YIYasuhiko Igarashi

Yasuhiko Igarashi

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yasuhiko Igarashi has a total of 86 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A New Framework for Multiline Analysis Combined Kernel Principal Component Analysis and Kernel Shapley Additive Explanations: A Case of NGC 1068 ALMA Band 3 Data

    by Hiroma Okubo, Tsutomu T. Takeuchi, Shotaro Akaho, Toshiki Saito, Yasuhiko Igarashi, Nario Kuno, Nanase Harada, Akio Taniguchi, Shuro Takano, Taku Nakajima

    We present a new framework for multiline analysis that combines kernel principal component analysis (Kernel PCA), an unsupervised machine learning method, and Kernel Shapley Additive Explanations (SHAP), an explainable artificial intelligence technique. To enable a comparison with PCA-based studies, which have been widely used in multiline analyses, we apply our framework to integrated intensity maps of 13 molecular lines from Atacama Large Millimeter/submillimeter Array Band 3 archival data of the nearby galaxy NGC 1068. Previous PCA-based studies of NGC 1068 reported that physically meaningful structures are mainly captured up to the second component. In contrast, our framework suggests that the features up to the third component are physically meaningful, whereas the physical meaning of the fourth component still requires further discussion. Furthermore, by comparing the results obtained from our framework with molecular column densities derived from local thermodynamical equilibrium analysis, we suggest that the abundance of HCO + may be relatively enhanced in the molecular outflow region extending to a radius of about 400 pc from the galactic center, likely due to the effects of ultraviolet radiation and highly dense gas. These results show that our framework can provide data-driven insights into physical and chemical features that have not been clearly identified in previous studies. It also provides an efficient tool for interpreting the rapidly increasing amount of multiline observational data.

  • Open Access

    Dictionary learning-based screening of layered materials via interface Fermi surface matching

    by Yuta Mizutori, Kodchakorn Simalaotao, Yuto Shimazaki, Yoshio Miura, Yuya Sakuraba, Yuma Iwasaki, Yasuhiko Igarashi

    Novel materials for spintronic devices require not only bulk electronic properties but also electronic structures compatible with magnetic/nonmagnetic interfaces. First-principles calculations have revealed the importance of electron band matching (EBM) at the Fermi energy for transport properties such as giant magnetoresistance (GMR). However, direct evaluation of ballistic conductance in GMR devices using first-principles calculations is computationally expensive and unsuitable for high-throughput screening. Here, we propose a machine learning framework to predict ballistic conductance using image representations of the Fermi surface similarity between magnetic and nonmagnetic materials. The images are decomposed into dictionary atoms, and the resulting feature vectors are subjected to regression analysis, with Gaussian process regression achieving the highest accuracy among the various models. Our results demonstrate that the proposed method effectively captures interfacial features essential for electron transport and provides a rapid means to screen material combinations with large EBM. This framework offers a practical step toward realizing material informatics for spintronics, enabling efficient exploration of heterogeneous material combinations for next-generation GMR devices.

  • Open Access

    Anomaly detection of fermi surface morphology in Co2MnGaxGe1-x via interpretable machine learning

    by Daichi Ishikawa, Kentaro Fuku, Yoshio Miura, Yasuhiko Igarashi, Yuma Iwasaki, Yuya Sakuraba, Koichiro Yaji, Alexandre Lira Foggiatto, Takahiro Yamazaki, Naoka Nagamura, et al.

    The Fermi surface provides indispensable insights into the electronic structure of materials. Here, we present a robust analysis framework employing an interpretable machine learning approach to investigate Fermi surfaces. Complex Fermi surface images of the Heusler alloy Co 2 MnGa x Ge 1−x , along with corresponding spin polarization, were analyzed using simple principal component analysis (PCA). Our results reveal that pronounced “jumps” in the PCA space correlate strongly with extrema and inflection points in the spin polarization. Notably, compositions near Ga = 0.94–0.95 exhibit significant changes attributable to the emergence of nodal lines. And the position of nodal lines in momentum space were automatically detected by differential analysis of outlier. Robustness evaluations demonstrate that our method remains effective even under conditions of increased image broadening and noise, mimicking ARPES experimental data. This method can contribute to the analysis of large-scale datasets by detecting non-systematic outliers.

  • Open Access

    A data-driven approach to control stimulus responsivity of functional polymer materials: predicting thermoresponsive color-changing properties of polydiacetylene

    by Risako Shibata, Nano Shioda, Hiroaki Imai, Yasuhiko Igarashi, Yuya Oaki

    Stimulus-responsive color-changing properties of layered polydiacetylene were controlled by a data-driven approach based on small experimental data. Such method can accelerate dynamic properties of functional polymer materials.


