Portfolio item number 1
Short description of portfolio item number 1
Short description of portfolio item number 1
Short description of portfolio item number 2 
Published in Journal of the American Chemical Society, 2019
Time-resolved terahertz spectroscopy, combined with a new sample preparation method, measures the photoconductivity of the conductive MOF Zn2TTFTB without contacts, resolving sub-picosecond carrier dynamics with two distinct lifetimes and Drude–Smith frequency dependence.
Recommended citation: Pattengale, B., Neu, J., Ostresh, S., Hu, G., Spies, J.A., Okabe, R., Brudvig, G.W., & Schmuttenmaer, C.A. (2019). Metal-Organic Framework Photoconductivity via Time-Resolved Terahertz Spectroscopy. Journal of the American Chemical Society 141, 9793–9797.
Download Paper
Published in Chemical Science, 2020
Photosensitizing arrays built from conductive metal–organic frameworks enable light harvesting and efficient charge separation, demonstrated as a conductive MOF photoanode.
Recommended citation: Pattengale, B., Freeze, J.G., Guberman-Pfeffer, M., Okabe, R., Ostresh, S., Chaudhuri, S., Batista, V.S., & Schmuttenmaer, C.A. (2020). A Conductive Metal-Organic Framework Photoanode. Chemical Science 11, 9593–9603.
Download Paper
Published in Journal of Biomolecular NMR, 2021
SLAP, a solvent-suppression scheme based on adiabatic inversion pulses for 1H-detected solid-state NMR, achieves up to 3.5-fold better suppression than MISSISSIPPI on a uniformly 13C/15N-labeled GB1 sample at 60 kHz magic-angle spinning, at lower average RF power.
Recommended citation: Matsunaga, T., Okabe, R., & Ishii, Y. (2021). Efficient solvent suppression with adiabatic inversion for 1H-detected solid-state NMR. Journal of Biomolecular NMR 12, 365-370.
Download Paper
Published in iScience, 2022
A Euclidean-equivariant graph neural network classifies magnetic order directly from atomic coordinates, using a descriptor that encodes crystal structures of any space group, as a data-driven complement to neutron diffraction and semi-empirical DFT.
Recommended citation: Merker, H.A., Heiberger, H., Nguyen, L., Liu, T., Chen, Z., Andrejevic, N., Drucker, N.C., Okabe, R., Wang, Y., Smidt, T., & Li, M. (2022). Machine Learning Magnetism Classifiers from Atomic Coordinates. iScience 25, 10, 105192.
Download Paper
Published in Synchrotron Radiation News, 2022
A feature article surveying how machine learning is reshaping neutron and X-ray scattering, from phase mapping and crystallographic analysis to super-resolution small-angle scattering, and the criteria that determine when ML-based analysis succeeds.
Recommended citation: Drucker, N.C., Liu, T., Chen, Z., Okabe, R., Chotrattanapituk, A., Nguyen, T., Wang, Y., & Li, M. (2022). Challenges and Opportunities of Machine Learning on Neutron and X-ray Scattering. Synchrotron Radiation News 35, 16-20.
Download Paper
Published in Chemistry of Materials, 2023
A materials perspective on topological superconductors: a short review of the basics and theory, an overview of natural and synthetic candidate materials, and the experimental signatures used to identify them, with a call for new signatures and stronger computational support.
Recommended citation: Mandal, M., Drucker, N.C., Siriviboon, P., Nguyen, T., Boonkird, A., Lamichhane, T.N., Okabe, R., Chotrattanapituk, A., & Li, M. (2023). Topological superconductors from a materials perspective. Chemistry of Materials 35, 16, 6184–6200.
Download Paper
Published in IEEE Magnetic Letters, 2023
A summary of recent developments in AI- and ML-driven searches for magnetic materials, with a flowchart to guide the choice of approach and an overview of work on topological materials, Heusler alloys, interfaces, and permanent magnets, based on the IEEE Intermag 2023 symposium.
Recommended citation: Okabe, R., Li, M., Iwasaki, Y., Regnault, N., Felser, C., Shirai, M., Kovacs, A., Schrefl, T., & Hirohata, A. (2023). Materials Informatics for the Development and Discovery of Future Magnetic Materials. IEEE Magnetic Letters 14, 1-5.
Download Paper
Published in arXiv, 2024
Thermodynamic, dilatometry, resonant X-ray, inelastic neutron, Larmor diffraction, and thermoelectric measurements reveal an unconventional, incipient nematic order in the kagome metal CoSn near 225 K, explained by thermally excited flat bands that promote symmetry breaking.
