a pre-trained aluminium MACE potential for non-equilibrium defect dynamics and plasticity](https://space-kitty.com/papers/arxiv:2610.35653)**. Yue Wu, Yuan Tian, Deng Pan et al. · 2026 (arXiv:2610.35653). Source: - **[Learning the Chronology of Materials Discovery for Synthesizability Prediction](https://space-kitty.com/papers/arxiv:2610.36193)**. Junkil Park, Aron Walsh · 2026 (arXiv:2610.36193). Source: --- Space Kitty Archive · https://space-kitty.com · API: https://space-kitty.com/api/v1 · MCP: https://space-kitty.com/mcp · Premium: $0.20/request via x402 (Base Sepolia (testnet)). Metadata: arXiv (CC0), OpenAlex (CC0), Europe PMC (CC BY/CC0 works), ClinicalTrials.gov.