  • Open Access

    Networking autonomous material exploration systems through transfer learning

    by Naoki Yoshida, Yutaro Iwabuchi, Yasuhiko Igarashi, Yuma Iwasaki

    Autonomous material exploration systems that integrate robotics, material simulations, and machine learning have advanced rapidly in recent years. Although their number continues to grow, these systems currently operate in isolation, limiting the overall efficiency of autonomous material discovery. In analogy to how human researchers advance materials science by sharing knowledge and collaborating, autonomous systems can also benefit from networking and knowledge exchange. Here, we propose a framework in which multiple autonomous material exploration systems form a network via transfer learning, selectively utilizing relevant knowledge from other systems in real time. We demonstrate this approach using three distinct autonomous systems and show that such networking significantly enhances the efficiency of material discovery. Our results suggest that the proposed framework can enable the development of large-scale autonomous material exploration networks, ultimately accelerating progress in material development.


  • Open Access

    Domain-specific simulated data enhances knife-mark noise suppression in microscopy images of materials

    by Masato Suzuki, Yasuhiko Igarashi

    Accurate quantitative analysis of material microstructures from images is often hindered by noise and artifacts generated during sample preparation. While deep learning is a promising approach for this challenge, preparing the large amount of ‘supervised data’ (labeled real images) required for training poses a significant barrier in material science. This study proposes and validates a simulation-driven learning paradigm where a deep learning model is trained exclusively on simulated images that mimic the key features of target structures and noise, serving as a powerful solution to this data scarcity problem. As a specific case study, we applied this paradigm to the removal of ‘knife-mark noise’ from cross-sectional images of rubber materials to enable accurate filler region segmentation. In evaluations using simulated data, the proposed method showed superior performance across all the metrics (PSNR, SSIM, and MAE) compared with conventional methods such as the median filter and TV reconstruction, as well as a U-Net model trained on general-purpose Gaussian noise. More importantly, the model also performed effectively on real images, despite being trained solely on simulated data. It successfully removed both knife-marks and material-derived background textures, which demonstrates the viability of simulation-driven learning to overcome the need for manually annotated datasets. This work highlights the power of task-specific simulations as a practical alternative to manual data annotation in quantitative materials analysis.

  • Open Access

    A Seafloor Pressure Sensor Effectiveness Evaluation in a Tsunami Height Estimation Model Using Gaussian Process Regression with Automatic Relevance Determination

    by Yutaro Iwabuchi, Toshitaka Baba, Takane Hori, Masato Okada, Yasuhiko Igarashi

    To meet the growing need for accurate and timely tsunami height predictions, a database comprising 3480 high-precision tsunami simulation scenarios for the Nankai Trough was constructed in this study. The database includes the Dense Oceanfloor Network for Earthquakes and Tsunamis (DONET) seafloor pressure sensor data and the maximum tsunami heights for 19 coastal cities. Gaussian process regression with automatic relevance determination (ARD) was used to quantitatively evaluate the effectiveness of each sensor location. In this framework, the ARD assigns a hyperparameter that functions as an indicator of the contribution of each sensor to the prediction. The proportion of this hyperparameter reflects the effectiveness of each sensor during the prediction process. The results demonstrated that removing the 20 least effective sensors (as identified by the ARD) led to an 11% increase in the estimation error, whereas removing the 10 most effective sensors resulted in a 38% increase. These results demonstrate that the proposed method enables the optimization of the sensor placement process and allows for a prior evaluation of the trade-off between the number of sensors and achieved prediction accuracy. This method offers a robust framework for optimizing observation networks, enhancing the accuracy of tsunami predictions, and supporting future disaster risk reduction.


  • Open Access

    Data-scientific validation of prediction models for the controlled syntheses of exfoliated nanosheets

    by Yuka Kitamura, Yuki Namiuchi, Hiroaki Imai, Yasuhiko Igarashi, Yuya Oaki

    Data-scientific validation is demonstrated on prediction models for the yield and size control of 2D materials. The significance of data size, descriptor visualizing method, and domain knowledge is studied in sparse modeling for small data.


  • Open Access

    Confidence evaluation for feature selection in expanded feature space based on density of states

    by Koki Obinata, Yasuhiko Igarashi, Kenji Nagata, Keitaro Sodeyama, Masato Okada

    In materials informatics, feature selection and model selection are utilized in the knowledge extraction process, and the confidence evaluation of the selection result is crucial for ensuring the reliability of the extracted knowledge. In this study, we propose a novel method to quantitatively evaluate the significance of low-dimensional models obtained from an expanded feature space using the density of states (DoS) for the evaluation metrics. This method allows us to compare the performance of the selected model to those of other models and evaluate its significance. We further propose an evaluation method for feature importance based on marginal posterior probabilities using the Bayesian model averaging (BMA) framework, which considers all models. We demonstrate the effectiveness of our proposed methods through their application to a crystal structure dataset. Our results show that the DoS analysis reveals the presence of a large number of models with a comparable performance with the best model reported in a previous research work. This suggests that knowledge extracted from a single selected model can be unreliable and that considering other models is crucial. We also show that the BMA-based feature importance evaluation provides valuable insights into the importance of features, highlighting both primary features and functional forms. In addition, we demonstrate that the LASSO + L0 method commonly used in existing research deteriorates the search space for model selection. Our findings suggest that our proposed methods provide valuable tools for assessing the significance of low-dimensional models and extracting knowledge from large-scale data in materials informatics.