Recommended citation: Drucker, N.C., Nguyen, T., Mandal, M., Siriviboon, P., Quan, Y., Boonkird, A., Okabe, R., Li, F., Burrage, K., Funuma, F., Matsuda, M., Abernathy, D., Williams, T., Chi, S., Ye, F., Nelson, C., Liao, B., Volkov, P., & Li, M. (2024). Incipient Nematicity from Electron Flat Bands in a Kagome Metal. arXiv preprint arXiv:2401.17141.
Download Paper
Published in Nature Communications, 2024
A radiation mapping framework using Tetris-inspired detector pixels: inter-pixel padding plus neural networks trained on Monte Carlo data let a detector with as few as four pixels predict source direction, and a moving detector with maximum a posteriori estimation localizes sources, verified in field tests.
Recommended citation: Okabe, R.†, Xue, S.†, Vavrek, J.†, Yu, J., Pavlovsky, R., Negut, V., Quiter, B., Cates, J., Liu, T., Forget, B., Jegelka, S., Kohse, G., Hu, L-W., & Li, M. (2024). Tetris-Inspired Detector with Neural Network for Radiation Mapping. Nature Communications 15, 3061.
Download Paper
Published in Applied Physics Reviews, 2024
Accelerator-based high-energy hydrogen implantation, guided by theory-driven planning, tunes the Fermi level of the bulk Weyl semimetal TaP with meV precision around the Weyl nodes while preserving crystallinity, the Weyl nodes, and carrier mobility.
Recommended citation: Mandal, M.†, Chotrattanapituk, A.†, Woller, K., Xu, H., Mao, N., Okabe, R., Boonkird, A., Nguyen, T., Drucker, N.C., Momiki, T., Li, J., Kong, J., & Li, M. (2024). Precise Fermi-level engineering in a topological Weyl semimetal via fast ion implantation. Applied Physics Reviews 11, 021429.
Download Paper
Published in Matter, 2024
A machine learning framework distinguishes Majorana zero modes from spurious zero-bias peaks using quantum transport simulations and topological data analysis, reaching 85% accuracy on 1D and 94% on 2D conductance data with Zeeman splitting.
Recommended citation: Cheng, M., Okabe, R., Chotrattanapituk, A., & Li, M. (2024). Machine Learning Detection of Majorana Zero Modes from Zero Bias Peak Measurements. Matter 7, 2507.
Download Paper
Published in Nature Computational Science, 2024
Virtual node graph neural networks predict Γ-phonon spectra and full phonon dispersions directly from atomic coordinates, orders of magnitude faster than machine-learning interatomic potentials with comparable accuracy, enabling a Γ-phonon database of over 146,000 materials.
Recommended citation: Okabe, R.†, Chotrattanapituk, A.†, Boonkird, A., Andrejevic, N., Fu, X., Jaakkola, T.S., Song, Q., Nguyen, T., Drucker, N.C., Mu, S., Liao, B., Cheng, Y., & Li, M. (2024). Virtual Node Graph Neural Network for Full Phonon Prediction. Nature Computational Science 4, 522-531.
Download Paper
Published in Advanced Materials, 2024
GNNOpt, an equivariant graph neural network with universal ensemble embedding, predicts optical spectra such as refractive index and absorption directly from crystal structures, enabling high-throughput screening of materials for light–matter applications.
Recommended citation: Hung, N.T., Okabe, R., Chotrattanapituk, A., & Li, M. (2024). Ensemble-Embedding Graph Neural Network for Direct Prediction of Optical Spectra from Crystal Structure. Advanced Materials, 2409175.
Download Paper
Published in arXiv, 2024
A framework that uses large language models to predict synthesis pathways for inorganic and quantum materials, turning literature-scale synthesis knowledge into actionable suggestions of precursors, reactions, and conditions.
Recommended citation: Okabe, R.†, West, Z.†, Chotrattanapituk, A., Cheng, M., Cordova Carrizales, D., Xie, W., Cava, R.J., & Li, M. (2024). Large Language Model-Guided Prediction Toward Quantum Materials Synthesis. arXiv preprint arXiv:2410.20976.
Download Paper
Published in arXiv, 2024
A microscopic quantum theory of X-ray photon correlation spectroscopy derived from electron–photon interaction Hamiltonians, introducing four configurations tied to distinct fourth-order density correlations and a generalized Siegert relation, which breaks down even for a non-interacting Fermi gas.
