Keitaro Sodeyama | Searcharxiv

arXiv2026

Construction of a Battery Research Knowledge Graph using a Global Open Catalog

Battery research is a rapidly growing and highly interdisciplinary field, making it increasingly difficult to track relevant expertise and identify potential collaborators across institutional boundaries. In this work, we present a pipeline for constructing an author-centric knowledge graph of battery research built on OpenAlex, a large-scale open bibliographic catalogue. For each author, we derive a weighted research descriptors vector that combines coarse-grained OpenAlex concepts with fine-grained keyphrases extracted from titles and abstracts using KeyBERT with ChatGPT (gpt-3.5-turbo) as the backend model, selected after evaluating multiple alternatives. Vector components are weighted by research descriptor origin, authorship position, and temporal recency. The framework is applied to a corpus of 189,581 battery-related works. The resulting vectors support author-author similarity computation, community detection, and exploratory search through a browser-based interface. The knowledge graph is then serialized in RDF and linked to Wikidata identifiers, making it interoperable with external linked open data sources and extensible beyond the battery domain. Unlike prior author-centric analyses confined to institutional repositories, our approach operates at cross-institutional scale and grounds similarity in domain semantics rather than citation or co-authorship structure alone.

cs.CL↗

arXiv2024

Rapid and Robust construction of an ML-ready peak feature table from X-ray diffraction data using Bayesian peak-top fitting

To advance the development of materials through data-driven scientific methods, appropriate methods for building machine learning (ML)-ready feature tables from measured and computed data must be established. In materials development, X-ray diffraction (XRD) is an effective technique for analysing crystal structures and other microstructural features that have information that can explain material properties. Therefore, the fully automated extraction of peak features from XRD data without the bias of an analyst is a significant challenge. This study aimed to establish an efficient and robust approach for constructing peak feature tables that follow ML standards (ML-ready) from XRD data. We challenge peak feature extraction in the situation where only the peak function profile is known a priori, without knowledge of the measurement material or crystal structure factor. We utilized Bayesian estimation to extract peak features from XRD data and subsequently performed Bayesian regression analysis with feature selection to predict the material property. The proposed method focused only on the tops of peaks within localized regions of interest (ROIs) and extracted peak features quickly and accurately. This process facilitated the rapid extracting of major peak features from the XRD data and the construction of an ML-ready feature table. We then applied Bayesian linear regression to the maximum energy product $(BH)_{max}$, using the extracted peak features as the explanatory variable. The outcomes yielded reasonable and robust regression results. Thus, the findings of this study indicated that \textit{004} peak height and area were important features for predicting $(BH)_{max}$.

cond-mat.mtrl-sci↗