Sergei Manzhos 研究室

主宰者：Sergei Manzhos

東京工業大学

AI 要約（直近 5 年の研究成果）

本研究室は、機械学習を用いた材料物性の予測と設計に関する研究を展開しています。主な研究の問いは、化学組成と構造から材料や分子の性質を効率的に予測し、新しい機能性材料を設計することです。ニューラルネットワークやガウス過程回帰などの機械学習手法を、計算化学と組み合わせることで、有機電子材料や電池材料など、様々な応用分野に向けた材料探索を行っています。特に、限られたデータから過学習を避けながら正確な予測を行うモデルの開発に注力しています。実験的アプローチとしては、実際に新規材料を合成・評価する研究も並行して進めています。有機半導体や電気化学触媒などの合成、および物理的・電気的特性の測定を通じて、計算予測の妥当性を検証しています。一方、理論的には密度汎関数理論を基盤とした計算手法や、キネティックエネルギー汎関数の開発にも取り組んでおり、大規模系のシミュレーションに必要な新しい理論的ツールの構築を目指しています。これらの研究を通じて、機械学習の実用的な限界や最適化手法が明らかになりつつあります。特に高次元の特徴空間においてカーネル法が低次多項式回帰に退化する現象や、ニューラルネットワークの層数と過学習の関係など、機械学習手法の根本的な性質に関する知見が蓄積されています。こうした基礎的な理解に基づいて、より信頼性の高い材料予測と設計システムの構築を進めています。

※ AI（Claude）が、公開されている論文要旨から研究の問い・手法・主要な発見を事実情報として抽出・再構成して自動生成しています。誤りを含む可能性があるため、正確性は研究室公式情報でご確認ください。

外部リンク

研究成果（100 件）

[2026] Gaussian Process Regression–Neural Network Hybrid with Optimized Redundant Coordinates: A New Simple Yet Potent Tool for Scientist's Machine Learning Toolbox
DOI: https://doi.org/10.1002/aidi.202500199
[2026] Informatics-Guided Computational Design of Polyaromatic Hydrocarbons Suitable for Use as Hole Transport Materials
DOI: https://doi.org/10.1021/acs.jcim.6c01380
[2026] Macroscopically reversible modulation of the surface mechanical response of rutile TiO2 via transient lithiation
DOI: https://doi.org/10.1016/j.ceramint.2026.04.285
[2026] Informatics-GuidedComputational Design of PolyaromaticHydrocarbons Suitable for Use as Hole Transport Materials
DOI: https://doi.org/10.1021/acs.jcim.6c01380.s001
[2026] The role of bonding vs. nonbonding interactions and minute geometry changes on the optical spectra of charge transfer nanoaggregates computed with TD-DFTB.
[2025] Methods for faster, interpretable and portable machine learning
[2025] A novel encoding method for high-dimensional categorical data for electricity demand forecasting in distributed energy systems
[2025] Machine learning-guided construction of an analytic kinetic energy functional for orbital free density functional theory
DOI: https://doi.org/10.1088/2632-2153/ade7ca
[2025] Effects of nonlinearity and inter-feature coupling in machine learning studies of Nb alloys with center-environment features
DOI: https://doi.org/10.20517/jmi.2025.05
[2025] A New Disposable Paper-Based Chemosensor for the Rapid and Direct Detection of Hexavalent Chromium in Aqueous Media
DOI: https://doi.org/10.1007/s41664-025-00380-z