Recommended citation: Siriviboon, P.†, Fu, C.†, Landry, M.†, Okabe, R., Cordova Carrizales, D., Wang, Y., & Li, M. (2024). Quantum Theory of X-ray Photon Correlation Spectroscopy. arXiv preprint arXiv:2412.03635.
Download Paper
Published in Digital Discovery, 2025
A review of AI-driven methods for atomic vibrations: databases, structural representations, machine-learning interatomic potentials, graph neural networks, and emerging approaches that accelerate predictions of lattice dynamics, phonons, molecular dynamics, and vibrational spectra.
Recommended citation: Han, B.†, Okabe, R.†, Chotrattanapituk, A.†, Cheng, M.†, Li, M., & Cheng, Y. (2025). AI-Powered Exploration of Molecular Vibrations, Phonons and Spectroscopy. Digital Discovery.
Download Paper
Published in Advanced Materials, 2025
A review of how AI and machine learning are transforming thermoelectric materials design, from deep and graph-based models that capture structure–property relations in a multiscale defect space to AI-enhanced defect engineering and inverse design.
Recommended citation: Fu, C.†, Cheng, M.†, Hung, N.T.†, Rha, E., Chen, Z., Okabe, R., Cordova Carrizales, D., Mandal, M., Cheng, Y.Q., & Li, M. (2025). AI-driven defect engineering in advanced thermoelectric materials. Advanced Materials 37, 2505642.
Download Paper
Published in Newton, 2025
A short perspective on using AI to predict superconducting gaps, discussing how machine learning can complement first-principles approaches in the search for new superconductors.
Recommended citation: Cheng, M., Okabe, R., & Li, M. (2025). Closing the superconducting gap with AI. Newton 1, 100093.
Download Paper
Published in Nano Letters, 2025
Fast-ion implantation of Nb-doped Cd3As2 thin films enhances the negative longitudinal magnetoresistance signature of the chiral anomaly by more than 100% relative to pristine films while maintaining crystallinity, establishing high-energy implantation as a route to chiralitronic properties.
Recommended citation: Mandal, M.†, Rha, E.†, Chotrattanapituk, A.†, Cordova Carrizales, D.†, Lygo, A., Woller, K.B., Cheng, M., Okabe, R., Zhu, G., Kishida, S., Mak, K., Fu, C.L., Michalopoulos, S., Liu, C., Wu, L., Zhu, Y., Stemmer, S., & Li, M. (2025). Tuning Chiral Anomaly Signature in a Dirac Semimetal via Fast-Ion Implantation. Nano Letters 25, 51, 17571–17577.
Download Paper
Published in Materials Today, 2025
A perspective assessing the economic and environmental sustainability of quantum materials, examining element criticality, cost, and supply considerations for the materials that underpin quantum technologies.
Recommended citation: Boonkird, A.†, Cheng, M.†, Chotrattanapituk, A.†, Cordova Carrizales, D., Okabe, R., Drucker, N.C., Mandal, M., Nguyen, T., Yeo, J., Belosevich, V., Spero, E., Ortiz, C., Ma, Q., Fu, L., Palacios, T., Niroui, F., & Li, M. (2025). Are Quantum Materials Economically and Environmentally Sustainable? Materials Today 90, 241-248.
Download Paper
Published in Nature Materials, 2025
SCIGEN enforces geometric constraints such as honeycomb and kagome lattices within diffusion-based generative models, generating ten million candidate compounds with Archimedean and Lieb lattices; over 10% pass multistage stability screening, and a GNN classifier detects magnetic ordering in 41% of DFT-relaxed structures.
Recommended citation: Okabe, R., Cheng, M., Chotrattanapituk, A., Mandal, M., Mak, K., Cordova Carrizales, D., Hung, N.T., Fu, X., Han, B., Wang, Y., Xie, W., Cava, R.J., Jaakkola, T.S., Cheng, Y., Li, M. (2025). Structural Constraint Integration in a Generative Model for the Discovery of Quantum Materials. Nature Materials 25, 223-230.
Download Paper
Published in Nature Materials, 2026
A Review of computational materials design over the past decades, from high-throughput forward machine learning and evolutionary algorithms to reinforcement learning and deep generative models, highlighting the shift from screening to inverse generation and the open challenges ahead.
Recommended citation: Cheng, M.†, Fu, C.†, Okabe, R.†, Chotrattanapituk, A.†, Boonkird, A., Hung, N.T., & Li, M. (2026). Artificial intelligence-driven approaches for materials design and discovery. Nature Materials 25, 174-190.
