Catalysts constitute a core enabling technology for solving a wide range of societal challenges, including resource circulation, mitigation of global warming, and environmental purification. In recent years, data-science-based approaches, particularly machine learning (ML), have attracted significant attention as promising tools to accelerate catalyst development. Despite this expectation, however, there have been very few successful demonstrations in which ML has led to the discovery of genuinely novel catalysts. This limitation arises because newly discovered catalysts typically fall outside the scope of existing datasets and can be regarded as so-called “outliers.” Conventional ML models, which rely on interpolation within known data domains, are fundamentally incapable of making reliable extrapolative predictions for such outliers.

In this review, I first describe our strategy for addressing this challenge by adopting advanced ML methodologies specifically designed to enable extrapolative prediction beyond existing data distributions. I then present a representative example in which a closed-loop exploration framework—iteratively integrating ML-based predictions with experimental investigation—successfully led to the development of a novel multicomponent catalyst for the reverse water–gas shift (RWGS) reaction, which produces CO from a CO₂/H₂ mixed gas. This closed-loop, ML-guided approach demonstrates the potential to substantially accelerate catalyst discovery and, more broadly, to serve as a powerful paradigm for advancing diverse areas of materials development research.

Cellulose nanofibers (CNFs) exhibit broad and multimodal morphology distributions, for which mean descriptors alone are often insufficient to explain the properties of polymer composites. This issue is particularly pronounced for mechanically fibrillated CNFs, where coarse fractions and fine fibrils coexist and cause large variability in material performance. This review overviews a data driven analytical framework that combines optical sedimentation profiling with machine learning to rapidly and non destructively estimate specific surface area (SSA) and morphology related distribution information from sedimentation behaviors. Sedimentation profiles are represented as velocity indices and spatiotemporal heatmaps, which are analyzed using gradient boosting regression and convolutional neural networks to predict SSA with high accuracy. Furthermore, sedimentation heatmaps are exploited to infer aspect ratio distributions, enabling separation of coarse and fine fractions. By integrating the inferred morphology descriptors with chemical information derived from IR spectroscopy, the impact strength of polypropylene (PP)/CNF composites can be quantitatively explained. This approach enables composite design that explicitly considers morphology distributions and provides a practical materials DX platform for quality control, process development, and data driven materials selection.

This article showcases an example of infrared (IR) spectra analysis with PCA ToolBox. PCA Toolbox is an app designed for informatics analysis. A characteristic feature of PCA Toolbox is that it requires no command input, and users can operate it just using the mouse. With visual support features such as preview displays of data pretreatment, users can easily analyze data without requiring any expertise. Time-dependent IR spectra of binary mixture solution of oleic acid and ethanol were analyzed by PCA ToolBox to demonstrate how this app can be utilized to elucidate subtle but pertinent change in the spectral feature.

Vitamin A is an essential and important nutrient (preventive agent) for maintaining health that plays a wide range of roles in various bodily tissues. Vitamin A (retinoic acid, RA), is currently used in clinical practice as a therapeutic agent (anticancer agent) for patients with acute promyelocytic leukemia. Recently, the effects of vitamin A on the skin have been spotlighted and attracting attention. In this paper, we will discuss the skin science of vitamin A; 1) the circulation of vitamin A, 2) types of vitamin A and their effects on non-skin tissues, 3) the action of vitamin A on the skin and its mechanism, 4) β-carotene and atopic dermatitis, 5) the skin of type I diabetic mice with vitamin A deficiency, and 6) introduction of skin improving effects of p-aminophenol (p-DDAP, p-DAP) developed from RA derivatives. Our efforts are directed toward developing preventive and therapeutic drugs from vitamin A, which is versatile in maintaining healthy skin, and to contribute to improving the quality of life of healthy people and patients.