続きを表示（残り 90 件）

[2025] A novel encoding method for high-dimensional categorical data for electricity demand forecasting in distributed energy systems
DOI: https://doi.org/10.1016/j.apenergy.2025.125989
[2025] Modeling of microstructured ceramics – from large-scale molecule dynamics to large-scale electronic structure
[2025] Accelerated Development of Novel Biomass-Based Polyurethane Adhesives via Machine Learning
DOI: https://doi.org/10.1021/acsami.4c20371
[2025] Kernel regression methods for prediction of materials properties: Recent developments
DOI: https://doi.org/10.1063/5.0242118
[2025] Exploring the electronic properties of carbon nanoflake-based charge transport materials for perovskite solar cells: a computational study
DOI: https://doi.org/10.1039/d4cp04608k
[2025] On the Sufficiency of a Single Hidden Layer in Feed-Forward Neural Networks Used for Machine Learning of Materials Properties
DOI: https://doi.org/10.3390/physchem5010004
[2025] Gaussian Process Regression – Neural Network hybrid with optimized redundant coordinates: a new simple yet potent tool for scientist’s machine learning toolbox
[2025] Neural networks for neurocomputing circuits: A computational study of tolerance to noise and activation function non-uniformity when machine learning materials properties
DOI: https://doi.org/10.1016/j.aichem.2025.100099
[2025] Comparison of Voronoi Tessellation‐Derived and Molecular Dynamics‐Derived Atomistic Models of Polycrystalline Titania: A Computational Study of Structures, Band Structures, and Mechanical Properties
DOI: https://doi.org/10.1002/adts.202501245
[2025] Large-scale density functional based methods for atomistic modeling of large scale phenomena
[2024] Machine learning of properties of lead-free perovskites with a neural network with additive kernel regression-based neuron activation functions
DOI: https://doi.org/10.1557/s43580-023-00749-1
[2024] Machine learning the screening factor in the soft bond valence approach for rapid crystal structure estimation
DOI: https://doi.org/10.1039/d4dd00152d
[2024] Degeneration of kernel regression with Matern kernels into low-order polynomial regression in high dimension
DOI: https://doi.org/10.1063/5.0187867
[2024] Significantly Improved Stability of Carbon/Air Secondary Battery System By Separating Carbon Deposition Area
DOI: https://doi.org/10.1149/ma2024-02483400mtgabs
[2024] Concept and Advantages of Carbon/Air Secondary Battery System as a Fixed Compact Power Storage with Large Capacity
DOI: https://doi.org/10.1149/ma2024-02483469mtgabs
[2024] Low Band Gap Furan‐Flanked Diketopyrrolopyrrole‐Naphthobisthiadiazole Based Conjugated Polymer/Stretchable Blend for Organic Field Effect Transistors
DOI: https://doi.org/10.1002/aelm.202400614
[2024] A machine-learned kinetic energy model for light weight metals and compounds of group III-V elements
DOI: https://doi.org/10.1088/2516-1075/ad7e8d
[2024] Bandstructure modulation and molecular adsorption properties of zirconia nanoparticles: a large-scale electronic structure study
[2024] Diketopyrrolopyrrole‐Dioxo‐Benzodithiophene‐Based Multifunctional Conjugated Polymers for Organic Field‐Effect Transistors and Perovskite Solar Cells
DOI: https://doi.org/10.1002/solr.202470143
[2024] Computational Investigation of the Potential and Limitations of Machine Learning with Neural Network Circuits Based on Synaptic Transistors
DOI: https://doi.org/10.1021/acs.jpclett.4c01413
[2024] Machine learning with kernel methods in high dimensional spaces
[2024] Diketopyrrolopyrrole‐Dioxo‐Benzodithiophene‐Based Multifunctional Conjugated Polymers for Organic Field‐Effect Transistors and Perovskite Solar Cells
DOI: https://doi.org/10.1002/solr.202400185
[2024] Effects of Nanosizing of Zirconia and Bandstructure Modulation on Catalytic Activity: Insights from a Combined Density Functional Tight Binding – Order(N) Density Functional Theory Study
[2024] Modelling of Natural-Like Grain Generation of TiO2 and its effect on Band Structures
[2024] Reliable machine learning from sparse data in high dimension with additive kernel based methods
[2024] Natural-like generation of grain boundary models and the combined effects of microstructural elements and lithiation on the plastic behavior of TiO2: A computational study
DOI: https://doi.org/10.1016/j.commatsci.2024.112989
[2024] Natural-like generation of grain boundary models and the combined effects of microstructural elements and lithiation on the plastic behavior of TiO2: a computational study
[2024] N‐DMBI Doping of Carbon Nanotube Yarns for Achieving High n‐Type Thermoelectric Power Factor and Figure of Merit
DOI: https://doi.org/10.1002/smtd.202301387
[2024] Insightful machine learning beyond traditional neural networks and kernel regression
[2024] Modelling of CO/CO2 Electrode Reactions in Carbon/Air Secondary Battery System