Download Paper
Published in arXiv, 2026
An ab initio quantum framework for the electromagnetic properties of functionally graded materials, whose aperiodic composition breaks Bloch’s theorem: modulated Bloch states, effective field equations, and a generalized WKB method valid in the fully quantum regime yield position-dependent conductivity and permeability.
Recommended citation: Landry, M.J.†, Okabe, R.†, Fu, C., & Li, M. (2026). Quantum Theory of Functionally Graded Materials. arXiv preprint arXiv:2603.03424.
Download Paper
Published in arXiv, 2026
Magnetic structure network (MSN), an E(3)-equivariant graph neural network trained on experimentally determined MAGNDATA structures, predicts collinear and non-collinear magnetic structures from atomic coordinates using a primitive modulated structure representation that unifies commensurate and incommensurate orders.
Recommended citation: Chotrattanapituk, A.†, Okabe, R.†, Rha, E., Al-Hinai, M., Jiang, E., Pajerowski, D., Cheng, Y., Turner, J.J., & Li, M. (2026). Universal Magnetic Structure Prediction from Atomic Coordinates with Near-Experimental Accuracy. arXiv preprint arXiv:2605.16230.
Download Paper
Published in arXiv, 2026
An LLM-based agentic workflow that autonomously plans, runs, and analyzes quantum sensing experiments on nitrogen-vacancy centers in diamond, together with offline benchmarks that evaluate the agent’s scientific reasoning.
Recommended citation: Isogawa, T.†, Okabe, R.†, Phadetsuwannukun, N., Li, M., & Cappellaro, P. (2026). Agentic AI for Scientific Reasoning in Autonomous Quantum Sensing Experiments. arXiv preprint arXiv:2607.25145.
Download Paper
Published in Journal of Magnetic Resonance, 2026
A theoretical framework explaining why the SLAP solvent-suppression scheme outperforms MISSISSIPPI in solid-state NMR: MISSISSIPPI is limited by solvent-signal refocusing, whereas SLAP circumvents echo formation by design, confirmed by simulations and 1H-detected experiments on GB1 at 60 kHz MAS.
Recommended citation: Matsunaga, T.†, Okabe, R.†, Liu, Y., Shigemitsu, Y., & Ishii, Y. (2026). A theoretical framework for efficient solvent suppression in solid-state NMR: Circumventing solvent-signal refocusing by adiabatic-inversion-based dephasing. Journal of Magnetic Resonance 392, 108183.
Download Paper
Published:
Poster presentation on the development of suppression pulse with adiabatic pulse for solid-state NMR experiments.
Published:
Poster presentation on the development of suppression pulse with adiabatic pulse and its application for biological solid-state NMR experiments.
Published:
Poster presentation on theoretical explanation of new solvent suppression scheme with adiabatic pulse and its application for solid-state NMR experiments.
Published:
Oral presentation on the application of radiation detection materials for radiation mapping using machine learning techniques.
Published:
Poster presentation on machine learning approaches for predicting gamma phonons from atomic coordinates.
Published:
Poster presentation on virtual node augmented machine learning for material property prediction at the MRS Spring Meeting.
Published:
Oral presentation on advancing quantum material discovery through structural constraint integration in generative models at the Competing Orders in Quantum Materials conference.
Published:
Poster presentation on virtual node augmented machine learning approaches for material property prediction.
Published:
Invited talk on structural constraint integration in generative models for quantum material discovery at the Quantum Materials for Emergent Applications conference.
Published:
Invited talk on machine learning approaches for studying quantum material properties and quantum material discovery.
Published:
Oral presentation on large language model-guided prediction approaches for quantum materials synthesis.
Published:
Oral presentation on structural constraint integration in generative models for quantum material discovery at the MRS Fall Meeting.
Published:
Graduate Student Award Talk and Poster presentation on advancing quantum material discovery through structural constraint integration in generative models.
Published:
Poster presentation on structural constraint integration in generative models for the discovery of quantum material candidates.
Published:
Presentation on structural constraint integration in generative models for quantum material discovery, focusing on advanced machine learning approaches for materials prediction.
Published:
Invited talk on advancing quantum material discovery with geometric machine learning.
Published:
Oral presentation on structural constraint integration in a generative model for the discovery of quantum materials.
Published:
Tutorial session on generative AI for physics, from models to materials.
Published:
Invited talk on accelerating quantum material discovery with machine learning, from property prediction to materials design.
Published:
Invited exhibition at the STEM showcase presented by the Consul General of Japan in Boston and the Museum of Science.