[2024] Modulation of Molecular Adsorption Properties of Zirconia Nanoparticles: A Density Functional Tight Binding Theory Study
[2024] Beyond neural networks and kernel regression: hybrid methods for machine learning from sparse data in high-dimensional spaces
[2023] Liquid‐State Dithiocarbonate‐Based Polymeric Additives with Monodispersity Rendering Perovskite Solar Cells with Exceptionally High Certified Photocurrent and Fill Factor
DOI: https://doi.org/10.1002/aenm.202203742
[2023] Atoms, dimers, and nanoparticles from orbital-free density-potential-functional theory
DOI: https://doi.org/10.1103/physreva.108.062802
[2023] (Keynote) Oxygen Reduction and Evolution Reactions on Faceted MnxCo1-XFe2O4 Nanoparticles Prepared By Induction-Coupled Plasma
DOI: https://doi.org/10.1149/ma2023-02582788mtgabs
[2023] Two Years of PhysChem: Current Status and Future Developments
DOI: https://doi.org/10.3390/physchem4010001
[2023] Machine learning of kinetic energy densities with target and feature smoothing: Better results with fewer training data
DOI: https://doi.org/10.1063/5.0175689
[2023] A controlled study of the effect of deviations from symmetry of the potential energy surface (PES) on the accuracy of the vibrational spectrum computed with collocation
DOI: https://doi.org/10.1063/5.0182373
[2023] Effect of naturally generated microstructure of a ceramic on ion transport: lithiation of titania
[2023] Neural networks with optimized neuron activation functions and without nonlinear optimization or how to prevent overfitting, cut CPU cost and get physical insight all at once
[2023] Neural networks with rules-based parameters and without nonlinear optimization: comparison of fixed-shaped and optimized neuron activation functions
[2023] Neural Network with Optimal Neuron Activation Functions Based on Additive Gaussian Process Regression
DOI: https://doi.org/10.1021/acs.jpca.3c02949
[2023] Neural networks without nonlinear optimization and with optimized neuron activation functions built with Gaussian processes
[2023] Orders-of-coupling representation achieved with a single neural network with optimal neuron activation functions and without nonlinear parameter optimization
DOI: https://doi.org/10.1016/j.aichem.2023.100013
[2023] Orders of coupling representations as a versatile framework for machine learning from sparse data in high-dimensional spaces
DOI: https://doi.org/10.1016/j.aichem.2023.100008
[2023] Hybrid Density Functional Tight Binding (DFTB)─Molecular Mechanics Approach for a Low-Cost Expansion of DFTB Applicability
DOI: https://doi.org/10.1021/acs.jctc.3c00310
[2023] Neural networks with additive Gaussian processes based neuron activation functions: combining high expressive power of a NN with robustness of a linear regression
[2023] Hybrid models combining neural networks (NN), Gaussian process regressions (GPR), and high-dimensional model representations (HDMR) for more powerful machine learning
[2023] Factors affecting the techno-economic and environmental performance of on-grid distributed hydrogen energy storage systems with solar panels
[2023] A local Gaussian Processes method for fitting potential surfaces that obviates the need to invert large matrices
DOI: https://doi.org/10.1016/j.jms.2023.111774
[2023] Computation-assisted and -guided development of renewable energy technologies
[2023] Clarifying the effects of nanostructured porosity of silicon on the band gap and band alignment: a computational study
[2023] Beyond silicon solar cells
[2023] Factors affecting the techno-economic and environmental performance of on-grid distributed hydrogen energy storage systems with solar panels
DOI: https://doi.org/10.1016/j.energy.2023.126736
[2023] The loss of the property of locality of the kernel in high-dimensional Gaussian process regression on the example of the fitting of molecular potential energy surfaces
DOI: https://doi.org/10.1063/5.0136156
[2023] Nano-scale smooth surface of the compact-TiO 2 layer via spray pyrolysis for controlling the grain size of the perovskite layer in perovskite solar cells
DOI: https://doi.org/10.1039/d3ra05547g
[2023] Surface engineering of two-dimensional hexagonal boron-nitride for optoelectronic devices
DOI: https://doi.org/10.1039/d3nr03864e
[2023] Clarifying the effects of nanoscale porosity of silicon on the bandgap and alignment: a combined molecular dynamics–density functional tight binding computational study
DOI: https://doi.org/10.1039/d3cp00633f
[2022] Investigation of expressive power of a neural network architecture suited for optical neural networks
DOI: https://doi.org/10.1117/12.2643705
[2022] Non-invasive improvement of machining by reversible electrochemical doping: A proof of principle with computational modeling on the example of lithiation of TiO2
DOI: https://doi.org/10.1016/j.matchemphys.2022.127183
[2022] Tetramethylammonium Iodide Additive for Enhancing the Charge Carrier Mobilities of <scp>Diketopyrrolopyrrole‐Based</scp> Conjugated Polymer in Ambipolar Organic <scp>Field‐Effect</scp> Transistors†
DOI: https://doi.org/10.1002/cjoc.202200678
[2022] Reversible electrochemical lithiation as a way to facilitate the machining of ceramics: a computational study
[2022] Investigation of expressive power of a neural network architecture suited for optical neural networks
[2022] Optimization of hyperparameters of Gaussian process regression with the help of а low-order high-dimensional model representation: application to a potential energy surface
DOI: https://doi.org/10.1007/s10910-022-01407-x
[2022] Bottom gate top contact organic transistors using thiophene and furan flanked diketopyrrolopyrrole polymers and its comparative study
DOI: https://doi.org/10.1088/2058-8585/ac8887
[2022] Density functional tight binding modeling of porous silicon for all-silicon tandem solar cells
[2022] Effect of a weak magnetic field on ductile-brittle transition in micro-cutting of single-crystal calcium fluoride
[2022] The Role of Local DFT+U Minima in the First-Principles Modeling of the Metal–Insulator Transition in Vanadium Dioxide
DOI: https://doi.org/10.1021/acs.jpca.2c03097
[2022] Fluorenone and triphenylamine based donor–acceptor–donor (D–A–D) for solution-processed organic light-emitting diodes
DOI: https://doi.org/10.1088/2058-8585/ac6b6d
[2022] Advanced Machine Learning Methods for Learning from Sparse Data in High-Dimensional Spaces: A Perspective on Uses in the Upstream of Development of Novel Energy Technologies
DOI: https://doi.org/10.3390/physchem2020006
[2022] Effective passivation of TiO2/Si by interlayer SiOx controlled by scanning zone annealing for perovskite/Si tandem solar cell
DOI: https://doi.org/10.1016/j.solener.2022.03.056
[2022] Directional Carrier Polarity Tunability in Ambipolar Organic Transistors Based on Diketopyrrolopyrrole and Bithiophene Imide Dual-Acceptor Semiconducting Polymers
DOI: https://doi.org/10.1021/acs.chemmater.1c04258
[2022] Modeling of the Effects of Porosity and Passivation on Porous Silicon
[2022] Study on Activity of Citric Acid-decorated Carbon Nanotubes for Oxygen Reduction Reaction
[2022] Welcome to Physchem: Status and Prospects
DOI: https://doi.org/10.3390/physchem2010002
[2022] Roadmap on Machine learning in electronic structure
DOI: https://doi.org/10.1088/2516-1075/ac572f
[2022] Random Sampling High Dimensional Model Representation Gaussian Process Regression (RS-HDMR-GPR) for representing multidimensional functions with machine-learned lower-dimensional terms allowing insight with a general method
[2022] Easy representation of multivariate functions with low-dimensional terms via Gaussian process regression kernel design: applications to machine learning of potential energy surfaces and kinetic energy densities from sparse data
DOI: https://doi.org/10.1088/2632-2153/ac4949
[2022] Non-parametric machine learning for orbital-free DFT simulations
[2021] Theoretical Insight Into Diamond Doping and Its Possible Effect on Diamond Tool Wear During Cutting of Steel
DOI: https://doi.org/10.3389/fmats.2021.806466
[2021] Effect of a weak magnetic field on ductile–brittle transition in micro-cutting of single-crystal calcium fluoride
DOI: https://doi.org/10.1016/j.jmst.2021.09.049
[2021] Structured Gaussian Process Regression models to address difficulties in modeling very high dimensional data with product kernels
[2021] Theoretical insight into diamond doping and its possible effect on diamond tool wear during cutting of steel
[2021] Easy construction of representations of multivariate functions with low-dimensional terms via Gaussian process regression kernel design
[2021] Random Sampling High Dimensional Model Representation Gaussian Process Regression (RS-HDMR-GPR) for representing multidimensional functions with machine-learned lower-dimensional terms allowing insight with a general method
DOI: https://doi.org/10.1016/j.cpc.2021.108220
[2021] Carbon/air secondary battery system and demonstration of its charge-discharge
DOI: https://doi.org/10.1016/j.jpowsour.2021.230681
[2021] Insight with a black box method beyond automatic relevance determination with the help of high-dimensional model representation
[2021] Machine learning for orbital-free DFT
[2021] Tuning the Charge Carrier Polarity of Organic Transistors by Varying the Electron Affinity of the Flanked Units in Diketopyrrolopyrrole‐Based Copolymers
DOI: https://doi.org/10.1002/adfm.202106250
[2021] Structural Geometry Variation of 1,4-Naphthalene-Based Co-Polymers to Tune the Device Performance of PVK-Host-Based OLEDs
DOI: https://doi.org/10.3390/polym13172914

科研費（0 件）

まだデータがありません（KAKEN 取り込み後に表示）。

所属学会・役職（0 件）

まだデータがありません（学会データ連携後に表示）。

AI 要約（直近 5 年の研究成果）

外部リンク

関連研究室(8 件)

研究成果（100 件）

科研費（0 件）

所属学会・役職（0 件）